scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-08-28 04:24:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Merge branch 'dev' into codex/pulse-local-x-exports

Browse source
This commit is contained in:
Alireza Rezvani 2026-08-25 08:34:47 +02:00 • committed by GitHub
commit 22149f4c34
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
451 changed files with 27615 additions and 1070 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

131
.claude-plugin/marketplace.json
View file

@ -8,8 +8,8 @@
"homepage": "https://github.com/alirezarezvani/claude-skills",
"repository": "https://github.com/alirezarezvani/claude-skills",
"metadata": {
"description": "364 production-ready skills across 19 domains (engineering, engineering-core, marketing, product, c-level, c-level-agents, compliance-os, project management, RA/QM, business growth, finance, productivity, marketing top-level, research, research-ops, business-operations, commercial, markdown-html, loop-library, plus standards). 667 Python tools, 750 reference guides, 104 agents (cs-* + personas), 120 slash commands across 90 marketplace plugins. v2.11.2 vendors engineering/skillopt-sleep — a verbatim copy of microsoft/SkillOpt's stdlib-only skillopt_sleep engine + Claude Code plugin surface, giving a local agent a nightly gated self-improvement cycle (read-only session harvest -> mine -> offline replay -> held-out-gated CLAUDE.md/SKILL.md edits -> staged for explicit /skillopt-sleep adopt). productivity/fable-goal (unreleased, post-v2.11.1) converts a rambling description of a desired outcome into one polished /goal prompt for a fresh autonomous session. v2.11.1 turns product-team and project-management into agent-harness domains: fork-orchestrators with deterministic goal routers, a Jira MCP snapshot bridge (Kanban flow metrics + Monte Carlo forecasting), a delegation-governance loop gate, a continuous-discovery cadence tracker, and an Opportunity Solution Tree linter, with /cs:pm and /cs:product command families. v2.10.3 completes the markdown-html domain with md-slides — slide-deck converter (arrow-key / Space / PgDn / Home/End / P keyboard navigation + presenter mode with split-view clock + speaker notes + next-slide preview + URL-hash deep linking like #3 for direct slide jumps + @media print page-per-slide for browser-native PDF export). Reuses md-document's markdown parser; vanilla JS only (no framework runtime); Prism.js opt-in via --syntax. Joins md-review (v2.10.2 code-review converter), md-document (v2.10.1 long-form converter), and the v2.10.0 foundation (orchestrator + design-system). Compatible with Claude Code, Codex CLI, Gemini CLI, Cursor, OpenClaw, Hermes Agent, Mistral Vibe, and 5 more coding agents.",
"version": "2.11.2"
"description": "380 production-ready skills across 20 domains (engineering, engineering-core, marketing, product, c-level, c-level-agents, compliance-os, project management, RA/QM, business growth, finance, productivity, marketing top-level, research, research-ops, business-operations, commercial, markdown-html, loop-library, plus standards). 706 Python tools, 823 reference guides, 114 agents (cs-* + personas), 138 slash commands across 96 marketplace plugins. v2.11.2 vendors engineering/skillopt-sleep — a verbatim copy of microsoft/SkillOpt's stdlib-only skillopt_sleep engine + Claude Code plugin surface, giving a local agent a nightly gated self-improvement cycle (read-only session harvest -> mine -> offline replay -> held-out-gated CLAUDE.md/SKILL.md edits -> staged for explicit /skillopt-sleep adopt). productivity/fable-goal (unreleased, post-v2.11.1) converts a rambling description of a desired outcome into one polished /goal prompt for a fresh autonomous session. v2.11.1 turns product-team and project-management into agent-harness domains: fork-orchestrators with deterministic goal routers, a Jira MCP snapshot bridge (Kanban flow metrics + Monte Carlo forecasting), a delegation-governance loop gate, a continuous-discovery cadence tracker, and an Opportunity Solution Tree linter, with /cs:pm and /cs:product command families. v2.10.3 completes the markdown-html domain with md-slides — slide-deck converter (arrow-key / Space / PgDn / Home/End / P keyboard navigation + presenter mode with split-view clock + speaker notes + next-slide preview + URL-hash deep linking like #3 for direct slide jumps + @media print page-per-slide for browser-native PDF export). Reuses md-document's markdown parser; vanilla JS only (no framework runtime); Prism.js opt-in via --syntax. Joins md-review (v2.10.2 code-review converter), md-document (v2.10.1 long-form converter), and the v2.10.0 foundation (orchestrator + design-system). Compatible with Claude Code, Codex CLI, Gemini CLI, Cursor, OpenClaw, Hermes Agent, Mistral Vibe, and 5 more coding agents.",
"version": "2.12.0"
},
"plugins": [
{
@ -401,7 +401,7 @@
{
"name": "pw",
"source": "./engineering-team/playwright-pro",
"description": "Production-grade Playwright testing toolkit. 9 skills, 3 agents, 55 templates, TestRail + BrowserStack MCP integrations. Generate tests, fix flaky failures, migrate from Cypress/Selenium.",
"description": "Production-grade Playwright testing toolkit. 9 skills, 3 agents, 55 templates, plus optional (manually enabled) TestRail/BrowserStack integrations. Generate tests, fix flaky failures, migrate from Cypress/Selenium.",
"version": "2.9.0",
"author": {
"name": "Alireza Rezvani"
@ -982,6 +982,28 @@
],
"category": "development"
},
{
"name": "skill-doctor",
"source": "./engineering/skill-doctor",
"description": "Grade an agent setup from real conversation history — a rebuild of warpdotdev/common-skills' skill-doctor (MIT). Harvests recent local Claude Code and Codex sessions scoped to one repo, condenses and secret-redacts transcripts (12-pattern redactor, chmod-0600 artifacts, nothing uploaded), has the agent judge each transcript against two verbatim-preserved rubrics (efficiency, code quality — labels only), then runs a deterministic aggregation gate that derives every number from the label tables, refuses scores for unsampled sessions and suggestions that cite no scored session, and renders one self-contained zero-JS HTML report (dark-mode, print-to-PDF). Proposed skill edits stay staged as diffs until an explicit per-skill yes; zero suggestions is a valid, reportable success. Ships cs-skill-doctor agent, /cs:skill-doctor command, 3 stdlib tools, 3 references citing 7 sources each.",
"version": "2.11.2",
"author": {
"name": "Alireza Rezvani"
},
"keywords": [
"skill-doctor",
"skill-grading",
"session-mining",
"llm-as-judge",
"rubric-scoring",
"transcript-analysis",
"skill-coverage",
"secret-redaction",
"agent-evals",
"engineering"
],
"category": "development"
},
{
"name": "grill-me",
"source": "./engineering/grill-me",
@ -1226,6 +1248,24 @@
],
"category": "productivity"
},
{
"name": "swedish-mentor",
"source": "./productivity/swedish-mentor",
"description": "CEFR-leveled Swedish-learning mentor: two-question placement probe, listening-first learning paths, vetted YouTube/podcast catalog (SFI, Radio Sweden pa latt svenska, Klartext), never-invent-a-URL rule.",
"version": "2.11.2",
"author": {
"name": "mh-mansouri"
},
"keywords": [
"productivity",
"language-learning",
"swedish",
"cefr",
"sfi",
"mentor"
],
"category": "productivity"
},
{
"name": "landing",
"source": "./marketing/landing",
@ -1425,6 +1465,25 @@
],
"category": "research"
},
{
"name": "deepread",
"source": "./research/deepread",
"description": "Evidence-first reading of supplied documents. Five modes (quick/deep/map/feynman/book), claim-reason-evidence decomposition, confidence labels, evidence ledger, knowledge maps, Feynman teach-back.",
"version": "2.11.2",
"author": {
"name": "xiehuan123"
},
"keywords": [
"research",
"reading",
"deep-read",
"feynman",
"knowledge-map",
"evidence",
"comprehension"
],
"category": "research"
},
{
"name": "aeo",
"source": "./marketing-skill/skills/aeo",
@ -1903,6 +1962,72 @@
"collab-proof"
],
"category": "engineering"
},
{
"name": "human-gate",
"source": "./engineering/human-gate",
"description": "Human-verification gate for an agent loop: builds a single-file review page (the page itself makes no network request; a reviewed HTML artifact's own https: assets still load), collects batched feedback as structured batch.v1 data instead of chat prose, and refuses to close while a BLOCKER is open, the reviewer is unnamed, or nobody has reviewed. Non-blocking, headless-guarded, round-capped. Stdlib-only.",
"version": "1.0.0",
"author": {
"name": "Alireza Rezvani",
"url": "https://alirezarezvani.com"
},
"keywords": [
"human-in-the-loop",
"review-gate",
"sign-off",
"agent-loop",
"verification",
"batched-feedback",
"human-gate"
],
"category": "engineering"
},
{
"name": "agent-launcher-skills",
"source": "./agent-launcher",
"description": "Build, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs:goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).",
"version": "2.11.2",
"author": {
"name": "Alireza Rezvani"
},
"keywords": [
"claude-managed-agents",
"cma",
"agent-launcher",
"launch-your-agent",
"managed-agent",
"session-goal",
"grade-iterate",
"max-iterations",
"scheduled-deployment",
"run-without-you",
"byok",
"build-sheet",
"context-fork"
],
"category": "agent-development"
},
{
"name": "agent-memory",
"source": "./engineering/agent-memory",
"description": "A four-tier memory ladder for Claude Code where promotion is earned by recurrence, not asserted by confidence. L0 raw transcripts are never injected; L1 candidate atoms are gitignored and recalled on lexical relevance per prompt; L2 project context loads each session start; L3 stable persona is always loaded. L1 to L2 needs three distinct sessions spanning two distinct calendar days (a stated claim needs two; a verified claim is the only single-observation path); L2 to L3 needs two projects and thirty days. Two gates refuse rather than guess: a claim altered by the redaction pass never promotes on evidence alone, and a contradicted claim freezes until a human resolves it. Three hooks run the loop unattended and every one fails open. Nothing reaches a committed CLAUDE.md without an explicit human adopt. Ships 5 stdlib scripts, 3 hooks, a cs-memory-curator agent, /cs:memory, a JSON schema, and a 69-check validator. Concept from TencentCloud/TencentDB-Agent-Memory (MIT); no upstream code included.",
"version": "2.11.2",
"author": {
"name": "Alireza Rezvani"
},
"keywords": [
"agent-memory",
"memory-tiers",
"claude-md",
"hooks",
"session-memory",
"promotion-gates",
"provenance",
"redaction",
"engineering"
],
"category": "development"
}
]
}

87
.codex/skills-index.json
View file

@ -3,8 +3,44 @@
"name": "claude-code-skills",
"description": "Production-ready skill packages for AI agents - Marketing, Engineering, Product, C-Level, PM, and RA/QM",
"repository": "https://github.com/alirezarezvani/claude-skills",
"total_skills": 346,
"total_skills": 356,
"skills": [
{
"name": "agent-launcher-orchestrator",
"source": "../../agent-launcher/skills/agent-launcher-orchestrator",
"category": "agent-development",
"description": "Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account \u2014 \"build me an agent\", \"launch this as a managed agent\", \"run this on a schedule\", \"grade my agent against a rubric\", \"set up a nightly worker\". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview \u2192 stage-launch \u2192 grade-iterate \u2192 run-without-you \u2192 wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade\u2192iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs)."
},
{
"name": "grade-iterate",
"source": "../../agent-launcher/skills/grade-iterate",
"category": "agent-development",
"description": "Phase 3 of building a Claude Managed Agent \u2014 the bounded grade\u2192iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader), read each verdict, decide the next move (sharpen / re-run / promote to schedule), and once a version passes, run held-back eval cases in parallel. Use when the user says \"grade my agent\", \"make it pass the rubric\", \"iterate until it's good\", \"is it good enough\", or when the orchestrator routes phase=grade-iterate. outcome_builder.py builds the user.define_outcome payload (rubric required, max_iterations clamped 1..20 \u2014 never unbounded); verdict_reader.py reads the grader result and recommends the next move; eval_scaffold.py generates held-back cases + a parallel run plan (capped at the 25-thread CMA ceiling). Distinct from stage-launch (first launch) and run-without-you (scheduling)."
},
{
"name": "interview",
"source": "../../agent-launcher/skills/interview",
"category": "agent-development",
"description": "Phase 1 of building a Claude Managed Agent \u2014 interview the founder about the one job the agent should do, then produce a build sheet (CMA primitives table + v1/v2 deferrals + eval plan) WITHOUT needing their API key yet. Use when the user says \"help me scope an agent\", \"I have an idea for an agent\", \"what should this agent be\", or when the orchestrator routes phase=interview. Drives the six intake slots (job, trigger, inputs, actions, definition-of-done, recurrence) via AskUserQuestion, maps them to primitives with interview_planner.py, assembles build-sheet.json with build_sheet_builder.py, and validates limits with primitives_validator.py. Connectors are mockable in v0 (schema-true custom tools); real MCP servers become v1 deferrals. Distinct from stage-launch (which turns the sheet into payloads)."
},
{
"name": "run-without-you",
"source": "../../agent-launcher/skills/run-without-you",
"category": "agent-development",
"description": "Phase 4 of building a Claude Managed Agent \u2014 make it run without you. Turn a graded agent into a recurring scheduled deployment (POSIX-cron), an event-driven curl trigger, or confirmed on-demand use, then finalize the versioned roadmap. Use when the user says \"run it every morning\", \"put it on a schedule\", \"nightly\", \"weekly\", \"automate this\", \"make it recurring\", or when the orchestrator routes phase=run-without-you. deployment_builder.py builds the POST /v1/deployments payload (initial_events must include user.message; optionally nests a user.define_outcome so each firing self-grades); cron_validator.py validates the 5-field cron + IANA timezone and prints the wall-clock DST note; next_directions_writer.py writes NEXT-DIRECTIONS.md. No tool makes API calls \u2014 the deployment is created via BYOK curl. Distinct from grade-iterate (the in-session loop) and wrap-up (closeout)."
},
{
"name": "stage-launch",
"source": "../../agent-launcher/skills/stage-launch",
"category": "agent-development",
"description": "Phase 2 of building a Claude Managed Agent \u2014 turn a validated build sheet into exact API payloads and a resumable BYOK curl launch script, then launch (environment \u2192 agent \u2192 session \u2192 kickoff) using the founder's OWN Anthropic key. Use when the user says \"launch it\", \"deploy the agent\", \"create the agent now\", or when the orchestrator routes phase=stage-launch. payload_generator.py emits the four ordered payloads; launch_script_writer.py writes launch.sh that reads $ANTHROPIC_API_KEY at runtime and never embeds it; payload_validator.py runs a pre-launch check including an API-key-leak scan. No tool in this skill makes network calls \u2014 the user runs launch.sh themselves. Distinct from interview (planning) and grade-iterate (the outcome loop)."
},
{
"name": "wrap-up",
"source": "../../agent-launcher/skills/wrap-up",
"category": "agent-development",
"description": "Close out a launched Claude Managed Agent \u2014 recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained ./my-agent/agent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done."
},
{
"name": "business-growth-skills",
"source": "../../business-growth/skills/business-growth-skills",
@ -815,6 +851,12 @@
"category": "engineering-advanced",
"description": "Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library)."
},
{
"name": "agent-memory",
"source": "../../engineering/agent-memory/skills/agent-memory",
"category": "engineering-advanced",
"description": "Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead \u2014 or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it."
},
{
"name": "agent-workflow-designer",
"source": "../../engineering/skills/agent-workflow-designer",
@ -1049,6 +1091,12 @@
"category": "engineering-advanced",
"description": "Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw \u2014 chart scaffolding, values design, template patterns, dependency management, security hardening, and chart testing. Use when: user wants to create or improve Helm charts, design values.yaml files, implement template helpers, audit chart security (RBAC, network policies, pod security), manage subcharts, or run helm lint/test."
},
{
"name": "hivemind",
"source": "../../engineering/hivemind",
"category": "engineering-advanced",
"description": "Orchestrate free opencode workers from Claude Code to cut token costs. Use when delegating grunt work to a single worker or a parallel swarm (scout/coder/tester) with worktree isolation, benchmarking against opencode, or when the user says \"spawn a worker\", \"swarm\", \"delegate to opencode\", or \"/oc\"."
},
{
"name": "hub-init",
"source": "../../engineering/agenthub/skills/hub-init",
@ -1061,6 +1109,12 @@
"category": "engineering-advanced",
"description": "Show DAG state, agent progress, and branch status for an AgentHub session. Use when the user runs /hub:hub-status or asks how the AgentHub agents are doing."
},
{
"name": "human-gate",
"source": "../../engineering/human-gate/skills/human-gate",
"category": "engineering-advanced",
"description": "Runs the human-verification lane of an agent loop, and proves review happened before work is called done. Builds a single-file HTML review page, collects batched feedback as a structured artifact instead of chat prose, and runs a gate that refuses to close while a BLOCKER is open, the reviewer is unnamed, or nobody has reviewed at all. Use when a plan, spec, RFC, report, landing page, migration, or any irreversible action needs human sign-off before shipping, or on requests such as 'get sign-off', 'have someone check this', 'hold until reviewed', 'needs approval first'. NOT for making AI text sound human (use content-humanizer or behuman). NOT for reviewing code diffs (use md-review or code-reviewer)."
},
{
"name": "interview-system-designer",
"source": "../../engineering/skills/interview-system-designer",
@ -1217,6 +1271,12 @@
"category": "engineering-advanced",
"description": ">"
},
{
"name": "skill-doctor",
"source": "../../engineering/skill-doctor/skills/skill-doctor",
"category": "engineering-advanced",
"description": "Use when the user wants their agent setup graded from real conversation history, asks which installed skills are actually working, or wants evidence-backed skill edits \u2014 scores recent local Claude Code / Codex sessions against efficiency and code-quality rubrics, then drafts skill changes gated by a deterministic aggregator and renders one local shareable report."
},
{
"name": "skill-security-auditor",
"source": "../../engineering/skills/skill-security-auditor",
@ -1347,7 +1407,7 @@
"name": "stock-analysis",
"source": "../../finance/skills/stock-analysis",
"category": "finance",
"description": "Produce a rigorous, sector-relative, multi-factor fundamental analysis of a publicly listed company \u2014 Indian (NSE/BSE) or US/global. Use this skill whenever the user asks to analyse, research, evaluate, value, or \"look into\" a stock, ticker, or listed company; asks whether a business is fundamentally strong or weak, cheap or expensive; asks to compare two or more companies or benchmark one against its sector; mentions metrics like OPM, ROCE, ROE, ROIC, P/E, EV/EBITDA, free cash flow, NIM, GNPA, CASA, promoter holding or pledging; or shares an annual report, 10-K, concall transcript, or screener page and wants it interpreted. Use it too for accounting-quality and forensic questions \u2014 \"is the profit real\", \"are they cooking the books\", \"the cash flow doesn't match the profit\", \"why is profit rising but cash isn't\", \"should I worry about this company's accounting\", auditor qualifications, promoter pledging, or related-party concerns \u2014 which route to the forensic-only mode. Use it for **IPOs and not-yet-listed companies** too \u2014 \"should I apply to this IPO\", \"is this IPO worth it\", \"is the price band expensive\", DRHP/RHP or S-1 questions, grey market premium, anchor allotment, lock-in expiry \u2014 which route to the IPO mode. Use it even when the request sounds casual (\"is Infosys any good?\", \"thoughts on HDFC Bank?\", \"why is this company's margin so low?\"). Do not use it for personalised investment advice, portfolio allocation, or trading signals."
"description": "Produce a rigorous, sector-relative, multi-factor fundamental analysis of a publicly listed company \u2014 Indian (NSE/BSE) or US/global. Use when the user asks to analyse, research, evaluate, or value a stock, ticker, or listed company; asks whether a business is fundamentally strong, cheap, or expensive; compares companies or benchmarks one against its sector; or mentions OPM, ROCE, ROE, ROIC, P/E, EV/EBITDA, free cash flow, NIM, GNPA, CASA, promoter holding or pledging. Use it for accounting-quality and forensic questions \u2014 \"is the profit real\", \"why is profit rising but cash isn't\", auditor qualifications, related-party concerns \u2014 which route to the forensic-only mode, and for IPOs and not-yet-listed companies \u2014 \"should I apply to this IPO\", DRHP/RHP or S-1 questions, price band, grey market premium \u2014 which route to the IPO mode. Use it even when the request sounds casual (\"is Infosys any good?\"). Do not use it for personalised investment advice, portfolio allocation, or trading signals."
},
{
"name": "ab-test-setup",
@ -1389,7 +1449,7 @@
"name": "business-name-fit",
"source": "../../marketing-skill/skills/business-name-fit",
"category": "marketing",
"description": "Suggest, pick, or vet a business, startup, or product name that stays true to the founder's cultural origin while working professionally in the markets they want to sell into. Use whenever someone is naming a company, brand, or product and cares about how it lands across languages and regions \u2014 for example a name that sounds right at home but might read oddly to English speakers, or an authentic name they want to check before committing. Trigger this for any request about choosing a business name, checking if a name \"works\" abroad, spotting bad meanings in other languages, or making a name sound trustworthy in a specific market \u2014 even if the person doesn't say the word \"skill\"."
"description": "Suggest, pick, or vet a business, startup, or product name that stays true to the founder's cultural origin while working professionally in the markets they want to sell into. Use when someone is naming a company, brand, or product and cares about how it lands across languages and regions \u2014 for example a name that sounds right at home but might read oddly to English speakers, or an authentic name they want to check before committing. Trigger this for any request about choosing a business name, checking if a name \"works\" abroad, spotting bad meanings in other languages, or making a name sound trustworthy in a specific market \u2014 even if the person doesn't say the word \"skill\"."
},
{
"name": "campaign-analytics",
@ -1997,18 +2057,18 @@
"category": "research",
"description": "Run a disciplined, multi-source research investigation for a high-stakes question or decision \u2014 fan-out web search across many channels, parallel sub-agents, source triangulation (each claim backed by \u22653 independent sources), an adversarial review pass, and every source saved to its own file with verbatim quotes for reuse. Use when a low-quality answer is expensive: strategy work, comparing N products/methods/markets, validating a hypothesis with external data, or mapping how a field works. NOT for quick fact-checks (answer directly), structured 12-dimension competitor scoring (use competitive-teardown), or fast topic overviews where the decision risk is low (use the research router instead)."
},
{
"name": "deepread",
"source": "../../research/deepread",
"category": "research",
"description": "Use when the user asks to deeply read a book, article, PDF, or document set; extract claims and evidence; build a knowledge map; or learn through Feynman explanation and recall. Covers quick, deep, map, Feynman, and whole-book reading modes."
},
{
"name": "dossier",
"source": "../../research/dossier/skills/dossier",
"category": "research",
"description": "Decision-grade entity research skill \u2014 produces a hypothesis-tested dossier on a specific company, person, nonprofit, or government org, not a generic profile. Forcing intake makes the user state their hypothesis upfront (what they already believe and want to verify or disprove) so the dossier tests it rather than confirms it. Output is an editable Word document (.docx) with verdict on the hypothesis, identity facts, 12-month activity timeline, network and reputation signals, red flags, conversation hooks tied to specific findings, and source-provenance audit log. Uses WebSearch + WebFetch + free APIs (SEC EDGAR, GitHub, ProPublica) as workhorses; optional BYOK MCPs enhance coverage. Use when the user asks for background research, diligence, or meeting prep on a specific entity (e.g., 'prep me for a meeting with [person/company]', 'due diligence on [company]'). Honors sensitivity exclusions for journalism + personal-vetting contexts."
},
{
"name": "dsh-deepread",
"source": "../../research/dsh-deepread",
"category": "research",
"description": "Use when the user asks to deeply read a book, article, PDF, or document set; extract claims and evidence; build a knowledge map; or learn through Feynman explanation and recall. Covers quick, deep, map, Feynman, and whole-book reading modes."
},
{
"name": "grants",
"source": "../../research/grants/skills/grants",
@ -2043,7 +2103,7 @@
"name": "research",
"source": "../../research/research/skills/research",
"category": "research",
"description": "Default entry point for any research request \u2014 a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants for NIH funding, litreview for academic literature, syllabus for course reading, patent for prior-art + IP landscape, dossier for entity research) or runs its own plan-decompose-multi-source-search-synthesize-cite fallback workflow when no specialist matches. Always surfaces the routing decision so users can override. Use when the user makes any research request that doesn't obviously match a more-specific specialist skill (e.g., \"research [topic]\", \"look into [topic]\", \"what do we know about [topic]\", \"investigate [topic]\", \"find me information on [topic]\", \"do some research on [topic]\", \"I need to understand [topic]\"). Output is a markdown briefing (default) or .docx document (on request) with full citations and an audit log."
"description": "Default entry point for any research request \u2014 a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants for NIH funding, litreview for academic literature, syllabus for course reading, patent for prior-art + IP landscape, dossier for entity research, deepread for evidence-first reading of supplied documents) or runs its own plan-decompose-multi-source-search-synthesize-cite fallback workflow when no specialist matches. Always surfaces the routing decision so users can override. Use when the user makes any research request that doesn't obviously match a more-specific specialist skill (e.g., \"research [topic]\", \"look into [topic]\", \"what do we know about [topic]\", \"investigate [topic]\", \"find me information on [topic]\", \"do some research on [topic]\", \"I need to understand [topic]\"). Output is a markdown briefing (default) or .docx document (on request) with full citations and an audit log."
},
{
"name": "syllabus",
@ -2083,6 +2143,11 @@
}
],
"categories": {
"agent-development": {
"count": 6,
"source": "../../agent-launcher",
"description": "Claude Managed Agent launcher (unreleased, post-v2.11.2): session-goal orchestrator (context: fork) + interview + stage-launch (BYOK curl) + grade-iterate (bounded outcome loop) + run-without-you (cron deployment loop) + wrap-up. Re-implements anthropics/launch-your-agent (Apache-2.0)."
},
"business-growth": {
"count": 5,
"source": "../../business-growth",
@ -2119,7 +2184,7 @@
"description": "Software engineering and technical skills"
},
"engineering-advanced": {
"count": 86,
"count": 90,
"source": "../../engineering",
"description": "Advanced engineering skills - agents, RAG, MCP, CI/CD, databases, observability"
},

1
.codex/skills/agent-launcher-orchestrator Symbolic link
View file

@ -0,0 +1 @@
../../agent-launcher/skills/agent-launcher-orchestrator

1
.codex/skills/agent-memory Symbolic link
View file

@ -0,0 +1 @@
../../engineering/agent-memory/skills/agent-memory

1
.codex/skills/deepread Symbolic link
View file

@ -0,0 +1 @@
../../research/deepread

1
.codex/skills/grade-iterate Symbolic link
View file

@ -0,0 +1 @@
../../agent-launcher/skills/grade-iterate

1
.codex/skills/hivemind Symbolic link
View file

@ -0,0 +1 @@
../../engineering/hivemind

1
.codex/skills/human-gate Symbolic link
View file

@ -0,0 +1 @@
../../engineering/human-gate/skills/human-gate

1
.codex/skills/interview Symbolic link
View file

@ -0,0 +1 @@
../../agent-launcher/skills/interview

1
.codex/skills/run-without-you Symbolic link
View file

@ -0,0 +1 @@
../../agent-launcher/skills/run-without-you

1
.codex/skills/skill-doctor Symbolic link
View file

@ -0,0 +1 @@
../../engineering/skill-doctor/skills/skill-doctor

1
.codex/skills/stage-launch Symbolic link
View file

@ -0,0 +1 @@
../../agent-launcher/skills/stage-launch

1
.codex/skills/wrap-up Symbolic link
View file

@ -0,0 +1 @@
../../agent-launcher/skills/wrap-up

106
.gemini/skills-index.json
View file

@ -1,7 +1,7 @@
{
"version": "1.0.0",
"name": "gemini-cli-skills",
"total_skills": 414,
"total_skills": 430,
"skills": [
{
"name": "README",
@ -173,6 +173,36 @@
"category": "agent",
"description": "Technical co-founder who's been through two startups and learned what actually matters. Makes architecture decisions, selects tech stacks, builds engineering culture, and prepares for technical due diligence \u2014 all while shipping fast with a small team. Use when an early-stage team needs pragmatic, ship-first technical leadership \u2014 e.g., picking a boring-but-fast stack for an MVP with two engineers, or prepping architecture answers for investor due diligence. (For company-scale CTO strategy, see cs-cto-advisor.)"
},
{
"name": "agent-launcher-orchestrator",
"category": "agent-launcher",
"description": "Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account \u2014 \"build me an agent\", \"launch this as a managed agent\", \"run this on a schedule\", \"grade my agent against a rubric\", \"set up a nightly worker\". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview \u2192 stage-launch \u2192 grade-iterate \u2192 run-without-you \u2192 wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade\u2192iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs)."
},
{
"name": "grade-iterate",
"category": "agent-launcher",
"description": "Phase 3 of building a Claude Managed Agent \u2014 the bounded grade\u2192iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader), read each verdict, decide the next move (sharpen / re-run / promote to schedule), and once a version passes, run held-back eval cases in parallel. Use when the user says \"grade my agent\", \"make it pass the rubric\", \"iterate until it's good\", \"is it good enough\", or when the orchestrator routes phase=grade-iterate. outcome_builder.py builds the user.define_outcome payload (rubric required, max_iterations clamped 1..20 \u2014 never unbounded); verdict_reader.py reads the grader result and recommends the next move; eval_scaffold.py generates held-back cases + a parallel run plan (capped at the 25-thread CMA ceiling). Distinct from stage-launch (first launch) and run-without-you (scheduling)."
},
{
"name": "interview",
"category": "agent-launcher",
"description": "Phase 1 of building a Claude Managed Agent \u2014 interview the founder about the one job the agent should do, then produce a build sheet (CMA primitives table + v1/v2 deferrals + eval plan) WITHOUT needing their API key yet. Use when the user says \"help me scope an agent\", \"I have an idea for an agent\", \"what should this agent be\", or when the orchestrator routes phase=interview. Drives the six intake slots (job, trigger, inputs, actions, definition-of-done, recurrence) via AskUserQuestion, maps them to primitives with interview_planner.py, assembles build-sheet.json with build_sheet_builder.py, and validates limits with primitives_validator.py. Connectors are mockable in v0 (schema-true custom tools); real MCP servers become v1 deferrals. Distinct from stage-launch (which turns the sheet into payloads)."
},
{
"name": "run-without-you",
"category": "agent-launcher",
"description": "Phase 4 of building a Claude Managed Agent \u2014 make it run without you. Turn a graded agent into a recurring scheduled deployment (POSIX-cron), an event-driven curl trigger, or confirmed on-demand use, then finalize the versioned roadmap. Use when the user says \"run it every morning\", \"put it on a schedule\", \"nightly\", \"weekly\", \"automate this\", \"make it recurring\", or when the orchestrator routes phase=run-without-you. deployment_builder.py builds the POST /v1/deployments payload (initial_events must include user.message; optionally nests a user.define_outcome so each firing self-grades); cron_validator.py validates the 5-field cron + IANA timezone and prints the wall-clock DST note; next_directions_writer.py writes NEXT-DIRECTIONS.md. No tool makes API calls \u2014 the deployment is created via BYOK curl. Distinct from grade-iterate (the in-session loop) and wrap-up (closeout)."
},
{
"name": "stage-launch",
"category": "agent-launcher",
"description": "Phase 2 of building a Claude Managed Agent \u2014 turn a validated build sheet into exact API payloads and a resumable BYOK curl launch script, then launch (environment \u2192 agent \u2192 session \u2192 kickoff) using the founder's OWN Anthropic key. Use when the user says \"launch it\", \"deploy the agent\", \"create the agent now\", or when the orchestrator routes phase=stage-launch. payload_generator.py emits the four ordered payloads; launch_script_writer.py writes launch.sh that reads $ANTHROPIC_API_KEY at runtime and never embeds it; payload_validator.py runs a pre-launch check including an API-key-leak scan. No tool in this skill makes network calls \u2014 the user runs launch.sh themselves. Distinct from interview (planning) and grade-iterate (the outcome loop)."
},
{
"name": "wrap-up",
"category": "agent-launcher",
"description": "Close out a launched Claude Managed Agent \u2014 recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained ./my-agent/agent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done."
},
{
"name": "business-growth-skills",
"category": "business-growth",
@ -793,6 +823,11 @@
"category": "engineering",
"description": "Build complete transactional email systems: React Email templates, provider integration (Resend, Postmark, SendGrid, AWS SES), preview server, i18n support, dark mode, spam optimization, analytics tracking. Use when adding transactional email to a new product, migrating between email providers, refactoring legacy email templates for accessibility, or adding internationalization to existing templates."
},
{
"name": "embedded-iot-mentor",
"category": "engineering",
"description": "Mentor for embedded and IoT hardware projects. Helps select MCUs, dev boards, and toolchains, decides where sensor readings end up (phone, PC, dashboard, or alert), and gives time/cost estimates and a phased build plan from breadboard MVP to production PCB. Use when the user mentions embedded, IoT, microcontroller, ESP32, STM32, Arduino, Raspberry Pi Pico, firmware, PCB, KiCad, EasyEDA, PlatformIO, MQTT, Home Assistant, ESPHome, Grafana, an IoT dashboard, seeing sensor data on a phone, or asks for hardware tool recommendations, project planning, or cost/time estimates for an electronics project."
},
{
"name": "engineering-skills",
"category": "engineering",
@ -1013,6 +1048,11 @@
"category": "engineering-advanced",
"description": "Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library)."
},
{
"name": "agent-memory",
"category": "engineering-advanced",
"description": "Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead \u2014 or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it."
},
{
"name": "agent-workflow-designer",
"category": "engineering-advanced",
@ -1063,6 +1103,11 @@
"category": "engineering-advanced",
"description": "Converts books, documentation folders, and source collections (PDF, EPUB, DOCX, HTML, Markdown, RST, AsciiDoc, RTF, MOBI/AZW) into structured agent skills \u2014 extracting named frameworks, principles, techniques, and anti-patterns into a master SKILL.md plus on-demand chapter files, a glossary, a patterns file, and a decision cheatsheet. Use when the user wants to study a document with an agent, apply an author's frameworks while working, turn internal docs or standards into a reusable knowledge base, or package a compiled book skill as a claude-skills plugin."
},
{
"name": "boost-asio-pro",
"category": "engineering-advanced",
"description": "Use when writing or reviewing asynchronous C++ networking code with Boost.Asio or standalone Asio \u2014 TCP/UDP servers and clients, SSL/TLS, timers, strands, io_context, co_spawn, awaitable, async_read/async_write, asio::spawn, yield_context, or pre-C++20 completion-handler callbacks."
},
{
"name": "browser-automation",
"category": "engineering-advanced",
@ -1188,6 +1233,11 @@
"category": "engineering-advanced",
"description": "Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw \u2014 chart scaffolding, values design, template patterns, dependency management, security hardening, and chart testing. Use when: user wants to create or improve Helm charts, design values.yaml files, implement template helpers, audit chart security (RBAC, network policies, pod security), manage subcharts, or run helm lint/test."
},
{
"name": "hivemind",
"category": "engineering-advanced",
"description": "Orchestrate free opencode workers from Claude Code to cut token costs. Use when delegating grunt work to a single worker or a parallel swarm (scout/coder/tester) with worktree isolation, benchmarking against opencode, or when the user says \"spawn a worker\", \"swarm\", \"delegate to opencode\", or \"/oc\"."
},
{
"name": "hub-init",
"category": "engineering-advanced",
@ -1198,6 +1248,11 @@
"category": "engineering-advanced",
"description": "Show DAG state, agent progress, and branch status for an AgentHub session. Use when the user runs /hub:hub-status or asks how the AgentHub agents are doing."
},
{
"name": "human-gate",
"category": "engineering-advanced",
"description": "Runs the human-verification lane of an agent loop, and proves review happened before work is called done. Builds a single-file HTML review page, collects batched feedback as a structured artifact instead of chat prose, and runs a gate that refuses to close while a BLOCKER is open, the reviewer is unnamed, or nobody has reviewed at all. Use when a plan, spec, RFC, report, landing page, migration, or any irreversible action needs human sign-off before shipping, or on requests such as 'get sign-off', 'have someone check this', 'hold until reviewed', 'needs approval first'. NOT for making AI text sound human (use content-humanizer or behuman). NOT for reviewing code diffs (use md-review or code-reviewer)."
},
{
"name": "interview-system-designer",
"category": "engineering-advanced",
@ -1296,7 +1351,7 @@
{
"name": "sample-skill",
"category": "engineering-advanced",
"description": "Skill from engineering/skills/skill-tester/assets/sample-skill"
"description": "Reference BASIC-tier skill used as a fixture by skill-tester. Counts words and characters and applies basic text transformations. Use when validating skill-tester itself or when you need a minimal, known-good skill layout to copy. Not a production skill."
},
{
"name": "secrets-vault-manager",
@ -1323,6 +1378,11 @@
"category": "engineering-advanced",
"description": ">"
},
{
"name": "skill-doctor",
"category": "engineering-advanced",
"description": "Use when the user wants their agent setup graded from real conversation history, asks which installed skills are actually working, or wants evidence-backed skill edits \u2014 scores recent local Claude Code / Codex sessions against efficiency and code-quality rubrics, then drafts skill changes gated by a deterministic aggregator and renders one local shareable report."
},
{
"name": "skill-security-auditor",
"category": "engineering-advanced",
@ -1453,10 +1513,15 @@
"category": "finance",
"description": "SaaS financial health advisor. Use when a user shares revenue or customer numbers, or mentions ARR, MRR, churn, LTV, CAC, NRR, or asks how their SaaS business is doing."
},
{
"name": "stock-analysis",
"category": "finance",
"description": "Produce a rigorous, sector-relative, multi-factor fundamental analysis of a publicly listed company \u2014 Indian (NSE/BSE) or US/global. Use when the user asks to analyse, research, evaluate, or value a stock, ticker, or listed company; asks whether a business is fundamentally strong, cheap, or expensive; compares companies or benchmarks one against its sector; or mentions OPM, ROCE, ROE, ROIC, P/E, EV/EBITDA, free cash flow, NIM, GNPA, CASA, promoter holding or pledging. Use it for accounting-quality and forensic questions \u2014 \"is the profit real\", \"why is profit rising but cash isn't\", auditor qualifications, related-party concerns \u2014 which route to the forensic-only mode, and for IPOs and not-yet-listed companies \u2014 \"should I apply to this IPO\", DRHP/RHP or S-1 questions, price band, grey market premium \u2014 which route to the IPO mode. Use it even when the request sounds casual (\"is Infosys any good?\"). Do not use it for personalised investment advice, portfolio allocation, or trading signals."
},
{
"name": "design-system",
"category": "markdown-html",
"description": "Captures the user's brand identity once via a 10-question onboarding wizard (primary/accent HEX + heading + body Google Fonts + design style editorial/technical/minimal/playful + default output directory + syntax theme + TOC behavior + optional logo/company), validates body-text and link contrast against WCAG 2.2 AA, derives 12 CSS custom properties in HSL space, and stores the result for every markdown-html converter to consume. Use before any markdown-html conversion. Triggers on first-run onboarding (\"set up the brand\", \"configure markdown-html\", \"run onboarding\"), on explicit reset (\"reset the design system\", \"re-onboard\"), and is checked by every converter via config_loader.py before rendering. Refuses to save if body-text contrast fails AA 4.5:1 or the output dir isn't writable. Precedence: project (./.markdown-html/) > global (~/.config/markdown-html/) > built-in defaults; MARKDOWN_HTML_NO_CONFIG=1 bypasses."
"description": "Captures the user's brand identity once via a 10-question onboarding wizard (primary/accent HEX + heading + body Google Fonts + design style editorial/technical/minimal/playful + default output directory + syntax theme + TOC behavior + optional logo/company), validates body-text and link contrast against WCAG 2.2 AA, derives 12 CSS custom properties in HSL space, and stores the result for every markdown-html converter to consume. Use before any markdown-html conversion. Triggers on first-run onboarding (\"set up the brand\", \"configure markdown-html\", \"run onboarding\"), on explicit reset (\"reset the design system\", \"re-onboard\"), and is checked by every converter via config_loader.py before rendering. Refuses to save if body-text contrast fails AA 4.5:1 or the output dir isn't writable. Precedence is project (./.markdown-html/) > global (~/.config/markdown-html/) > built-in defaults; MARKDOWN_HTML_NO_CONFIG=1 bypasses."
},
{
"name": "markdown-html-orchestrator",
@ -1476,7 +1541,7 @@
{
"name": "md-slides",
"category": "markdown-html",
"description": "Converts a markdown deck (slides separated by `"
"description": "\"Converts a markdown deck (slides separated by `"
},
{
"name": "ab-test-setup",
@ -1508,6 +1573,11 @@
"category": "marketing",
"description": "When the user wants to apply, document, or enforce brand guidelines for any product or company. Also use when the user mentions 'brand guidelines,' 'brand colors,' 'typography,' 'logo usage,' 'brand voice,' 'visual identity,' 'tone of voice,' 'brand standards,' 'style guide,' 'brand consistency,' or 'company design standards.' Covers color systems, typography, logo rules, imagery guidelines, and tone matrix for any brand \u2014 including Anthropic's official identity."
},
{
"name": "business-name-fit",
"category": "marketing",
"description": "Suggest, pick, or vet a business, startup, or product name that stays true to the founder's cultural origin while working professionally in the markets they want to sell into. Use when someone is naming a company, brand, or product and cares about how it lands across languages and regions \u2014 for example a name that sounds right at home but might read oddly to English speakers, or an authentic name they want to check before committing. Trigger this for any request about choosing a business name, checking if a name \"works\" abroad, spotting bad meanings in other languages, or making a name sound trustworthy in a specific market \u2014 even if the person doesn't say the word \"skill\"."
},
{
"name": "campaign-analytics",
"category": "marketing",
@ -1858,6 +1928,11 @@
"category": "productivity",
"description": "Use when someone asks to roast an idea, pressure-test or stress-test an idea, validate a business idea, \"convene the panel\", get a brutal second opinion before building something, or says \"/roast\". Spins up a 5-angle panel (Critic, Champion, Analyst, Investigator, Customer) that attacks the idea from every angle, then a Judge returns one GO / RESHAPE / KILL verdict with the cheapest test to de-risk it."
},
{
"name": "swedish-mentor",
"category": "productivity",
"description": "Mentor Swedish language learners by selecting YouTube video clips and podcast episodes by CEFR level and skill (listening, reading, writing, speaking), and building a simple learning path. Use when the user asks about a Swedish learning path, YouTube clips or podcasts for Swedish, SFI videos, level assessment for svenska, or requests for Peter SFI / L\u00e4tt Svenska med Oskar / Radio Sweden p\u00e5 l\u00e4tt svenska / Klartext-style recommendations."
},
{
"name": "weekly-review",
"category": "productivity",
@ -2008,6 +2083,11 @@
"category": "research",
"description": "Run a disciplined, multi-source research investigation for a high-stakes question or decision \u2014 fan-out web search across many channels, parallel sub-agents, source triangulation (each claim backed by \u22653 independent sources), an adversarial review pass, and every source saved to its own file with verbatim quotes for reuse. Use when a low-quality answer is expensive: strategy work, comparing N products/methods/markets, validating a hypothesis with external data, or mapping how a field works. NOT for quick fact-checks (answer directly), structured 12-dimension competitor scoring (use competitive-teardown), or fast topic overviews where the decision risk is low (use the research router instead)."
},
{
"name": "deepread",
"category": "research",
"description": "Use when the user asks to deeply read a book, article, PDF, or document set; extract claims and evidence; build a knowledge map; or learn through Feynman explanation and recall. Covers quick, deep, map, Feynman, and whole-book reading modes."
},
{
"name": "dossier",
"category": "research",
@ -2041,7 +2121,7 @@
{
"name": "research-bundle",
"category": "research",
"description": "Default entry point for any research request \u2014 a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants for NIH funding, litreview for academic literature, syllabus for course reading, patent for prior-art + IP landscape, dossier for entity research) or runs its own plan-decompose-multi-source-search-synthesize-cite fallback workflow when no specialist matches. Always surfaces the routing decision so users can override. Use when the user makes any research request that doesn't obviously match a more-specific specialist skill (e.g., \"research [topic]\", \"look into [topic]\", \"what do we know about [topic]\", \"investigate [topic]\", \"find me information on [topic]\", \"do some research on [topic]\", \"I need to understand [topic]\"). Output is a markdown briefing (default) or .docx document (on request) with full citations and an audit log."
"description": "Default entry point for any research request \u2014 a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants for NIH funding, litreview for academic literature, syllabus for course reading, patent for prior-art + IP landscape, dossier for entity research, deepread for evidence-first reading of supplied documents) or runs its own plan-decompose-multi-source-search-synthesize-cite fallback workflow when no specialist matches. Always surfaces the routing decision so users can override. Use when the user makes any research request that doesn't obviously match a more-specific specialist skill (e.g., \"research [topic]\", \"look into [topic]\", \"what do we know about [topic]\", \"investigate [topic]\", \"find me information on [topic]\", \"do some research on [topic]\", \"I need to understand [topic]\"). Output is a markdown briefing (default) or .docx document (on request) with full citations and an audit log."
},
{
"name": "syllabus",
@ -2079,6 +2159,10 @@
"count": 34,
"description": "Agent resources"
},
"agent-launcher": {
"count": 6,
"description": "Agent-launcher resources"
},
"business-growth": {
"count": 5,
"description": "Business-growth resources"
@ -2104,15 +2188,15 @@
"description": "Compliance-os resources"
},
"engineering": {
"count": 52,
"count": 53,
"description": "Engineering resources"
},
"engineering-advanced": {
"count": 86,
"count": 91,
"description": "Engineering-advanced resources"
},
"finance": {
"count": 4,
"count": 5,
"description": "Finance resources"
},
"markdown-html": {
@ -2120,7 +2204,7 @@
"description": "Markdown-html resources"
},
"marketing": {
"count": 48,
"count": 49,
"description": "Marketing resources"
},
"marketing-top-level": {
@ -2132,7 +2216,7 @@
"description": "Product resources"
},
"productivity": {
"count": 11,
"count": 12,
"description": "Productivity resources"
},
"project-management": {
@ -2144,7 +2228,7 @@
"description": "Ra-qm resources"
},
"research": {
"count": 9,
"count": 10,
"description": "Research resources"
},
"research-ops": {

1
.gemini/skills/agent-launcher-orchestrator/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../agent-launcher/skills/agent-launcher-orchestrator/SKILL.md

1
.gemini/skills/agent-memory/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../engineering/agent-memory/skills/agent-memory/SKILL.md

1
.gemini/skills/boost-asio-pro/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../engineering/boost-asio-pro/SKILL.md

1
.gemini/skills/business-name-fit/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../marketing-skill/skills/business-name-fit/SKILL.md

1
.gemini/skills/deepread/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../research/deepread/SKILL.md

1
.gemini/skills/embedded-iot-mentor/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../engineering-team/skills/embedded-iot-mentor/SKILL.md

1
.gemini/skills/grade-iterate/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../agent-launcher/skills/grade-iterate/SKILL.md

1
.gemini/skills/hivemind/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../engineering/hivemind/SKILL.md

1
.gemini/skills/human-gate/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../engineering/human-gate/skills/human-gate/SKILL.md

1
.gemini/skills/interview/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../agent-launcher/skills/interview/SKILL.md

1
.gemini/skills/run-without-you/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../agent-launcher/skills/run-without-you/SKILL.md

1
.gemini/skills/skill-doctor/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../engineering/skill-doctor/skills/skill-doctor/SKILL.md

1
.gemini/skills/stage-launch/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../agent-launcher/skills/stage-launch/SKILL.md

1
.gemini/skills/stock-analysis/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../finance/skills/stock-analysis/SKILL.md

1
.gemini/skills/swedish-mentor/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../productivity/swedish-mentor/SKILL.md

1
.gemini/skills/wrap-up/SKILL.md Symbolic link
View file

@ -0,0 +1 @@
../../../agent-launcher/skills/wrap-up/SKILL.md

26
.github/workflows/skill-quality-review.yml vendored
View file

@ -99,6 +99,7 @@ jobs:
SKILLS='${{ needs.detect-skills.outputs.skills }}'
REPORT_FILE=$(mktemp)
OVERALL_EXIT=0
TESSL_ERRORS=0
THRESHOLD=70
echo "## 📊 Skill Quality Review (Tessl)" > "$REPORT_FILE"
@ -141,8 +142,17 @@ jobs:
IFS='|' read -r NAME SCORE DS CS VSTATUS SUGGESTIONS <<< "$PARSED"
# Determine verdict
if [ "$SCORE" -ge "$THRESHOLD" ]; then
# Determine verdict. VSTATUS=ERROR means the Tessl CLI or the JSON
# parse failed before producing a review — that is a tool outage,
# not a genuine 0-score skill, so it must not block the merge
# (a real CLI failure scores every skill an identical 0/100; see
# the false-negative triage on the v2.12.0 promotion PR #985).
if [ "$VSTATUS" = "ERROR" ]; then
ICON="⚙️"
VERDICT="TOOL ERROR (not scored)"
TESSL_ERRORS=$((TESSL_ERRORS + 1))
echo "::warning::Tessl could not score $skill_dir — CLI output (truncated): $(echo "$JSON_OUT" | head -c 300)"
elif [ "$SCORE" -ge "$THRESHOLD" ]; then
ICON="✅"
VERDICT="PASS"
else
@ -151,7 +161,11 @@ jobs:
OVERALL_EXIT=1
fi
echo "| \`$skill_dir\` | **${SCORE}/100** ${ICON} | ${DS}% | ${CS}% | ${VERDICT} |" >> "$REPORT_FILE"
if [ "$VSTATUS" = "ERROR" ]; then
echo "| \`$skill_dir\` | ${ICON} not scored | — | — | ${VERDICT} |" >> "$REPORT_FILE"
else
echo "| \`$skill_dir\` | **${SCORE}/100** ${ICON} | ${DS}% | ${CS}% | ${VERDICT} |" >> "$REPORT_FILE"
fi
# Add suggestions as details
SUGG_COUNT=$(echo "$SUGGESTIONS" | python3 -c "import sys,json; print(len(json.loads(sys.stdin.readline())))" 2>/dev/null || echo "0")
@ -184,6 +198,12 @@ jobs:
echo "" >> "$REPORT_FILE"
echo "_Threshold: ${THRESHOLD}/100 — skills below this score need improvement before merge._" >> "$REPORT_FILE"
if [ "$TESSL_ERRORS" -gt 0 ]; then
echo "" >> "$REPORT_FILE"
echo "> ⚙️ ${TESSL_ERRORS} skill(s) could not be scored — the Tessl CLI errored before producing a review." >> "$REPORT_FILE"
echo "> Reported as a warning, not a merge blocker; if this persists, check the Tessl CLI install/auth in this workflow." >> "$REPORT_FILE"
fi
echo "report_file=$REPORT_FILE" >> "$GITHUB_OUTPUT"
echo "exit_code=$OVERALL_EXIT" >> "$GITHUB_OUTPUT"

18
.gitignore vendored
View file

@ -63,3 +63,21 @@ tests/
# Autoresearch agent workspace
.autoresearch/
.idea/
# human-gate generated artifacts (review pages + local gate state).
# The review page is a disposable viewing surface rebuilt on every `open`;
# the sidecar (<artifact>.review.md) is deliberately NOT ignored — it is the
# reviewer's feedback and belongs next to the artifact in git.
*.review.html
.human-gate/
# engineering/agent-memory runtime store. L1 candidate atoms are raw-adjacent:
# they are extracted from session transcripts and redaction is a lexical filter,
# never a guarantee. Only the L2/L3 lines a human explicitly adopts into a
# CLAUDE.md are ever committed. errors.log records dropped writes; staged/ holds
# promotion proposals awaiting review. None of it belongs in git.
.memory/
# agent-launcher user output folders (goal.json, payloads, launch.sh live here)
my-agent/
my-agent-*/

1
.hermes/skills/claude-skills/agent-launcher/agent-launcher-orchestrator Symbolic link
View file

@ -0,0 +1 @@
../../../../agent-launcher/skills/agent-launcher-orchestrator

1
.hermes/skills/claude-skills/agent-launcher/grade-iterate Symbolic link
View file

@ -0,0 +1 @@
../../../../agent-launcher/skills/grade-iterate

1
.hermes/skills/claude-skills/agent-launcher/interview Symbolic link
View file

@ -0,0 +1 @@
../../../../agent-launcher/skills/interview

1
.hermes/skills/claude-skills/agent-launcher/run-without-you Symbolic link
View file

@ -0,0 +1 @@
../../../../agent-launcher/skills/run-without-you

1
.hermes/skills/claude-skills/agent-launcher/stage-launch Symbolic link
View file

@ -0,0 +1 @@
../../../../agent-launcher/skills/stage-launch

1
.hermes/skills/claude-skills/agent-launcher/wrap-up Symbolic link
View file

@ -0,0 +1 @@
../../../../agent-launcher/skills/wrap-up

1
.hermes/skills/claude-skills/business-operations/business-operations-skills Symbolic link
View file

@ -0,0 +1 @@
../../../../business-operations/skills/business-operations-skills

1
.hermes/skills/claude-skills/business-operations/capacity-planner Symbolic link
View file

@ -0,0 +1 @@
../../../../business-operations/skills/capacity-planner

1
.hermes/skills/claude-skills/business-operations/internal-comms Symbolic link
View file

@ -0,0 +1 @@
../../../../business-operations/skills/internal-comms

1
.hermes/skills/claude-skills/business-operations/knowledge-ops Symbolic link
View file

@ -0,0 +1 @@
../../../../business-operations/skills/knowledge-ops

1
.hermes/skills/claude-skills/business-operations/process-mapper Symbolic link
View file

@ -0,0 +1 @@
../../../../business-operations/skills/process-mapper

1
.hermes/skills/claude-skills/business-operations/procurement-optimizer Symbolic link
View file

@ -0,0 +1 @@
../../../../business-operations/skills/procurement-optimizer

1
.hermes/skills/claude-skills/business-operations/vendor-management Symbolic link
View file

@ -0,0 +1 @@
../../../../business-operations/skills/vendor-management

1
.hermes/skills/claude-skills/c-level-advisor/arquiteto-de-empresa Symbolic link
View file

@ -0,0 +1 @@
../../../../c-level-advisor/skills/arquiteto-de-empresa

1
.hermes/skills/claude-skills/commercial/channel-economics Symbolic link
View file

@ -0,0 +1 @@
../../../../commercial/skills/channel-economics

1
.hermes/skills/claude-skills/commercial/commercial-forecaster Symbolic link
View file

@ -0,0 +1 @@
../../../../commercial/skills/commercial-forecaster

1
.hermes/skills/claude-skills/commercial/commercial-policy Symbolic link
View file

@ -0,0 +1 @@
../../../../commercial/skills/commercial-policy

1
.hermes/skills/claude-skills/commercial/commercial-skills Symbolic link
View file

@ -0,0 +1 @@
../../../../commercial/skills/commercial-skills

1
.hermes/skills/claude-skills/commercial/deal-desk Symbolic link
View file

@ -0,0 +1 @@
../../../../commercial/skills/deal-desk

1
.hermes/skills/claude-skills/commercial/partnerships-architect Symbolic link
View file

@ -0,0 +1 @@
../../../../commercial/skills/partnerships-architect

1
.hermes/skills/claude-skills/commercial/pricing-strategist Symbolic link
View file

@ -0,0 +1 @@
../../../../commercial/skills/pricing-strategist

1
.hermes/skills/claude-skills/commercial/rfp-responder Symbolic link
View file

@ -0,0 +1 @@
../../../../commercial/skills/rfp-responder

1
.hermes/skills/claude-skills/compliance-os/ai-act-readiness Symbolic link
View file

@ -0,0 +1 @@
../../../../compliance-os/skills/ai-act-readiness

1
.hermes/skills/claude-skills/compliance-os/aims-audit Symbolic link
View file

@ -0,0 +1 @@
../../../../compliance-os/skills/aims-audit

1
.hermes/skills/claude-skills/compliance-os/compliance-os Symbolic link
View file

@ -0,0 +1 @@
../../../../compliance-os/skills/compliance-os

1
.hermes/skills/claude-skills/compliance-os/compliance-readiness Symbolic link
View file

@ -0,0 +1 @@
../../../../compliance-os/skills/compliance-readiness

1
.hermes/skills/claude-skills/compliance-os/fda-qsr-audit-prep Symbolic link
View file

@ -0,0 +1 @@
../../../../compliance-os/skills/fda-qsr-audit-prep

1
.hermes/skills/claude-skills/compliance-os/gdpr-audit-prep Symbolic link
View file

@ -0,0 +1 @@
../../../../compliance-os/skills/gdpr-audit-prep

1
.hermes/skills/claude-skills/compliance-os/iso13485-audit-prep Symbolic link
View file

@ -0,0 +1 @@
../../../../compliance-os/skills/iso13485-audit-prep

1
.hermes/skills/claude-skills/compliance-os/iso27001-audit-prep Symbolic link
View file

@ -0,0 +1 @@
../../../../compliance-os/skills/iso27001-audit-prep

1
.hermes/skills/claude-skills/compliance-os/soc2-audit-prep Symbolic link
View file

@ -0,0 +1 @@
../../../../compliance-os/skills/soc2-audit-prep

1
.hermes/skills/claude-skills/engineering-team/embedded-iot-mentor Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering-team/skills/embedded-iot-mentor

1
.hermes/skills/claude-skills/engineering-team/named-persona-adversarial-review Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering-team/skills/named-persona-adversarial-review

1
.hermes/skills/claude-skills/engineering/agent-harness Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/agent-harness/skills/agent-harness

1
.hermes/skills/claude-skills/engineering/boost-asio-pro Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/boost-asio-pro

1
.hermes/skills/claude-skills/engineering/claude-coach Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/claude-coach/skills/claude-coach

1
.hermes/skills/claude-skills/engineering/collab-proof Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/collab-proof/skills/collab-proof

1
.hermes/skills/claude-skills/engineering/human-gate Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/human-gate/skills/human-gate

1
.hermes/skills/claude-skills/engineering/memory-engineering Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/memory-engineering/skills/memory-engineering

1
.hermes/skills/claude-skills/engineering/minimalist Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/minimalist

1
.hermes/skills/claude-skills/engineering/skillopt-sleep Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/skillopt-sleep/skills/skillopt-sleep

1
.hermes/skills/claude-skills/engineering/strict-api Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/strict-api

1
.hermes/skills/claude-skills/engineering/universal-scraping-architect Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/universal-scraping-architect/skills/universal-scraping-architect

1
.hermes/skills/claude-skills/engineering/workflow-builder Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/workflow-builder/skills/workflow-builder

1
.hermes/skills/claude-skills/engineering/zero-hallucination-coder Symbolic link
View file

@ -0,0 +1 @@
../../../../engineering/zero-hallucination-coder/skills/zero-hallucination-coder

1
.hermes/skills/claude-skills/finance/stock-analysis Symbolic link
View file

@ -0,0 +1 @@
../../../../finance/skills/stock-analysis

1
.hermes/skills/claude-skills/markdown-html/design-system Symbolic link
View file

@ -0,0 +1 @@
../../../../markdown-html/skills/design-system

1
.hermes/skills/claude-skills/markdown-html/markdown-html-orchestrator Symbolic link
View file

@ -0,0 +1 @@
../../../../markdown-html/skills/markdown-html-orchestrator

1
.hermes/skills/claude-skills/markdown-html/md-document Symbolic link
View file

@ -0,0 +1 @@
../../../../markdown-html/skills/md-document

1
.hermes/skills/claude-skills/markdown-html/md-review Symbolic link
View file

@ -0,0 +1 @@
../../../../markdown-html/skills/md-review

1
.hermes/skills/claude-skills/markdown-html/md-slides Symbolic link
View file

@ -0,0 +1 @@
../../../../markdown-html/skills/md-slides

1
.hermes/skills/claude-skills/marketing-skill/business-name-fit Symbolic link
View file

@ -0,0 +1 @@
../../../../marketing-skill/skills/business-name-fit

1
.hermes/skills/claude-skills/marketing-skill/local-seo-manager Symbolic link
View file

@ -0,0 +1 @@
../../../../marketing-skill/skills/local-seo-manager

1
.hermes/skills/claude-skills/marketing-skill/webinar-marketing Symbolic link
View file

@ -0,0 +1 @@
../../../../marketing-skill/skills/webinar-marketing

1
.hermes/skills/claude-skills/marketing-skill/youtube-full Symbolic link
View file

@ -0,0 +1 @@
../../../../marketing-skill/skills/youtube-full

1
.hermes/skills/claude-skills/productivity/andreessen Symbolic link
View file

@ -0,0 +1 @@
../../../../productivity/andreessen/skills/andreessen

1
.hermes/skills/claude-skills/productivity/deep-work Symbolic link
View file

@ -0,0 +1 @@
../../../../productivity/deep-work/skills/deep-work

1
.hermes/skills/claude-skills/productivity/fable-goal Symbolic link
View file

@ -0,0 +1 @@
../../../../productivity/fable-goal/skills/fable-goal

1
.hermes/skills/claude-skills/productivity/handoff Symbolic link
View file

@ -0,0 +1 @@
../../../../productivity/handoff/skills/handoff

1
.hermes/skills/claude-skills/productivity/meetings Symbolic link
View file

@ -0,0 +1 @@
../../../../productivity/meetings/skills/meetings

1
.hermes/skills/claude-skills/productivity/roast Symbolic link
View file

@ -0,0 +1 @@
../../../../productivity/roast/skills/roast

1
.hermes/skills/claude-skills/productivity/swedish-mentor Symbolic link
View file

@ -0,0 +1 @@
../../../../productivity/swedish-mentor

1
.hermes/skills/claude-skills/productivity/weekly-review Symbolic link
View file

@ -0,0 +1 @@
../../../../productivity/weekly-review/skills/weekly-review

1
.hermes/skills/claude-skills/ra-qm-team/agent-decision-receipts Symbolic link
View file

@ -0,0 +1 @@
../../../../ra-qm-team/skills/agent-decision-receipts

1
.hermes/skills/claude-skills/research-ops/clinical-research Symbolic link
View file

@ -0,0 +1 @@
../../../../research-ops/skills/clinical-research

1
.hermes/skills/claude-skills/research-ops/market-research Symbolic link
View file

@ -0,0 +1 @@
../../../../research-ops/skills/market-research

1
.hermes/skills/claude-skills/research-ops/product-research Symbolic link
View file

@ -0,0 +1 @@
../../../../research-ops/skills/product-research

1
.hermes/skills/claude-skills/research-ops/research-finance Symbolic link
View file

@ -0,0 +1 @@
../../../../research-ops/skills/research-finance

Some files were not shown because too many files have changed in this diff Show more