Ben Fairless
02c04e3d32
fix(frontmatter): repair 14 unloadable YAML blocks
...
Twelve files had frontmatter that yaml.safe_load rejects, all from the same
cause: an unquoted plain scalar containing ": " inside description. Claude Code
responds by loading the body with empty metadata, so the skill keeps working
via /name but has no description for the model to match against, and the seven
affected agents (where name and description are required) may not load at all.
Eleven are fixed by quoting the existing scalar, leaving the text
byte-identical. design-system carries both ' and " so quoting would defeat the
repo's regex extractors in generate-docs.py and sync-codex-skills.py; its one
colon-space is reworded instead ("Precedence:" -> "Precedence is").
Two agents had no frontmatter at all and were being listed with a placeholder
description; both now declare name and description. tools is deliberately
omitted so they keep inheriting the full set, as before.
Assisted-by: Claude Code:claude-opus-5
2026-08-03 08:55:36 +08:00
Claude
aecfb8e0bb
feat(skills): wave-3 optimization — domain overhauls per newgen audit
...
marketing: context-file unified on .claude/product-marketing-context.md;
ai-seo merged into aeo (2 new cited references, folder deleted); index +
marketing-ops routers rebuilt honestly; 24 orphan scripts wired with exact
CLIs; prompt-engineer-toolkit stub references rewritten with cited content;
Meta 20%-rule + GA4 terminology freshness; 5 zips + 3 planning docs removed
c-level-advisor: role registry 9->14 across all 6 routing surfaces; decision
memory unified on ~/.claude/decisions/{raw,approved}; onboarding schema
canonicalized; 12 phantom commands resolved; index repaired (33/37/68 real
counts); ma-playbook sourced + verification loop; 28 trigger descriptions
engineering(+team): agent-designer 279->76 lines and rag-architect 318->71
lines rebuilt around their tools (stale ada-002/pricing gone); release-manager
merged into changelog-generator (version_bumper + hotfix refs moved, crashing
release_planner dropped); 6 skills' orphan scripts wired; ms365 tools gained
real CLIs; 5 brochure skills de-filled; 4 unreferenced zips removed;
bundle counts trued (25->37, 23->32); 18 trigger descriptions
product/research/compliance/bizops: apple-hig-expert rebuilt around
hig_checker's real CLI with web-verified facts; notebooklm re-verified against
live product; 5 index skills converted to honest routers; research-summarizer
repaired with explicit lane statement; 8 over-1024 descriptions compressed;
9 sub-skills gained fenced CLI examples; GDPR one-month (Art. 12(3)) with
calendar-month deadline math; MDR PSUR table per Art. 86(1); 12 ra-qm zips
removed; 24 trigger descriptions
Verified: check_paths 0 findings; check_dual_publish 0 drifted; smoke 581/581;
check_plugin_json 77 OK; compileall rc=0; all descriptions <=1024 chars
https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF
2026-06-11 03:58:41 +00:00
Claude
a088c8ba77
fix: phantom-path sweep — 888 unresolvable references to zero
...
A directory reorg added a skills/ path segment; hundreds of references never
followed. This sweep repoints every path-like reference in SKILL.md, agents,
commands, orchestration, and templates to verified on-disk targets:
- 30 root commands + 19 root agents: missing skills/ segment inserted
- 7 c-level persona agents: 17 hallucinated reference filenames substituted
with the real files (e.g. okr_execution.md -> process_frameworks.md)
- 5 research skills: phantom scripts/office/validate.py step replaced with a
runnable stdlib zip-integrity check
- email agents: skills frontmatter corrected to productivity/email
- orchestration/ORCHESTRATION.md + templates: stale paths fixed;
agent-template now requires trigger phrasing in descriptions (root cause)
- 76 more files across engineering, c-level-advisor, compliance-os,
research-ops, ra-qm, marketing, productivity; dual-publish pairs mirrored
- dead refs dropped/replaced where no target ever existed (REGISTRY.md,
trend_analyzer.py, cursor-microinteractions.md)
New: scripts/check_paths.py linter (CI gate G1) + narrow allowlist for
teaching examples. Verified: 540 files scanned, 0 unresolvable.
https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF
2026-06-10 14:33:00 +00:00
Claude
0f88555485
chore(versioning,docs): normalize stale versions to 2.9.0 + refresh counts
...
Version normalization (scope: only plugins/skills older than 2.7.0):
- Bumped 52 plugin.json + 21 SKILL.md `version` fields from pre-2.7.0
values (1.0.0 / 2.0.x / 2.2.x / 2.3.x / 2.4.x / 2.5.x) to 2.9.0.
Left 2.7.0+ packages untouched. Tool mirrors (.codex/.gemini/.vibe/
.hermes) excluded. All manifests still pass check_plugin_json --all.
Doc count refresh (recomputed raw figures: 338 skills, 16 domains,
62 plugins, 533 Python tools, 676 references):
- marketplace.json: both descriptions + metadata.version -> 2.9.0.
- Root README: headline, badges (Skills 338, Agents 51+, Commands 87+),
intro counts, convert section (338 skills / 9 tools), and the full
domain table rebuilt to 16 domains summing to 338 (adds research-ops,
business-operations, commercial, compliance-os; corrects product 17,
marketing 46, c-level 66, ra-qm 18, finance 4, engineering 51/78).
- Fixed stale per-skill README `Version:` lines left inconsistent by the
bump (andreessen, c-level-agents, product-team, senior-qa).
- Fixed stale domain README footers (product-team 17/17, c-level 66/66,
project-management 9/9).
- CLAUDE.md scope line, structure tree, highlight, and footer synced to
the raw figures.
https://claude.ai/code/session_01PUNmQVE4WYvcrzpq2anC3D
2026-05-27 05:22:59 +00:00
Claude
8fd3155868
fix(plugin-schema): align with live Claude Code spec — migrate to "./"-prefixed skills field
...
Resolves #712 and #714 .
Claude Code's plugin spec (code.claude.com/docs/en/plugins-reference) requires
"All paths must be relative to the plugin root and start with ./". CC 2.1.144+
rejects the bare "skills" form with `Validation errors: skills: Invalid input`,
breaking plugin installs from this repo.
Changes:
- 47 plugin.json manifests migrated from "skills": "skills" → ["./skills"]
(canonical post-CC 2.1.144 form, also accepts string "./skills")
- scripts/check_plugin_json.py rewritten to enforce the live spec:
* Hard-fails on non-"./"-prefixed strings (except the legacy "skills" literal)
* Hard-fails on empty strings/arrays and non-string array entries
* Emits WARN (non-fatal) on the legacy "skills" literal as a safety net
for copied templates — the WARN tolerance can be removed later
* Tested against all four canonical forms + 3 garbage forms
- CLAUDE.md §5 rewritten to document the live spec, including the historical
context of the v2.1.107 → v2.1.144 regression window that's now closed
- 15 stale broken symlinks under .gemini/skills/ removed (orphans from older
reorgs that the sync script didn't prune because its cleanup is disabled)
Verification:
- scripts/check_plugin_json.py --all → 0 FAIL, 0 WARN, exit 0 (69 files OK)
- pytest tests/ → 2103 passed
- find . -type l ! -exec test -e {} \; → 0 broken symlinks
- Live spec forms tested: ["./"], ["./skills"], "./skills", ["./a","./b"] all pass
- Garbage forms rejected: bare "./", empty array, non-string entries, plain strings
2026-05-21 07:03:11 +00:00
Claude
663bc8afa2
fix(plugin.json): drop "./" prefix from skills field to clear /doctor warning ( #686 )
...
Claude Code 2.1.133+ rejects "skills": "./skills" with a "Path escapes
plugin directory" warning, even though ./skills resolves to a valid
subdirectory inside the plugin root. Per the upstream docs example, the
correct value is "skills" (no ./ prefix), which works across all CC
versions and other tools (Codex, Gemini CLI, etc.).
Applied to all 47 plugin.json files that used "./skills"; updated
CLAUDE.md ClawHub publishing constraints to document the new convention
and reference the issue.
2026-05-19 03:43:34 +00:00
Claude
1b152ab675
fix(v2.6.2): fix remaining 11 placeholder descriptions
...
Continues the v2.6.1 cleanup (PR #647 ). Fixes the final 11 placeholder
descriptions identified in the audit — skills whose description field was
literally just the skill name from a v2.0.0 batch import.
Skills fixed across 4 domains:
c-level-advisor (executive-mentor):
- executive-mentor/skills/challenge — pre-mortem plan analysis ("imagine
it's 12 months from now and this plan failed")
- executive-mentor/skills/board-prep — adversarial board meeting prep
engineering (POWERFUL tier):
- git-worktree-manager — parallel feature work with Git worktrees
- skill-tester — meta-skill QA (structure + script + quality scoring)
- monorepo-navigator — Turborepo / Nx / pnpm / Lerna navigation
- env-secrets-manager — env-var hygiene + secrets rotation
- agent-workflow-designer — production-grade multi-agent workflows
engineering-team:
- incident-commander — incident response framework (detection → resolution)
- email-template-builder — React Email + provider integration (Resend,
Postmark, SendGrid, AWS SES)
- stripe-integration-expert — subscriptions, webhooks, billing patterns
business-growth:
- contract-and-proposal-writer — jurisdiction-aware business documents
(US/EU/UK/DACH; contracts, SOWs, NDAs, MSAs)
Each new description: ≤1024 chars, third person, action verb in first
sentence, "Use when ..." trigger in second sentence per Matt Pocock's rule.
All 11 descriptions PASS or WARN on skill_description_validator.py:
- 6 PASS: git-worktree-manager, skill-tester, monorepo-navigator,
env-secrets-manager, incident-commander, email-template-builder
- 5 WARN: challenge, board-prep, agent-workflow-designer,
stripe-integration-expert, contract-and-proposal-writer (warnings
from other rules — SKILL.md > 100 lines, terminology drift — not
the description itself)
Cumulative impact across v2.6.0 → v2.6.1 → v2.6.2:
- PASS: 4 (1%) → 7 (2%) → 9 (3%) [+5]
- WARN: 111 → 134 → 137 [+26]
- FAIL: 183 → 157 → 152 [-31]
- Missing-trigger: 119 → 79 → 68 [-51]
31 skills total lifted from FAIL → WARN/PASS across v2.6.1 + v2.6.2.
Audit baseline preserved at 298 real skills (excludes auto-generated
.gemini/.codex/.cursor/.cline bundles and template fixtures).
Next cleanup target (v2.6.3 candidate): the 27% terminology-consistency
drift (agent/bot, skill/tool mixing) — bigger scope, requires careful
prose edits per file.
https://claude.ai/code/session_01VFreMf7XLBqMgjsrG4wSYe
2026-05-14 05:08:23 +00:00
Reza Rezvani
1851c8fb09
fix(plugins): restructure 9 multi-skill domain plugins into ./skills/ layout
...
Same root cause as #587/#591 — Claude Code's runtime loader rejects
array-form skills paths like ["./content-production", "./ai-seo", ...]
even when each entry is a valid subdirectory containing SKILL.md.
`claude plugin validate` accepts them but the loader does not.
The proven canonical layout (used by self-improving-agent in #536 ):
<plugin>/
├── .claude-plugin/plugin.json skills: "./skills"
└── skills/
├── <skill-1>/SKILL.md
├── <skill-2>/SKILL.md
└── ...
Restructured 9 multi-skill domain plugins:
- business-growth (4 skills moved)
- c-level-advisor (28)
- engineering (36)
- engineering-team (32)
- finance (2)
- marketing-skill (43)
- product-team (12)
- project-management (8)
- ra-qm-team (13)
Also fixed standalone plugins that had root SKILL.md + ./skills/ subdir
(agenthub, autoresearch-agent, executive-mentor, playwright-pro). The
loader rejected them despite skills="./skills" because of the conflicting
root SKILL.md (compare self-improving-agent which works because PR #536
moved its root SKILL.md). Moved each root SKILL.md into ./skills/<name>/.
Restored standalone plugin folders to their original paths after the
multi-skill restructure swept them into parent skills/ directories
(marketplace.json source paths require original locations).
Removed 7 orphaned marketplace entries that pointed to skill folders
without their own plugin.json (content-creator, demand-gen,
fullstack-engineer, aws-architect, product-manager, scrum-master,
skill-security-auditor) — these were already non-functional.
Bumped patch versions on every changed plugin and synced
marketplace.json. Marketplace now lists 29 working plugins (down
from 36).
After merge: users run `/plugin marketplace update claude-code-skills`
followed by `/plugin update --all` to pick up the working layout.
2026-05-02 22:51:20 +02:00
Reza Rezvani
2717c8f933
fix(plugins): bump versions to force /plugin update to pick up #587 fix
...
PR #587 fixed `"skills": "./"` in 35 plugin.json files but did not bump
versions. Claude Code uses version as the cache key — same version string
means /plugin update is a no-op and users keep loading the cached
plugin.json with the broken path. The /plugin UI shows "1 error" on
every plugin from this marketplace because the installed cache is stale.
Per the official version-management docs:
> If you set `version` in `plugin.json`, you must bump it every time
> you want users to receive changes. Pushing new commits alone is not
> enough.
Bump every plugin.json by one patch using max(plugin_version,
marketplace_version) as the base so no version moves backward. Sync the
new versions back into .claude-plugin/marketplace.json.
After this lands, users run `/plugin marketplace update claude-code-skills`
followed by `/plugin update --all` to pull the fixed manifests.
2026-05-02 22:14:12 +02:00
Reza Rezvani
55e7e45512
fix(plugins): repair skills path in 35 plugin.json files ( #539 )
...
Claude Code v2.1.107+ rejects bare "skills": "./" with "Path escapes
plugin directory: ./". This blocks every plugin in the marketplace from
loading. Replace with the layout-appropriate form per the official
plugins reference:
- Single-skill plugin (SKILL.md at root):
"skills": ["./"] array form (per docs example)
- Plugin with skills/ subdir:
"skills": "./skills" standard subdir layout
- Multi-skill domain plugin (skills are subfolders at root):
"skills": ["./sub1", "./sub2"] explicit list of skill dirs
The multi-skill case omits "./" from the array so the index SKILL.md
at the plugin root does not register as a skill — that would create
a redundant `marketing-skills:marketing-skills` namespace.
Verified by running `claude plugin validate` against all 35 manifests.
Closes #539
2026-05-02 21:55:58 +02:00
Reza Rezvani
95f8bd42b2
fix(plugins): normalize author fields and versions in 4 plugin.json files
...
- executive-mentor: add url to author, add homepage + repository
- self-improving-agent: add url to author, version 1.0.0 → 2.1.2
- playwright-pro: fix author name (Reza → Alireza), replace email with url, version 1.0.0 → 2.1.2
- google-workspace-cli: add url to author
All plugin.json files now use consistent author object format.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-25 11:07:08 +01:00
Alireza Rezvani
5adbfdce47
release: sync dev → main — a11y-audit, /seo-auditor, /plugin-audit, 28 plugins ( #380 )
...
* fix: add missing plugin.json files and restore trailing newlines
- Add plugin.json for review-fix-a11y skill
- Add plugin.json for free-llm-api skill
- Restore POSIX-compliant trailing newlines in JSON index files
* feat(engineering): add review-fix-a11y skill (WCAG 2.2 a11y audit + fix) (#375 )
Adds review-fix-a11y (WCAG 2.2 a11y audit + fix) and free-llm-api skills.
Includes:
- review-fix-a11y: WCAG 2.2 audit workflow, a11y_audit.py scanner, contrast_checker.py
- free-llm-api: ChatAnywhere, Groq, Cerebras, OpenRouter, llm-mux, One API setup
- secret_scanner.py upgrade with secrets-patterns-db integration (1,600+ patterns)
Co-authored-by: ivanopenclaw223-alt <ivanopenclaw223-alt@users.noreply.github.com>
* chore: sync codex skills symlinks [automated]
* Revert "feat(engineering): add review-fix-a11y skill (WCAG 2.2 a11y audit + fix) (#375 )"
This reverts commit 49c9f2109f#375 )"
This reverts commit 49c9f2109f#376 )
Built from scratch (replaces reverted PR #375 contribution).
Skill package:
- SKILL.md: 1132 lines, 3-phase workflow (scan → fix → verify),
per-framework fix patterns (React, Next.js, Vue, Angular, Svelte, HTML),
CI/CD integration guide, 20+ issue type coverage
- scripts/a11y_scanner.py: static scanner detecting 20+ violation types
across HTML/JSX/TSX/Vue/Svelte/CSS — severity-ranked, CI-friendly exit codes
- scripts/contrast_checker.py: WCAG contrast calculator with AA/AAA checks,
--suggest mode, --batch CSS scanning, named color support
- references/wcag-quick-ref.md: WCAG 2.2 Level A/AA criteria table
- references/aria-patterns.md: ARIA roles, live regions, keyboard interaction
- references/framework-a11y-patterns.md: React, Vue, Angular, Svelte fix patterns
- assets/sample-component.tsx: sample file with intentional violations
- expected_outputs/: scan report, contrast output, JSON output samples
- /a11y-audit slash command, settings.json, plugin.json, README.md
Validation: 97.6/100 (EXCELLENT), quality 73.9/100 (B-), scripts 2/2 PASS
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* chore: sync codex skills symlinks [automated]
* docs: sync counts across all docs — 205 skills, 268 tools, 19 commands, 22 plugins
Update CLAUDE.md, README.md, docs/index.md, docs/getting-started.md,
mkdocs.yml, marketplace.json with consistent counts. Sync Gemini CLI
index with new skills (code-to-prd, plugin-audit).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(marketplace): add 6 missing standalone plugins — total 22→28
Added to marketplace:
- a11y-audit (WCAG 2.2 accessibility audit)
- executive-mentor (adversarial thinking partner)
- docker-development (Dockerfile, compose, multi-stage)
- helm-chart-builder (Helm chart scaffolding)
- terraform-patterns (IaC module design)
- research-summarizer (structured research synthesis)
Also fixed version 1.0.0 → 2.1.2 on 4 plugin.json files
(executive-mentor, docker-development, helm-chart-builder, research-summarizer)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(commands): add /seo-auditor — 7-phase SEO audit pipeline for documentation
- 7 phases: discovery → meta tags → content quality → keywords → links → sitemap → report
- Integrates 8 marketing-skill scripts: seo_checker, content_scorer,
humanizer_scorer, headline_scorer, seo_optimizer, sitemap_analyzer,
schema_validator, topic_cluster_mapper
- References 6 SEO knowledge bases for audit framework, AI search,
content optimization, URL design, internal linking, AI detection
- Auto-fixes: generic titles, missing descriptions, broken links, orphan pages
- Preserves high-ranking pages — only fixes critical issues on those
- Registered in both commands/ (distributable) and .claude/commands/ (local)
Also: sync all doc counts — 28 plugins, 26 eng-core skills, 21 commands
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(seo): fix multi-line YAML description parser, add 2 orphan pages to nav
- generate-docs.py: extract_description_from_frontmatter() now handles
multi-line YAML block scalars (|, >, indented continuation) — fixes
14 pages that had 56-65 char truncated descriptions
- mkdocs.yml: add epic-design and research-summarizer to nav (orphan pages)
- Regenerated 251 pages, rebuilt sitemap (278 URLs)
- SEO audit: 0 broken links, 17→3 short descriptions, 278/278 pages
have "Claude Code Skills" in <title>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Leo <leo@openclaw.ai>
Co-authored-by: ivanopenclaw223-alt <ivanopenclaw223@gmail.com>
Co-authored-by: ivanopenclaw223-alt <ivanopenclaw223-alt@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-18 13:03:48 +01:00
Alireza Rezvani
8902ba79d7
release: v2.1.1 — skill optimization, agents, commands, reference splits ( #297 )
2026-03-09 15:54:25 +01:00
Reza Rezvani
0ce6de262e
fix: resolve plugin.json schema validation errors
...
- marketplace.json: fix self-improving-agent entry (add version, author,
rename tags→keywords), update engineering-skills count (21→23)
- c-level-advisor/plugin.json: replace explicit skills/scripts arrays with
"skills": "./" auto-discovery, remove namespace field
- executive-mentor/plugin.json: same — use auto-discovery, fix author format,
remove namespace/scripts/references fields
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 08:58:39 +01:00
Alireza Rezvani
466aa13a7b
feat: C-Suite expansion — 8 new executive advisory roles (2→10) ( #264 )
...
* feat: C-Suite expansion — 8 new executive advisory roles
Add COO, CPO, CMO, CFO, CRO, CISO, CHRO advisors and Executive Mentor.
Expands C-level advisory from 2 to 10 roles with 74 total files.
Each role includes:
- SKILL.md (lean, <5KB, ~1200 tokens for context efficiency)
- Reference docs (loaded on demand, not at startup)
- Python analysis scripts (stdlib only, runnable CLI)
Executive Mentor features /em: slash commands (challenge, board-prep,
hard-call, stress-test, postmortem) with devil's advocate agent.
21 Python tools, 24 reference frameworks, 28,379 total lines.
All SKILL.md files combined: ~17K tokens (8.5% of 200K context window).
Badge: 88 → 116 skills
* feat: C-Suite orchestration layer + 18 complementary skills
ORCHESTRATION (new):
- cs-onboard: Founder interview → company-context.md
- chief-of-staff: Routing, synthesis, inter-agent orchestration
- board-meeting: 6-phase multi-agent deliberation protocol
- decision-logger: Two-layer memory (raw transcripts + approved decisions)
- agent-protocol: Inter-agent invocation with loop prevention
- context-engine: Company context loading + anonymization
CROSS-CUTTING CAPABILITIES (new):
- board-deck-builder: Board/investor update assembly
- scenario-war-room: Cascading multi-variable what-if modeling
- competitive-intel: Systematic competitor tracking + battlecards
- org-health-diagnostic: Cross-functional health scoring (8 dimensions)
- ma-playbook: M&A strategy (acquiring + being acquired)
- intl-expansion: International market entry frameworks
CULTURE & COLLABORATION (new):
- culture-architect: Values → behaviors, culture code, health assessment
- company-os: EOS/Scaling Up operating system selection + implementation
- founder-coach: Founder development, delegation, blind spots
- strategic-alignment: Strategy cascade, silo detection, alignment scoring
- change-management: ADKAR-based change rollout framework
- internal-narrative: One story across employees/investors/customers
UPGRADES TO EXISTING ROLES:
- All 10 roles get reasoning technique directives
- All 10 roles get company-context.md integration
- All 10 roles get board meeting isolation rules
- CEO gets stage-adaptive temporal horizons (seed→C)
Key design decisions:
- Two-layer memory prevents hallucinated consensus from rejected ideas
- Phase 2 isolation: agents think independently before cross-examination
- Executive Mentor (The Critic) sees all perspectives, others don't
- 25 Python tools total (stdlib only, no dependencies)
52 new files, 10 modified, 10,862 new lines.
Total C-suite ecosystem: 134 files, 39,131 lines.
* fix: connect all dots — Chief of Staff routes to all 28 skills
- Added complementary skills registry to routing-matrix.md
- Chief of Staff SKILL.md now lists all 28 skills in ecosystem
- Added integration tables to scenario-war-room and competitive-intel
- Badge: 116 → 134 skills
- README: C-Level Advisory count 10 → 28
Quality audit passed:
✅ All 10 roles: company-context, reasoning, isolation, invocation
✅ All 6 phases in board meeting
✅ Two-layer memory with DO_NOT_RESURFACE
✅ Loop prevention (no self-invoke, max depth 2, no circular)
✅ All /em: commands present
✅ All complementary skills cross-reference roles
✅ Chief of Staff routes to every skill in ecosystem
* refactor: CEO + CTO advisors upgraded to C-suite parity
Both roles now match the structural standard of all new roles:
- CEO: 11.7KB → 6.8KB SKILL.md (heavy content stays in references)
- CTO: 10KB → 7.2KB SKILL.md (heavy content stays in references)
Added to both:
- Integration table (who they work with and when)
- Key diagnostic questions
- Structured metrics dashboard table
- Consistent section ordering (Keywords → Quick Start → Responsibilities → Questions → Metrics → Red Flags → Integration → Reasoning → Context)
CEO additions:
- Stage-adaptive temporal horizons (seed=3m/6m/12m → B+=1y/3y/5y)
- Cross-references to culture-architect and board-deck-builder
CTO additions:
- Key Questions section (7 diagnostic questions)
- Structured metrics table (DORA + debt + team + architecture + cost)
- Cross-references to all peer roles
All 10 roles now pass structural parity: ✅ Keywords ✅ QuickStart ✅ Questions ✅ Metrics ✅ RedFlags ✅ Integration
* feat: add proactive triggers + output artifacts to all 10 roles
Every C-suite role now specifies:
- Proactive Triggers: 'surface these without being asked' — context-driven
early warnings that make advisors proactive, not reactive
- Output Artifacts: concrete deliverables per request type (what you ask →
what you get)
CEO: runway alerts, board prep triggers, strategy review nudges
CTO: deploy frequency monitoring, tech debt thresholds, bus factor flags
COO: blocker detection, scaling threshold warnings, cadence gaps
CPO: retention curve monitoring, portfolio dog detection, research gaps
CMO: CAC trend monitoring, positioning gaps, budget staleness
CFO: runway forecasting, burn multiple alerts, scenario planning gaps
CRO: NRR monitoring, pipeline coverage, pricing review triggers
CISO: audit overdue alerts, compliance gaps, vendor risk
CHRO: retention risk, comp band gaps, org scaling thresholds
Executive Mentor: board prep triggers, groupthink detection, hard call surfacing
This transforms the C-suite from reactive advisors into proactive partners.
* feat: User Communication Standard — structured output for all roles
Defines 3 output formats in agent-protocol/SKILL.md:
1. Standard Output: Bottom Line → What → Why → How to Act → Risks → Your Decision
2. Proactive Alert: What I Noticed → Why It Matters → Action → Urgency (🔴 🟡 ⚪ )
3. Board Meeting: Decision Required → Perspectives → Agree/Disagree → Critic → Action Items
10 non-negotiable rules:
- Bottom line first, always
- Results and decisions only (no process narration)
- What + Why + How for every finding
- Actions have owners and deadlines ('we should consider' is banned)
- Decisions framed as options with trade-offs
- Founder is the highest authority — roles recommend, founder decides
- Risks are concrete (if X → Y, costs $Z)
- Max 5 bullets per section
- No jargon without explanation
- Silence over fabricated updates
All 10 roles reference this standard.
Chief of Staff enforces it as a quality gate.
Board meeting Phase 4 uses the Board Meeting Output format.
* feat: Internal Quality Loop — verification before delivery
No role presents to the founder without passing verification:
Step 1: Self-Verification (every role, every time)
- Source attribution: where did each data point come from?
- Assumption audit: [VERIFIED] vs [ASSUMED] tags on every finding
- Confidence scoring: 🟢 high / 🟡 medium / 🔴 low per finding
- Contradiction check against company-context + decision log
- 'So what?' test: every finding needs a business consequence
Step 2: Peer Verification (cross-functional)
- Financial claims → CFO validates math
- Revenue projections → CRO validates pipeline backing
- Technical feasibility → CTO validates
- People/hiring impact → CHRO validates
- Skip for single-domain, low-stakes questions
Step 3: Critic Pre-Screen (high-stakes only)
- Irreversible decisions, >20% runway impact, strategy changes
- Executive Mentor finds weakest point before founder sees it
- Suspicious consensus triggers mandatory pre-screen
Step 4: Course Correction (after founder feedback)
- Approve → log + assign actions
- Modify → re-verify changed parts
- Reject → DO_NOT_RESURFACE + learn why
- 30/60/90 day post-decision review
Board meeting contributions now require self-verified format with
confidence tags and source attribution on every finding.
* fix: resolve PR review issues 1, 4, and minor observation
Issue 1: c-level-advisor/CLAUDE.md — completely rewritten
- Was: 2 skills (CEO, CTO only), dated Nov 2025
- Now: full 28-skill ecosystem map with architecture diagram,
all roles/orchestration/cross-cutting/culture skills listed,
design decisions, integration with other domains
Issue 4: Root CLAUDE.md — updated all stale counts
- 87 → 134 skills across all 3 references
- C-Level: 2 → 33 (10 roles + 5 mentor commands + 18 complementary)
- Tool count: 160+ → 185+
- Reference count: 200+ → 250+
Minor observation: Documented plugin.json convention
- Explained in c-level-advisor/CLAUDE.md that only executive-mentor
has plugin.json because only it has slash commands (/em: namespace)
- Other skills are invoked by name through Chief of Staff or directly
Also fixed: README.md 88+ → 134 in two places (first line + skills section)
* fix: update all plugin/index registrations for 28-skill C-suite
1. c-level-advisor/.claude-plugin/plugin.json — v2.0.0
- Was: 2 skills, generic description
- Now: all 28 skills listed with descriptions, all 25 scripts,
namespace 'cs', full ecosystem description
2. .codex/skills-index.json — added 18 complementary skills
- Was: 10 roles only
- Now: 28 total c-level entries (10 roles + 6 orchestration +
6 cross-cutting + 6 culture)
- Each with full description for skill discovery
3. .claude-plugin/marketplace.json — updated c-level-skills entry
- Was: generic 2-skill description
- Now: v2.0.0, full 28-skill ecosystem description,
skills_count: 28, scripts_count: 25
* feat: add root SKILL.md for c-level-advisor ClawHub package
---------
Co-authored-by: Leo <leo@openclaw.ai>
2026-03-06 01:35:08 +01:00
