mirror of
https://github.com/alirezarezvani/claude-skills.git
synced 2026-08-28 04:24:58 +00:00
8 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Alireza Rezvani
|
4570768781
|
Merge pull request #936 from benrfairless/fix/frontmatter-yaml-validation
fix(frontmatter): repair 14 unloadable YAML blocks + add gate G10 |
||
|
Claude
|
7405298b4b
|
fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885)
- #954: strip non-spec source/attribution keys from all 39 plugin.json manifests so Claude Code's validator accepts them; metadata preserved in new .claude-plugin/authoring-notes.json sidecars; check_plugin_json.py now hard-fails manifests carrying those keys and sanity-checks the sidecar; CLAUDE.md ClawHub schema section updated to the new rule. - #949: move the c-level-agents plugin out of c-level-advisor/ to a top-level directory so the two marketplace sources no longer overlap; updated marketplace.json source, homepage, descriptions, all cross-references, docs, harness manifest, mirror-tree symlinks/indexes, and rebased the moved files' relative links; domain counters trued up (18 -> 19 domains). - #933: replace dead links to the gitignored maintainer-local megaprompts/ tree with annotated plain-text references (44 files: SKILL.md, READMEs, agents, commands). - #931: DynamoDB on-demand pricing updated to post-Nov-2024 rates ($0.625/M writes, $0.125/M strongly consistent reads). - #969: skill_security_auditor.py and the three dossier scripts reconfigure stdout/stderr to UTF-8 (errors=replace) so legacy Windows codepages no longer crash at print time; PYTHONUTF8=1 documented. - #968: Windows Notes section in INSTALLATION.md + README pointer for the core.symlinks mirror-tree checkout caveat. - #924/#885 residuals: hook commands quote "${CLAUDE_PLUGIN_ROOT}" paths in all plugin hooks.json/settings.json (space-safe roots); removed the stale pre-rename status/review mirror symlinks and index entries left over from the memory-status/memory-review rename. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Qgc6RYXWJPr5oW9DHU7zR4 |
||
|
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
|
||
|
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
|
||
|
Claude
|
3db7dab15f
|
chore(versioning): unify remaining 20 plugins to 2.9.0
PR #756 normalized most marketplace versions to 2.9.0, but 20 newer plugins (added after the normalization pass) remained on their own versions on both marketplace.json and their plugin.json. Bump them all to 2.9.0 so the registry advertises one unified release version, with marketplace.json and every plugin.json fully in sync (62/62 at 2.9.0). https://claude.ai/code/session_01JGwZR83iSg59EAtpTSCBjH |
||
|
Claude
|
8fd073c49d
|
feat(v2.8.0-sprint2-complete): add final 5 sub-skills (knowledge-ops, procurement-optimizer, commercial-policy, rfp-responder, commercial-forecaster)
Completes Sprint 2 of v2.8.0 — all 9 remaining sub-skills now in. Both business-operations/ and commercial/ domains fully complete (7 + 8 skills incl. orchestrators). ## New skills (5 — final batch) ### business-operations (+2) - knowledge-ops (context: fork) — Company SOPs + runbooks + KB hygiene with 5W2H scaffolding. 3 tools: sop_generator (5W2H Who/What/When/Where/Why/How/ How-much with 5 regulatory overlays SOC2/HIPAA/ISO13485/GDPR/SOX), runbook_validator (6-rule per-step check, vague-token detection like "the team", "service is up"), kb_ingester (cross-link map + orphans + stale + glossary drift detection). 6 industry profiles. Canon: Ishikawa (5W2H origin), Liker (Toyota SOP), Gawande (Checklist Manifesto), ISO 9001, ITIL v4, FDA 21 CFR Part 211, Google SRE Workbook, AWS Well-Architected, Atlassian Team Playbook. Distinct from engineering/llm-wiki (personal PKM) and engineering-team/runbook-generator (system-ops). - procurement-optimizer — UNSPSC-aligned spend categorization + supplier rationalization. 3 tools: spend_categorizer (~30-category built-in map, Pareto top-20%, YoY growth), purchasing_cycle_analyzer (Goldratt 2× median bottleneck flag), supplier_consolidation (duplicate-function clustering, HARD REFUSAL for tier-1 single-source without break_glass_documented, renewal-month clustering flag). 5 industry profiles. Canon: A.T. Kearney, Spend Matters/Mitchell, Hackett, BCG, Procurement Leaders, Gartner, UNSPSC, IACCM, Productiv, Zylo, Vendr, Tropic, BetterCloud. Distinct from sibling vendor-management (performance scoring of kept vendors). ### commercial (+3) - commercial-policy — Data-backed discount matrix + exception flow + linter. 3 tools: discount_matrix_builder (4-dim ARR×term×payment×strategic matrix with per-cell data backing + approver tier + margin floor), exception_router (severity-tiered compensating commitments, machine-readable audit_trail JSON, precedent-risk check flags matrix-rebuild if 3+ similar exceptions in trailing Q), policy_linter (10 lint rules L01-L10 BLOCKER/MAJOR/MINOR: approver-inversion, band-inversion, margin-floor, coverage-gap, cliff-edge, strategic-undefined). Canon: OpenView, Skok, Tunguz, BVP, KeyBanc, SaaStr, Winning by Design, Forrester, McKinsey, Bain. Distinct from sibling deal-desk (applies policy) and pricing-strategist (sets model). - rfp-responder (context: fork) — Shipley-method structured RFP/RFI/RFQ response. 3 tools: rfp_parser (section + requirement extractor with NICE>MANDATORY>WEIGHTED precedence, correctly handles "preferred but not required" as NICE despite containing "required"), response_drafter (proof-point matrix with STRONG/PARTIAL/GAP, win-theme threading flags decorative themes, HARD RULE: never invent claims for GAP, surface them for leadership decision), winrate_predictor (Shipley factor model with BID/PARTNER-BID/NO-BID verdict at 35%/20% thresholds). 5 industry profiles. Canon: Shipley Proposal Guide v6, Shipley Capture Guide, APMP BoK, Sant, Searcy+DeVries, Strategic Proposals, FAR, GSA, Forrester, Bain. Distinct from business-growth/contract-and-proposal-writer (free-form authoring). - commercial-forecaster — 4Q-weighted bookings + cohort NRR/GRR + funnel- confidence with MANDATORY assumption disclosure. 3 tools: bookings_ forecaster (3-tier commit/best-case/pipe-only with 70/30 last-4Q/last-12Q blend, time-to-close decay, stall rule, pipeline-coverage warning at <3x, sandbag/hockey-stick detection; non-optional assumption block in every output), cohort_arr_projector (per-cohort NRR/GRR + leaky-cohort flag at ≥5pp gap vs trailing mean), funnel_confidence_scorer (CoV bands HIGH/ MEDIUM/LOW/VERY-LOW with 4 treatment recommendations). 5 industry profiles. Canon: Skok, Tunguz, OpenView, BVP, KeyBanc, ProfitWell/Campbell, Chen, Balfour, Ramanujam, Rachitsky, Reforge. Distinct from finance/financial- analysis (close+report — backward) and cfo-advisor (strategic). ## Verification - All 39 v2.8.0 Python tools (4 Sprint-1 sub-skills + 9 Sprint-2 sub-skills, 3 tools each, plus 0 from orchestrators) pass --help and --sample (exit 0) - All Python 3.11 compileall clean (no syntax errors) - Local pytest passes 2101 tests - Stdlib-only verified across all tools ## Sprint 2 totals - 9 new sub-skills (4 in previous commit + 5 in this commit) - 27 new Python tools (3 per sub-skill) - 9 new slash commands (one per sub-skill) - 27 new reference docs (3 per sub-skill, each citing ≥7 authoritative sources) - 10 new asset templates (1 per sub-skill, except knowledge-ops which has 2) - Updates to plugin.json × 2, CLAUDE.md × 2, README.md × 2, marketplace.json ## v2.8.0 final totals - 2 new top-level domains: business-operations (7 skills), commercial (8 skills) - 39 stdlib Python tools across 13 sub-skills + 2 orchestrators - 39 reference docs citing ≥7 authoritative sources each - 2 cs-* agents - 17 new slash commands (8 Sprint-1 + 9 Sprint-2) - 59 marketplace plugins (was 57; +2 for the new domain plugins) https://claude.ai/code/session_015bBb4HzWCf5HH5QK2TGtnW |
||
|
Claude
|
a42cb9bec4
|
feat(v2.8.0-sprint2-partial): add 4 sub-skills (capacity-planner, internal-comms, channel-economics, partnerships-architect)
Partial Sprint 2 commit — 4 of 9 remaining sub-skills done. 5 more in-flight
(knowledge-ops, procurement-optimizer, commercial-policy, rfp-responder,
commercial-forecaster) will land in follow-up commit.
## New skills
### business-operations (+2)
- capacity-planner — Erlang-C queueing math for ops teams (CX/Support/CS/BizOps/
IT ops/Finance ops). Pure-stdlib Erlang-C in log-space (avoids factorial
overflow). 3 tools: capacity_modeler (P50/P90/P99 SLA breach + 4-tier risk
band), utilization_analyzer (red-zone detection per Little's Law),
hiring_sequencer (12-month quarterly plan with ramp + attrition + growth +
span-of-control manager trigger). 5 industry profiles. Canon: Erlang 1909,
Little 1961, Hopp & Spearman, Reinertsen, Kingman, Cleveland, ITIL, Armony.
Distinct from vpe-advisor (eng-specific) and project-management (tracking).
- internal-comms — ADKAR + Kotter 8-step change comms. 3 tools:
comms_template_filler (ADKAR-tagged 4-artifact package), change_announcement_
builder (Kotter-labeled output with magnitude/tone validation — rejects
celebratory framing on disruptive change, layoff keywords without disruptive
magnitude), comms_calendar_builder (7-touchpoint sequencing with anti-pattern
flags like Slack-only-for-layoff). 5 tone profiles. Canon: Hiatt (Prosci),
Kotter, Bridges, Schein, McKinsey 7-S, Heath brothers, Lencioni, Edelman,
Gallup, Welch & Jackson, IABC. Distinct from marketing-skill (external) and
c-level-advisor/internal-narrative (strategic).
### commercial (+2)
- channel-economics — Direct vs partner-led economics. 3 tools:
cost_to_serve_calculator (fully-loaded CTS per deal + per $ ARR, hidden-cost
flags, inconsistent-allocation warnings), channel_roi_analyzer (3-lens ROI:
Cash / LTV / Marginal with diminishing-returns inflection point + verdict
DOUBLE-DOWN/MAINTAIN/DEFUND/EXIT), channel_mix_optimizer (effective LTV +
payback + LTV-CAC, discrete grid-search constrained optimizer, sensitivity
scenarios). 5 industry profiles. Canon: Skok, BVP, Tunguz, KeyBanc, Ramanujam,
McBain, OpenView, Kaplan & Cooper, Horngren, McKinsey, BCG. Distinct from
partnerships-architect (structure not economics) and revenue-operations.
- partnerships-architect — 5-tier partner classifier + joint GTM + revshare.
3 tools: partner_tier_classifier (REFERRAL/RESELLER/OEM/SI/STRATEGIC with
hard floors per tier — STRATEGIC requires ≥5 named accounts sourced +
multi-year commit + dedicated resources), joint_gtm_planner (tier×motion
compatibility matrix, refuses channel_led for REFERRAL, refuses white_label
outside OEM), revshare_modeler (direct vs via-partner margin, recommended
band by tier × contribution depth, break-even sourced-deal count, 3-yr NPV).
5 industry profiles. Canon: Caro/HP, Chintagunta, Hessling, Forrester, IDC,
Tzuo, Moore, MPN, AWS APN. Distinct from sales-engineer (tech sale) and
ma-playbook (acquisition).
## Infrastructure (full Sprint 2 coverage)
- 9 new slash commands (one per Sprint 2 sub-skill): /cs:capacity-plan,
/cs:internal-comms, /cs:knowledge-ops, /cs:procurement, /cs:partner-tier,
/cs:channel-econ, /cs:commercial-policy, /cs:rfp-respond,
/cs:commercial-forecast
- business-operations/.claude-plugin/plugin.json: skills array expanded
to all 7 (orchestrator + 6 sub-skills)
- commercial/.claude-plugin/plugin.json: skills array expanded to all 8
(orchestrator + 7 sub-skills)
- Domain CLAUDE.md + README.md updated with Sprint 2 skills
- .claude-plugin/marketplace.json: version 2.7.3 → 2.8.0, top-level
description bumped to 328 skills across 14 domains, expanded keywords
on both new plugins
- Master plan updated to reflect Sprint 2 in-progress
## Hard rules per skill (Matt Pocock discipline)
- Every SKILL.md ships a Forcing-question library section (5-7 cited
canon-anchored questions, one-at-a-time discipline)
- Every Python tool is stdlib-only (verified: argparse, json, sys, pathlib,
statistics, dataclasses, enum, math, re, collections only)
- Industry tuning via --profile on scoring tools
- All 12 new tools pass --help + --sample (exit 0)
## Sprint 2 remaining (next commit)
knowledge-ops (5W2H SOP+runbook + KB hygiene, context: fork)
procurement-optimizer (UNSPSC spend categorization + supplier consolidation)
commercial-policy (data-backed discount matrix + exception flow + linter)
rfp-responder (Shipley structured RFP/RFI/RFQ + winrate predictor, context: fork)
commercial-forecaster (4Q-weighted bookings + cohort NRR/GRR + funnel-confidence
with mandatory assumption disclosure)
https://claude.ai/code/session_015bBb4HzWCf5HH5QK2TGtnW
|
||
|
Claude
|
7947638b31
|
feat(v2.8.0-sprint1): add business-operations + commercial top-level domains
Two new top-level domain folders expanding the repo from 313 → 319 production
skills across 14 domains. Path-B 11-file contract per skill, stdlib-only Python
tools, Matt Pocock grill-with-docs discipline baked into every SKILL.md.
## New domains
- business-operations/ — internal-ops skills for BizOps leads, COO direct
reports, vendor management, IT ops. Sprint 1 ships 3 skills:
- business-operations-skills (orchestrator, context: fork)
- process-mapper (BPMN + bottleneck + cycle-time, 4 industry profiles,
Lean/TOC canon)
- vendor-management (scorecard + SLA + 3rd-party risk, 4 industry profiles,
Shared Assessments SIG-Lite, NIST SP 800-161, ISO/IEC 27036)
- commercial/ — per-deal-and-packaging skills. Sprint 1 ships 3 skills:
- commercial-skills (orchestrator, context: fork)
- pricing-strategist (5-model picker, Van Westendorp PSM with OPP/IDP/PMC/PME,
packaging with 7 anti-pattern detectors, Ramanujam/Skok/Tunguz canon)
- deal-desk (5-dim scorer, discount approval router, 10-pattern terms redliner,
never auto-approves — every verdict names the human approver)
## Chaining via context: fork
Both domain orchestrators set context: fork in frontmatter so heavy ingestion
(vendor catalogs, RFP docs, process transcripts) stays out of the parent
session. Sub-skills opt into fork only when they ingest large artifacts
(vendor-management does, pricing-strategist and deal-desk do not).
## Matt Pocock grill discipline
Every Sprint 1 SKILL.md ships a "Forcing-question library" section: 5-7
questions, walked one at a time by the orchestrator (or /cs:grill-bizops,
/cs:grill-commercial), each with a recommended answer + canon citation.
Discipline derived from engineering/grill-me + engineering/grill-with-docs
(Matt Pocock, MIT).
## Hard rules per domain
- BizOps: every output is a recommendation, never an auto-decision.
- Commercial: pricing outputs model+range (never a single number); deal outputs
route to a named human approver (never auto-approve); forecasts surface the
conversion assumption explicitly.
## Agents + commands
- cs-bizops-orchestrator agent ("Where does the work spend most of its time
waiting?")
- cs-commercial-orchestrator agent ("What's the margin on this deal at full
discount?")
- 8 new slash commands: /cs:bizops, /cs:commercial, /cs:grill-bizops,
/cs:grill-commercial, /cs:process-map, /cs:vendor-review, /cs:pricing-strategy,
/cs:deal-review
## Verification
- All 12 new Python tools (4 skills × 3 each) pass --help and --sample
smoke tests, exit 0
- Stdlib-only across the board
- 12 reference docs each cite ≥ 7 authoritative sources
- Marketplace registry: 57 → 59 plugins
## Sprint 2 (not in this PR)
- BizOps: capacity-planner, internal-comms, knowledge-ops, procurement-optimizer
- Commercial: partnerships-architect, channel-economics, commercial-policy,
rfp-responder, commercial-forecaster
## Files
50 new files: 6 SKILL.md (2 orchestrators + 4 leaf) + 12 Python tools + 12
references + 4 asset templates + 2 plugin.json + 2 CLAUDE.md + 2 README.md +
2 cs-* agents + 8 slash commands + 1 master plan doc + marketplace.json +
root CLAUDE.md update.
Master plan: documentation/implementation/bizops-commercial-expansion-plan.md
https://claude.ai/code/session_015bBb4HzWCf5HH5QK2TGtnW
|