claude-skills/engineering/skills/monorepo-navigator
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
..
references fix(plugins): restructure 9 multi-skill domain plugins into ./skills/ layout 2026-05-02 22:51:20 +02:00
scripts fix(plugins): restructure 9 multi-skill domain plugins into ./skills/ layout 2026-05-02 22:51:20 +02:00
SKILL.md fix(v2.6.2): fix remaining 11 placeholder descriptions 2026-05-14 05:08:23 +00:00