moonlight-lupin/agent-skills / software-development/skill-quality-review
skill-quality-review
VerifiedUse when auditing or reviewing skill quality — batch checks across a library, deep per-skill grep methodology, usage stats, efficacy testing, or fix planning. Single consolidated home for the writing-for-agents review framework and the 3-surface review methodology.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 33.1 KB |
| references/batch-checks.md | markdown | 23.4 KB |
| references/claude-plugin-review.md | markdown | 10.8 KB |
| references/domain-passive-voice.md | markdown | 1.8 KB |
| references/efficacy-ab-test.md | markdown | 6.3 KB |
| references/fix-phase-pitfalls.md | markdown | 3.3 KB |
| references/hermes-library-review.md | markdown | 3.3 KB |
| references/independent-skills.md | markdown | 2.1 KB |
| references/recurring-failure-patterns.md | markdown | 15.0 KB |
| references/skill-review-methodology.md | markdown | 38.9 KB |
| references/writing-for-agents-framework.md | markdown | 12.2 KB |
| scripts/add_toc.py | script | 5.8 KB |
| scripts/check_calls.py | script | 26.2 KB |
| scripts/check_references.py | script | 6.3 KB |
| templates/efficacy-rubric-template.md | markdown | 1.1 KB |
| tests/acceptance.md | markdown | 1.5 KB |
| tests/test_harness_acceptance.py | script | 4.7 KB |
references/independent-skills.md
View on GitHub# Independent Skills When a Reference Toolkit Exists
When building an agent skill for a domain where a separate reference toolkit already exists (e.g. an accounting-toolkit repo with 34 skills and 7 foundations, or a separate audit-suite plugin), the new skill must be **independent**.
## The pattern
1. A domain has an existing, comprehensive reference toolkit (foundations, engines, playbooks).
2. A new product-specific skill is needed (e.g. an ERP agent skill that calls MCP tools).
3. The new skill covers the same domain ground but binds to a different execution layer.
## What to do
- **Study the reference toolkit** for domain coverage — read its foundations, engines, and skill playbooks.
- **Do gap analysis** — identify what the new skill's reference files miss that the reference toolkit covers.
- **Fill the gaps** into the new skill's own reference files with original content.
- **No cross-references** — do not link to the reference toolkit repo, do not mention it by name, do not say "see accounting-toolkit/foundations/doctrine.md".
- **The skill stands on its own.** A user who installs only the new skill gets full domain coverage without needing the reference toolkit.
## User correction (Aug 2026)
User said: "Want it to be independent. I want the Hermes erp agent skill to see if there's any gap with accounting toolkit and bridge that accordingly."
The first attempt linked the ERP skill to the accounting-toolkit repo with cross-references. The user corrected this. The fix was to revert all cross-references, study the accounting-toolkit for domain content, and write 7 new reference files + update 3 existing ones with original content covering the same ground.
## Why independence matters
- The reference toolkit may be private, licensed differently, or move repositories.
- A skill that depends on an external repo breaks when that repo is unavailable.
- The skill should be self-contained for distribution.
- Gap analysis against a reference toolkit is a technique for ensuring coverage — the reference toolkit informs the content, but does not appear in the output.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |