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/domain-passive-voice.md
View on GitHub# Domain-Specific Passive Voice False Positives
When reviewing skills in regulated or technical domains (accounting, law, medicine, engineering), the passive voice heuristic (`is \w+ed`, `are \w+ed`, `was \w+ed`, `were \w+ed`) flags domain-standard terminology as passive voice. These are correct usage, not writing failures.
## Examples by domain
### Accounting (SG FRS, IFRS)
- "revenue is recognised when earned" — SG FRS 18 standard phrasing
- "the period is closed" — period status terminology
- "receipts are recorded as deferred income" — accounting policy description
- "items are matched" — reconciliation terminology
- "output tax is recorded as a liability" — GST phrasing
### Legal
- "the contract is governed by" — jurisdiction phrasing
- "damages are awarded" — court terminology
### Medical
- "the patient is administered" — clinical phrasing
- "the dose is adjusted" — protocol phrasing
## When to fix vs when to leave
**Fix** — passive voice hides a knowable actor the agent needs to understand:
- "is enforced in approve_entry()" → "the engine enforces this in approve_entry()" ✓
- "are stored as hashes" → "the store hashes all secrets" ✓
**Leave** — passive construction names a domain-standard phrase from an authoritative source:
- "revenue is recognised when earned" — leave (SG FRS 18 standard)
- "the period is closed" — leave (period status terminology)
- "tax is recorded as a liability" — leave (accounting policy)
## Rule of thumb
If the passive construction names a domain-standard phrase from an authoritative standard (FRS, IFRS, IAS, legal statute, clinical protocol), leave it. The connection to the standard matters more than active voice style.
If the passive construction hides a knowable actor that the agent needs to understand (engine, system, user, store), fix it to active voice.
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 |