# Skill Audit

> Compares compiled Skills against recent BehavioralTraces to detect workflow drift or obsolescence. Use when auditing learned skills, checking if a Soulcatcher skill still matches behavior, or after major project changes.

- Skill: `justtyashh/skill-audit` (Agent Skill)
- Install (CLI): `npx skillmds@latest add justtyashh/skill-audit`
- Raw SKILL.md: https://api.skillmd.com/api/skills/justtyashh/skill-audit/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: JusttYashh (https://skillmd.com/u/justtyashh)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/justtyashh/skill-audit

---


# Skill Audit

Test whether a compiled Skill still matches how work actually happens.

Read schemas in [../soulcatcher/reference.md](../soulcatcher/reference.md).

## Input

- Compiled skill in `learned-skills/{skill-name}/` (SKILL.md + evidence.md)
- Recent BehavioralTraces (3+ sessions since compile date, or user-specified window)

## Process

1. Read compiled SKILL.md procedure steps
2. Read evidence.md baseline (original sessions, sequence, confidence)
3. Observe recent sessions → new BehavioralTraces
4. Compare recent sequences to compiled steps
5. Score alignment per core step (% of recent sessions where step appeared)
6. Issue verdict

## Alignment Scoring

| Core step present in session | Score |
|------------------------------|-------|
| Yes, same position | 1.0 |
| Yes, different position | 0.5 |
| Skipped | 0.0 |

**Alignment** = average across core steps and recent sessions × 100

## Verdicts

| Verdict | Condition | Action |
|---------|-----------|--------|
| `still_valid` | Alignment ≥ 80% | No change |
| `drift_detected` | Alignment 50–79% | Propose SKILL.md diff or re-run pipeline |
| `obsolete` | Alignment < 50% | Recommend deprecating or full re-learn |

## Output Format

```markdown
# Skill Audit: {skill-name}

**Verdict:** still_valid | drift_detected | obsolete
**Alignment:** {N}%
**Sessions audited:** {count}
**Compile date:** {from evidence.md}

## Step alignment

| Step | Recent presence |
|------|-----------------|
| Generate candidates | 5/5 sessions |
| Search counterexamples | 3/5 sessions ⚠ |
| ... | ... |

## Drift details

{What changed — e.g. user now skips counterexample search under time pressure}

## Recommendation

{Keep skill | Patch step 4 as optional | Re-run Soulcatcher on recent sessions}
```

## Cadence

Suggest audit when:
- User requests it
- 10+ new relevant sessions since compile
- Major role or project shift