Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Autonomous skill lifecycle manager. Reviews skill-compounder drafts, promotes high-confidence patterns, merges duplicates, archives low-quality drafts. Zero manual review required - runs on every session start.
.claude/skills/skill-curator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-02 | ✗→✓ | ▲ Improved | — | — |
| case-20 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✗→✓ | ▲ Improved | — | — |
| case-22 | ✗→✓ | ▲ Improved | — | — |
Autonomous skill lifecycle system. Works in partnership with skill-compounder to close the loop: observe -> draft -> review -> promote.
1. You work normally (no manual action needed)
2. skill-compounder (Stop hook) detects successful patterns
3. Draft written to ~/.claude/skills-drafts/
4. skill-curator (SessionStart hook) reviews all drafts
5. Drafts are either:
- PROMOTED to ~/.claude/skills/ (confidence >= 80, no duplicates)
- MERGED with existing similar skill
- ARCHIVED to ~/.claude/skills-drafts/archive/ (confidence < 50)
- KEPT in drafts for next review (50-79, needs more evidence)A draft is auto-promoted when ALL of these are true:
| Criterion | Threshold | |-----------|-----------| | Confidence | >= 80 | | Occurrences | >= 3 (or category is error-recovery) | | Uniqueness | Not duplicate of existing skill | | Age | Less than 14 days old | | Category | One of: repeated-workflow, error-recovery, domain-pattern |
A draft is auto-archived when ANY of these are true:
Before promoting, check against existing skills:
If duplicate found, either merge evidence into existing skill or archive.
Drafts live in ~/.claude/skills-drafts/<name>.md:
yaml--- name: pattern-abc123 description: "Procedural pattern: Read -> Edit -> Test -> Commit" category: repeated-workflow confidence: 85 occurrences: 7 source_session: s-xyz789 generated_at: 2026-04-12T03:45:00Z status: draft ---
When promoted, status: draft becomes status: active.
Tracked in ~/.claude/skill-evolution.jsonl:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +68 percentage points is the difference between those two pass rates over the 19 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.