Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Capture a session summary — what was done, what decisions were made, and what to do next.
.claude/skills/sharpdeveye-capture/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 86% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 310% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 136% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 129% | 0% |
Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first.
Capture the current session's work into a persistent summary. This creates a record that survives session boundaries — future commands can reference what happened here.
Read the conversation history and identify:
Generate a session summary file at .maestro/sessions/{date}_{topic}.md:
markdown# Session: {topic} Date: {YYYY-MM-DD} ## Commands Run - /diagnose → Score: 18/25 - /fortify → Added retry logic to API handlers - /evaluate → Verified with 3 test scenarios ## Decisions - Chose retry-with-backoff over circuit breaker (simpler, sufficient for current load) - Kept synchronous error handling (async not justified yet) ## Files Changed - `src/api/handler.ts` — added retry wrapper - `src/middleware/auth.ts` — added input validation - `tests/api.test.ts` — new test file ## Open Issues - Rate limiting not yet implemented (deferred to next session) ## Next Steps 1. Run `/guard` to add rate limiting 2. Run `/evaluate` with adversarial test cases
Also append a decision entry to .maestro/decisions.jsonl recording this capture.
.maestro/sessions/After capturing, your next session should start with /recap to restore context, then proceed with the next steps listed above.
NEVER:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 8,224 | 3,607 | -56% | 1 | 1 | 0% | 1,337 | 1,065 | -20% | 0 | 0 | — |
case-02 | fail→fail | 9,056 | 3,625 | -60% | 1 | 1 | 0% | 1,414 | 696 | -51% | 0 | 0 | — |
case-03 | fail→fail | 6,793 | 5,255 | -23% | 1 | 1 | 0% | 1,065 | 792 | -26% | 0 | 0 | — |
case-04 | fail→fail | 10,309 | 8,088 | -22% | 1 | 1 | 0% | 1,623 | 1,205 | -26% | 0 | 0 | — |
case-05 | fail→fail | 5,982 | 6,301 | +5% | 1 | 1 | 0% | 252 | 928 | +268% | 0 | 0 | — |
case-06 | fail→fail | 6,130 | 8,131 | +33% | 1 | 1 | 0% | 323 | 1,344 | +316% | 0 | 0 | — |
case-07 | fail→fail | 7,426 | 6,099 | -18% | 1 | 1 | 0% | 496 | 899 | +81% | 0 | 0 | — |
case-08 | fail→pass | 8,093 | 10,140 | +25% | 1 | 1 | 0% | 1,344 | 2,503 | +86% | 0 | 0 | — |
case-09 | fail→pass | 5,029 | 10,820 | +115% | 1 | 1 | 0% | 618 | 2,535 | +310% | 0 | 0 | — |
case-10 | fail→fail | 3,223 | 4,421 | +37% | 1 | 1 | 0% | 273 | 757 | +177% | 0 | 0 | — |
case-11 | fail→fail | 4,580 | 13,825 | +202% | 1 | 1 | 0% | 495 | 2,848 | +475% | 0 | 0 | — |
case-12 | fail→pass | 6,726 | 2,911 | -57% | 1 | 1 | 0% | 1,212 | 1,062 | -12% | 0 | 0 | — |
case-13 | fail→fail | 10,796 | 7,763 | -28% | 1 | 1 | 0% | 2,065 | 1,017 | -51% | 0 | 0 | — |
case-14 | fail→fail | 9,815 | 30,537 | +211% | 1 | 1 | 0% | 1,698 | 884 | -48% | 0 | 0 | — |
case-15 | fail→pass | 13,352 | 11,373 | -15% | 1 | 1 | 0% | 1,119 | 2,645 | +136% | 0 | 0 | — |
case-16 | fail→fail | 11,255 | 12,061 | +7% | 1 | 1 | 0% | 1,482 | 2,874 | +94% | 0 | 0 | — |
case-17 | fail→fail | 9,130 | 14,912 | +63% | 1 | 1 | 0% | 1,583 | 3,165 | +100% | 0 | 0 | — |
case-18 | fail→pass | 5,885 | 7,725 | +31% | 1 | 1 | 0% | 833 | 1,911 | +129% | 0 | 0 | — |
case-19 | fail→fail | 4,006 | 18,459 | +361% | 1 | 1 | 0% | 709 | 2,834 | +300% | 0 | 0 | — |
case-20 | pass→pass | 10,104 | 16,432 | +63% | 1 | 1 | 0% | 1,677 | 3,266 | +95% | 0 | 0 | — |
case-21 | pass→fail | 8,317 | 6,287 | -24% | 1 | 1 | 0% | 294 | 959 | +226% | 0 | 0 | — |
case-22 | pass→pass | 13,667 | 11,915 | -13% | 1 | 1 | 0% | 2,216 | 2,498 | +13% | 0 | 0 | — |
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 12 counted toward the lift figure. The other 10 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 +18 percentage points is the difference between those two pass rates over the 12 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.