Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Phase transition validation with artifact checklists, PASS/FAIL/CONDITIONAL gates for workflows
.claude/skills/gate-check/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | — | — |
| case-05 | ✗→✓ | ▲ Improved | — | — |
| case-11 | ✗→✓ | ▲ Improved | — | — |
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
Faz gecis validasyonu. Bir sonraki faza gecmeden once gerekliliklerin tamam oldugundan emin ol.
Planning ──▶ Development ──▶ Testing ──▶ Staging ──▶ Production
G1 G2 G3 G4 G5| # | Kriter | Kanit | |---|--------|-------| | 1 | Requirements dokumani var | PRD/spec dosyasi | | 2 | Teknik plan onaylandi | Plan dosyasi + onay | | 3 | Task'lar olusturuldu | Task listesi | | 4 | Dependency'ler belirlendi | Dependency listesi | | 5 | Risk analizi yapildi | Risk matrisi (opsiyonel) |
| # | Kriter | Kanit | |---|--------|-------| | 1 | Tum task'lar implement edildi | Task durumlari | | 2 | Code review tamamlandi | Review onaylari | | 3 | Build basarili | Build log | | 4 | Unit test coverage >= 80% | Coverage raporu | | 5 | Lint/type check temiz | Lint raporu | | 6 | Security review (auth/data isleri) | Security raporu |
| # | Kriter | Kanit | |---|--------|-------| | 1 | Unit testler PASS | Test raporu | | 2 | Integration testler PASS | Test raporu | | 3 | E2E critical path testleri PASS | Playwright raporu | | 4 | Bug'lar triaged (P0/P1 yok) | Bug listesi | | 5 | Performance baseline karsilandi | Metrikler |
| # | Kriter | Kanit | |---|--------|-------| | 1 | Staging'de 24h+ stabil | Monitoring | | 2 | Smoke testler PASS | Test raporu | | 3 | Rollback plani hazir | Rollback dokumani | | 4 | Changelog yazildi | CHANGELOG.md | | 5 | Stakeholder onay | Onay kaydi |
| Karar | Anlam | Aksiyon | |-------|-------|---------| | PASS | Tum kriterler saglanmis | Sonraki faza gec | | FAIL | Kritik kriter(ler) saglanmamis | Mevcut fazda kal, eksikleri tamamla | | CONDITIONAL | Minor eksikler var, ilerlenebilir | Sonraki faza gec, eksikleri paralel tamamla |
GATE CHECK: G2 (Development -> Testing)
Date: [tarih]
[PASS] Build basarili
[PASS] Code review tamamlandi
[PASS] Lint/type check temiz
[FAIL] Unit test coverage 72% (min 80%)
[PASS] Security review temiz
[PASS] Tum task'lar implement edildi
KARAR: FAIL
NEDEN: Test coverage yetersiz (72% < 80%)
AKSIYON: Test ekle, %80 ustune cik, gate check'i tekrarlaProjeye ozel gate tanimlamak icin:
markdown### Custom Gate: [Isim] | # | Kriter | Zorunlu | Kanit | |---|--------|---------|-------| | 1 | [Kriter] | Evet/Hayir | [Ne bekleniyor] |
Zorunlu=Evet olan kriterler FAIL'de FAIL, Zorunlu=Hayir olan CONDITIONAL'a duser.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
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. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.