wehub-resource-sync
d48cda4081
CI / Test (ubuntu-latest, Node 18.x, bun) (push) Failing after 15m1s
CI / Test (ubuntu-latest, Node 18.x, npm) (push) Failing after 15m1s
CI / Test (ubuntu-latest, Node 18.x, pnpm) (push) Failing after 15m1s
CI / Test (ubuntu-latest, Node 18.x, yarn) (push) Failing after 15m1s
CI / Test (ubuntu-latest, Node 20.x, bun) (push) Failing after 17m13s
CI / Test (ubuntu-latest, Node 20.x, npm) (push) Failing after 18m42s
CI / Test (ubuntu-latest, Node 20.x, pnpm) (push) Failing after 15m0s
CI / Test (ubuntu-latest, Node 20.x, yarn) (push) Failing after 49m44s
CI / Test (ubuntu-latest, Node 22.x, bun) (push) Failing after 51m55s
CI / Test (ubuntu-latest, Node 22.x, pnpm) (push) Failing after 21m57s
CI / Test (ubuntu-latest, Node 22.x, npm) (push) Failing after 37m39s
CI / Test (ubuntu-latest, Node 22.x, yarn) (push) Failing after 34m7s
CI / Validate Components (push) Failing after 37m15s
CI / Python Tests (push) Failing after 10m1s
CI / Security Scan (push) Failing after 10m1s
CI / Lint (push) Failing after 17m12s
CI / Coverage (push) Failing after 20m19s
CI / Test (macos-latest, Node 18.x, bun) (push) Has been cancelled
CI / Test (macos-latest, Node 18.x, npm) (push) Has been cancelled
CI / Test (macos-latest, Node 18.x, pnpm) (push) Has been cancelled
CI / Test (macos-latest, Node 18.x, yarn) (push) Has been cancelled
CI / Test (windows-latest, Node 18.x, npm) (push) Has been cancelled
CI / Test (windows-latest, Node 18.x, pnpm) (push) Has been cancelled
CI / Test (windows-latest, Node 18.x, yarn) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, bun) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, npm) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, pnpm) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, yarn) (push) Has been cancelled
CI / Test (windows-latest, Node 20.x, npm) (push) Has been cancelled
CI / Test (windows-latest, Node 20.x, pnpm) (push) Has been cancelled
CI / Test (windows-latest, Node 20.x, yarn) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, bun) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, npm) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, pnpm) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, yarn) (push) Has been cancelled
CI / Test (windows-latest, Node 22.x, npm) (push) Has been cancelled
CI / Test (windows-latest, Node 22.x, pnpm) (push) Has been cancelled
CI / Test (windows-latest, Node 22.x, yarn) (push) Has been cancelled
2.4 KiB
2.4 KiB
Comando Eval
Gestionar el flujo de trabajo de desarrollo orientado a evals.
Uso
/eval [define|check|report|list] [nombre-feature]
Definir Eval
/eval define nombre-feature
Crear una nueva definición de eval:
- Crear
.claude/evals/nombre-feature.mdcon la plantilla:
## EVAL: nombre-feature
Created: $(date)
### Capability Evals
- [ ] [Descripción de Capability 1]
- [ ] [Descripción de Capability 2]
### Regression Evals
- [ ] [El comportamiento existente 1 sigue funcionando]
- [ ] [El comportamiento existente 2 sigue funcionando]
### Success Criteria
- pass@3 > 90% para capability evals
- pass^3 = 100% para regression evals
- Pedir al usuario que complete los criterios específicos
Verificar Eval
/eval check nombre-feature
Ejecutar los evals para una feature:
- Leer la definición de eval desde
.claude/evals/nombre-feature.md - Para cada capability eval:
- Intentar verificar el criterio
- Registrar PASS/FAIL
- Guardar el intento en
.claude/evals/nombre-feature.log
- Para cada regression eval:
- Ejecutar las pruebas relevantes
- Comparar con la línea base
- Registrar PASS/FAIL
- Reportar el estado actual:
EVAL CHECK: nombre-feature
========================
Capability: X/Y pasando
Regression: X/Y pasando
Estado: EN PROGRESO / LISTO
Reporte de Eval
/eval report nombre-feature
Generar reporte exhaustivo de eval:
EVAL REPORT: nombre-feature
=========================
Generated: $(date)
CAPABILITY EVALS
----------------
[eval-1]: PASS (pass@1)
[eval-2]: PASS (pass@2) - requirió reintento
[eval-3]: FAIL - ver notas
REGRESSION EVALS
----------------
[test-1]: PASS
[test-2]: PASS
[test-3]: PASS
METRICS
-------
Capability pass@1: 67%
Capability pass@3: 100%
Regression pass^3: 100%
NOTES
-----
[Cualquier problema, caso límite u observación]
RECOMMENDATION
--------------
[SHIP / NEEDS WORK / BLOCKED]
Listar Evals
/eval list
Mostrar todas las definiciones de eval:
EVAL DEFINITIONS
================
feature-auth [3/5 pasando] EN PROGRESO
feature-search [5/5 pasando] LISTO
feature-export [0/4 pasando] NO INICIADO
Argumentos
$ARGUMENTS:
define <nombre>- Crear nueva definición de evalcheck <nombre>- Ejecutar y verificar evalsreport <nombre>- Generar reporte completolist- Mostrar todos los evalsclean- Eliminar logs de evals antiguos (mantiene las últimas 10 ejecuciones)