Saltar al contenido
TakoAPI
Volver a skills

self-review

por leic8959-sudo

Communication
402Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Automatically review agent output quality before sending to user.

Descripción

Qué hace esta skill

Runs a rule-based quality check on agent output before it reaches the user. Evaluates clarity, conciseness, actionability, and structure. Returns exit code 0 for approved output or 1 when improvement is needed.

Catches output quality issues without LLM API calls, keeping review costs at zero.

Cuándo usarla

  • Catching verbose or unclear agent responses before delivery
  • Filtering low-quality output in automated agent pipelines
  • Running post-generation checks without extra API costs
  • Enforcing response structure standards across agent workflows
  • Validating output during CI/CD for agent-based tools

Flujo de trabajo de ejemplo

ENTRADA

User asks: Check this agent response before sending it

AGENTE
  1. 1

    Pipe the generated response text to self-review/index.js via stdin

  2. 2

    Rule-based engine evaluates clarity, conciseness, actionability, and structure

  3. 3

    Returns exit code 0 if output passes all checks

  4. 4

    Returns exit code 1 with feedback if output needs improvement

SALIDA

Exit code 0 with approved response, or exit code 1 indicating which checks failed

Instalación

clawhub install leic8959-sudo/self-review

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces