Saltar al contenido
TakoAPI
Volver a skills

adversarial-coach

por killerapp

Personal Development
1.4kDescargas según clawskills.sh
1Estrellas
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Adversarial implementation review based on Block's g3.

Descripción

Qué hace esta skill

A dialectical review loop where an adversarial coach independently validates implementation completeness against a requirements file. Based on Block's g3 research, it separates the implementing agent from the reviewer to catch gaps the implementer would rationalize away. Returns either IMPLEMENTATION_APPROVED or a concrete list of missing items.

Unlike self-review, the coach discards prior context and evaluates code against requirements as written, catching gaps the implementing agent would overlook or excuse.

Cuándo usarla

  • Catching missing auth endpoints before code review
  • Verifying a spec is fully implemented after a coding session
  • Looping on fixes until all requirements are met
  • Reviewing JWT/bcrypt security gaps in auth implementations
  • Validating edge case test coverage against a written spec

Flujo de trabajo de ejemplo

ENTRADA

User asks: /coach SPEC.md

AGENTE
  1. 1

    Locate and parse SPEC.md to extract all requirements

  2. 2

    Review the current implementation independently, ignoring prior conversation context

  3. 3

    Check each requirement for implementation status, compilation, tests, and security gaps

  4. 4

    Return compliance report with IMMEDIATE ACTIONS NEEDED listing specific files and fixes

  5. 5

    After user applies fixes, re-run review until IMPLEMENTATION_APPROVED is issued

SALIDA

IMPLEMENTATION_APPROVED with each requirement verified and test count confirmed

Instalación

clawhub install killerapp/adversarial-coach

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

Enlaces