Saltar al contenido
TakoAPI
Volver a skills

skilldevelop

por raghuraam25

Browser & Automation
—Aún sin valoraciones
Tu valoración

Resumen

Captures learnings, errors, and corrections to enable continuous improvement.

Descripción

Qué hace esta skill

Logs errors, corrections, and feature requests to local markdown files during AI agent sessions. Entries use structured fields for priority, area, and status, and can be promoted to permanent project files like CLAUDE.md or AGENTS.md. Hook scripts enable automatic logging when commands fail or prompts are submitted.

Persistent structured logging lets agents avoid repeating the same mistakes across sessions, unlike in-context memory that resets each time.

Cuándo usarla

  • Logging a bash command failure mid-task for later review
  • Recording a correction when the agent used the wrong package manager
  • Capturing a feature request the agent cannot fulfill yet
  • Promoting a recurring best practice into the project's CLAUDE.md
  • Reviewing past errors before starting a database migration

Flujo de trabajo de ejemplo

ENTRADA

User says: 'Actually, this project uses pnpm, not npm'

AGENTE
  1. 1

    Detect correction trigger from user message

  2. 2

    Append entry to .learnings/LEARNINGS.md with category 'correction' and area 'config'

  3. 3

    Search existing entries for related package manager issues with grep

  4. 4

    Distill the correction into a concise rule and add it to CLAUDE.md under Build & Dependencies

SALIDA

Learning entry logged with a generated ID and status 'pending', correction promoted to CLAUDE.md

Instalación

clawhub install raghuraam25/skilldevelop

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

Enlaces