Saltar al contenido
TakoAPI
Volver a skills

code-cache

por ryx2

Search & Research
487Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Semantic code caching for AI agents.

Descripción

Qué hace esta skill

Stores code generated during agent executions and retrieves semantically similar code for future tasks. Uses the Raysurfer API to search, upload, and vote on cached snippets. Cuts redundant generation by reusing validated solutions from prior runs.

Retrieving pre-validated cached code avoids the latency and token cost of having an LLM regenerate the same patterns on every run.

Cuándo usarla

  • Reusing a prior data pipeline script without regenerating it
  • Retrieving cached chart-building code for a recurring report
  • Searching past executions before writing new API fetch code
  • Uploading a successful script to the cache after an agent run
  • Downvoting a broken cached snippet to improve future retrieval quality

Flujo de trabajo de ejemplo

ENTRADA

User asks: 'Fetch GitHub trending repos'

AGENTE
  1. 1

    Search cache with /code-cache search "Fetch GitHub trending repos" --show-code

  2. 2

    Review the top match score and inspect the returned snippet

  3. 3

    Retrieve execution-ready files with /code-cache files "Fetch GitHub trending repos"

  4. 4

    Run the retrieved code in the agent sandbox

  5. 5

    Upload the result with /code-cache upload "Fetch GitHub trending repos" --files fetch.py

SALIDA

GitHub trending repos fetched using cached code, with the execution stored and auto-voted for future reuse

Requisitos

  • RAYSURFER_API_KEY environment variable
  • Raysurfer account (sign up at raysurfer.com to access the API key dashboard)

Instalación

clawhub install ryx2/code-cache

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

Enlaces