Cierra el ciclo de un informe de Caveman learn: revisa los principales sumideros de tokens y aplica correcciones para reducir costos (recortar configuración, descargar contexto recurrente a cavemem) con consentimiento por edición. Úsalo cuando el usuario ejecute "caveman learn", pida reducir el costo de tokens de su agente, quiera recortar un CLAUDE.md / AGENTS.md pesado, o descargar contexto que repite cada sesión a cavemem.
Caveman-learn es una habilidad para agentes de IA (compatible con Claude Code, Cursor, Codex y otros) que cierra el ciclo de optimización de costos de tokens iniciado por la herramienta "caveman learn". Tras generar un informe que identifica los principales sumideros de tokens —como configuraciones infladas o contextos repetidos—, esta habilidad permite aplicar correcciones de forma interactiva: recortar archivos pesados como CLAUDE.md o AGENTS.md, descargar bloques de contexto recurrente a la base de conocimiento de cavemem, y optimizar la configuración del agente. Cada edición requiere consentimiento explícito del usuario, garantizando control y seguridad. Es ideal para desarrolladores que buscan reducir costos operativos de sus agentes de IA sin perder funcionalidad, automatizando tareas manuales de depuración y mantenimiento de contexto.
npx skills add https://github.com/geovanejunior92-debug/claude-skills/tree/main/skills/caveman-learnInstalled? Explore more Programación y desarrollo skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Cierra el ciclo de un informe de Caveman learn: revisa los principales sumideros de tokens y aplica correcciones para reducir costos (recortar configuración, descargar contexto recurrente a cavemem) con consentimiento por edición. Úsalo cuando el usuario ejecute "caveman learn", pida reducir el costo de tokens de su agente, quiera recortar un CLAUDE.md / AGENTS.md pesado, o descargar contexto que repite cada sesión a cavemem.
This repo contains 3 individual skills — each has its own dedicated page.
Compress natural language memory files (CLAUDE.md / AGENTS.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
Monitors task execution for skill improvement opportunities. Use this skill during ANY multi-step task, agentic workflow, or substantive work session where the agent is using tools and producing deliverables. It captures patterns, user corrections, workflow insights, and methodology worth preserving as reusable skills. Also triggers during post-task feedback discussions and when the user explicitly mentions skill observations, improvements, the observation log, skill taxonomy, or asks the agent to watch for skill opportunities. Also known as "One Skill to Rule Them All" — trigger on this phrase too. IMPORTANT: this skill should be invoked at the start of every task-oriented session — if you are about to use tools to produce deliverables, invoke this skill first. For reliable activation, pair this description with a CLAUDE.md / AGENTS.md instruction or harness-level session-start hook (see Recommended Activation Setup) — description-level matching alone is not enforceable.
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.