Finaliza o ciclo de um relatório Caveman Learn — revise os maiores consumidores de tokens e aplique correções que reduzem custos (otimizar configuração, transferir contexto recorrente para cavemem) com consentimento por edição.
Esta skill automatiza a conclusão do ciclo de um relatório 'caveman learn', permitindo que o usuário revise as maiores fontes de consumo de tokens e aplique correções para reduzir custos. Ela é útil quando o usuário executa o comando 'caveman learn', solicita redução do custo de tokens de seu agente, deseja otimizar arquivos pesados como CLAUDE.md/AGENTS.md ou transferir contexto que ele repassa a cada sessão para o cavemem. A skill funciona analisando o relatório gerado, identificando os principais 'token sinks', e aplicando correções como trim config e offload de contexto recorrente para cavemem, sempre solicitando consentimento para cada edição.
npx skills add https://github.com/geovanejunior92-debug/claude-skills/tree/main/skills/caveman-learnInstalled? Explore more Programação e Desenvolvimento skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Finaliza o ciclo de um relatório Caveman Learn — revise os maiores consumidores de tokens e aplique correções que reduzem custos (otimizar configuração, transferir contexto recorrente para cavemem) com consentimento por edição. Use quando o usuário executar "caveman learn", solicitar redução do custo de tokens de seu agente, desejar otimizar um CLAUDE.md / AGENTS.md pesado, ou transferir contexto que ele repassa a cada sessão para 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.