caveman-learn 是做什麼的？
關閉 Caveman learn 報告迴圈 — 審查排名後的 token 消耗源，並在每次編輯前取得同意，套用降低成本修正（如修剪設定、將重複上下文卸載至 cavemem）。當使用者執行「caveman learn」、要求降低其代理的 token 成本、想要修剪過大的 CLAUDE.md / AGENTS.md，或想將每次工作階段都重複貼上的上下文卸載至 cavemem 時使用。
關閉 Caveman learn 報告迴圈 — 審查排名後的 token 消耗源，並在每次編輯前取得同意，套用降低成本修正（如修剪設定、將重複上下文卸載至 cavemem）。當使用者執行「caveman learn」、要求降低其代理的 token 成本、想要修剪過大的 CLAUDE.md / AGENTS.md，或想將每次工作階段都重複貼上的上下文卸載至 cavemem 時使用。
此技能用於完成 Caveman learn 報告的後續處理，幫助開發者與 AI 代理使用者有效降低 token 成本。它會審查並排名 token 消耗源（token sinks），然後在每次編輯前徵得使用者同意，自動套用降低成本修正。修正方式包括：修剪過大的設定檔（如 CLAUDE.md / AGENTS.md），或將每輪對話中都重複出現的上下文卸載到 cavemem 儲存庫。本技能特別適合在執行「caveman learn」後、使用者抱怨 token 費用過高、或發現代理總是重複讀取相同的上下文時呼叫。支援所有能執行 Caveman 工具的 AI 代理平台（如 Claude Code、Cursor、Codex），能讓工作階段更輕量、成本更低。
npx skills add https://github.com/geovanejunior92-debug/claude-skills/tree/main/skills/caveman-learnInstalled? Explore more 程式設計與開發 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
關閉 Caveman learn 報告迴圈 — 審查排名後的 token 消耗源，並在每次編輯前取得同意，套用降低成本修正（如修剪設定、將重複上下文卸載至 cavemem）。當使用者執行「caveman learn」、要求降低其代理的 token 成本、想要修剪過大的 CLAUDE.md / AGENTS.md，或想將每次工作階段都重複貼上的上下文卸載至 cavemem 時使用。
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.