자연어 메모리 파일(CLAUDE.md, AGENTS.md, 할 일, 설정)을 원시인 포맷으로 압축하여 입력 토큰을 절약합니다. 모든 기술적 내용, 코드, URL 및 구조를 보존하며, 압축된 버전이 원본 파일을 덮어씁니다. 사람이 읽을 수 있는 백업은 FILE.original.md로 저장됩니다. 실행 명령어: /caveman-compress FILEPATH 또는 "compress memory file"
이 스킬은 AI 어시스턴트(Claude Code, Cursor, Codex 등)가 사용하는 메모리 파일(예: CLAUDE.md, AGENTS.md)을 '원시인 포맷'으로 압축하여 입력 토큰 사용량을 대폭 줄입니다. 기술적 정확성을 유지하면서 불필요한 자연어 표현을 생략하고, 코드, URL, 파일 경로, 핵심 명령어 등 중요한 정보는 그대로 보존합니다. 압축된 내용은 원본 파일을 덮어쓰며, 원본 텍스트는 FILE.original.md로 자동 백업됩니다. 이는 대규모 문맥을 처리해야 하는 장기 실행 세션에서 특히 유용하며, /caveman-compress FILEPATH 명령어나 'compress memory file' 자연어 프롬프트로 트리거할 수 있습니다.
npx skills add https://github.com/geovanejunior92-debug/claude-skills/tree/main/skills/caveman-compressInstalled? Explore more 라이팅 & 에디팅 skills: steipete/notion, langchain-ai/langchain, bytedance/podcast-generation · View all 6 →
자연어 메모리 파일(CLAUDE.md / AGENTS.md, 할 일, 설정)을 원시인 포맷으로 압축하여 입력 토큰을 절약합니다. 모든 기술적 내용, 코드, URL 및 구조를 보존합니다. 압축된 버전이 원본 파일을 덮어씁니다. 사람이 읽을 수 있는 백업은 FILE.original.md로 저장됩니다.
실행 명령어: /caveman-compress FILEPATH 또는 "compress memory file"
This repo contains 3 individual skills — each has its own dedicated page.
Close the loop on a Caveman learn report — review the ranked token sinks and apply cost-lowering fixes (trim config, offload recurring context to cavemem) with per-edit consent. Use when the user runs "caveman learn", asks to lower their agent's token cost, wants to trim a heavy CLAUDE.md / AGENTS.md, or wants to offload context they re-paste every session into cavemem.
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.
Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.
The agent engineering platform.
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
Analyze and optimize tweets for maximum reach using Twitter's open-source algorithm insights. Rewrite and edit user tweets to improve engagement and visibility based on how the recommendation system ranks content.
Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors