Loading...
Loading...
Found 91 Skills
Stretches OpenAI Codex (CLI, IDE extension, cloud) 5-hour and weekly usage limits or credits while keeping output quality. Use when the user hits or nears a Codex limit, sees fast usage in /status, has a long session, asks to audit or tune config.toml (model, reasoning effort, verbosity, compaction, tool output limits, MCP servers, profiles) or AGENTS.md, or asks how to use Codex more efficiently. Triggers include "usage limit", "rate limit", "5-hour limit", "weekly limit", "credits", "token saving", "reduce cost", "使用量", "トークン節約", "節約", "5時間制限", "週間制限", "上限", "クレジット".
Use when context is growing large (50k+ tokens), performance is degrading, instructions are being ignored mid-conversation, or planning multi-agent workflows. Triggers on "lost context", forgotten instructions, or sessions exceeding 30 minutes.
Configure RTK (command output), Caveman (prose), and stacked compression modes. Manage language packs, custom rules, and test prompt compression reducing tokens by 60–90%.
Stretches Cursor's monthly included usage (Cursor models pool and other models pool) and on-demand spend while keeping output quality. Use when the user is running out of Cursor usage, sees high on-demand charges, asks when to use Auto, Composer, Max Mode or a frontier model, or asks to audit .cursor/rules, .cursorrules, AGENTS.md, .cursorignore or MCP servers for efficiency. Triggers include "usage limit", "included usage", "on-demand", "Max Mode", "token saving", "reduce cost", "context limit", "使用量", "トークン節約", "節約", "月間制限", "上限", "従量課金".
한국어 마크다운 볼트(옵시디언 세컨드브레인) 전용 감사·최적화 스킬. 9개 프레임워크(F1 Anthropic CLAUDE.md, F2 Karpathy Wiki, F3 Caveman 압축, F4 Chroma Context Rot, F5 Anthropic Memory, F6 Progressive Disclosure, G7 위생, F8 Reflection, F9 아키텍처·탐색성)를 모든 .md 파일에 적용한다. 영어 원본 os-optimizer와 달리 (1) 사용자에게 보이는 모든 출력(안내·질문·발견 항목·리포트·요약)을 한국어로 내고, (2) 한국어 텍스트에 맞게 토큰 추정 공식·em대시 치환·파일 크기 예산·문체 위생 규칙을 조정한다. 발견된 모든 문제는 구체적 수정안과 함께 나오며(경고만 남기지 않음), 사용자가 항목별로 지금 적용 또는 계획 저장을 고른다. TaskCreate로 진행 상황을 실시간 노출한다. 트리거: os optimizer 한국어, 볼트 감사, 볼트 최적화, 세컨드브레인 감사, 세컨드브레인 정리, 볼트 정리, 프레임워크 감사, 탐색성 점검, 아키텍처 감사, reorg vault, 볼트 리팩터. 볼트 루트에서 실행한다.
Programmatic web search and scrape with context isolation. Use for any research task where you need to search the web, filter results, and extract specific information — without flooding your context window with raw HTML and boilerplate. This is the single biggest token-saver in the crw skill set. Triggered by "search for", "look up", "find", "research", "what's the latest on", or any query that requires current web information. Also use when asked to "search and filter", "find the important parts", or any task where you suspect the raw output will be large (multi-page scrapes, news aggregation, competitive research).
Stretches Claude Code's 5-hour and weekly plan limits (or API spend) while keeping output quality. Use when the user hits or nears a usage limit, sees high usage in /usage, has a long or slow session, asks to audit or slim down CLAUDE.md, rules, MCP servers, skills, subagents, hooks, model or effort settings, or asks how to use Claude Code more efficiently. Triggers include "usage limit", "rate limit", "session limit", "weekly limit", "token saving", "reduce cost", "context is full", "使用量", "トークン節約", "節約", "5時間制限", "週間制限", "上限に達した", "コンテキストがいっぱい".