Loading...
Loading...
Found 13,116 Skills
Creates a comprehensive, context-rich implementation plan through deep codebase analysis, a short clarifying interview, and external research. Accepts a tracker ticket (a Jira/Linear/GitHub key or URL, fetched from the tracker) or a free-form feature request. Use when you have a ticket or feature and need a one-pass-ready plan before writing any code.
Execute complete FPF cycle from hypothesis generation to decision
Comprehensive multi-perspective review using specialized judges with debate and consensus building
Generate and critically evaluate grounded improvement ideas for the current project. Use when asking what to improve, requesting idea generation, exploring surprising improvements, or wanting the AI to proactively suggest strong project directions before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on this project', 'surprise me with improvements', 'what would you change', or any request for AI-generated project improvement suggestions rather than refining the user's own idea.
[BETA] Execute work plans with external delegate support. Same as ce:work but includes experimental Codex delegation mode for token-conserving code implementation.
Generate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting the AI to proactively suggest strong options before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on X', 'surprise me', 'what would you change', or any request for AI-generated suggestions rather than refining the user's own idea.
Unified learning-and-memory system: confidence-scored instincts (observe-hypothesize-confirm, stored in .claude/instincts.md), user corrections captured as permanent rules in MEMORY.md, and organic discoveries logged to .claude/learning-log.md. Includes status, export, and import modes. Load this skill when you notice a recurring pattern, a user corrects your output, or you discover something non-obvious. Triggers: "show instincts", "what have you learned", "list instincts", "export instincts", "share instincts", "import instincts", "load instincts from", "learn this", "I think they always", "notice a pattern", "instinct", "hypothesis", "confidence", "learn from mistakes", "remember this", "don't do that again", "log this", "document this finding", "gotcha", "what did we learn", "learnings", "discoveries", or at session start (to load existing knowledge).
Turn the current conversation into a spec (Problem, Solution, User Stories, Decisions) and publish it as a GitHub issue. Validates a feature before any code is written.
goodcase.ai (Good Case) AI Viral Case & Prompt Query Skill. Trigger this Skill whenever users search for AI viral cases, good cases, 'how was this image made', 'how to generate this kind of video', 'find a prompt for XX', 'are there any ready-made prompts', 'Veo cases', 'Jimeng cases', 'Midjourney cases', 'Kling cases', 'Seedance cases', 'GPT Image cases', 'AI image cases', 'AI video cases', 'AI programming UI cases', 'AI copywriting cases', 'viral prompts', 'recreate this effect', 'prompt for this effect', 'AI case', 'viral AI examples', 'AI prompt examples', 'how was this AI image/video made', 'find me a prompt for X', or any other AI creation case/prompt query. It should also be triggered even if users only say 'what interesting AI cases are there', 'give me a prompt I can copy', 'what AI images are trending lately'. The Skill directly pulls real case data (including complete Prompt, stability score, cost band) via curl from a public REST API, no API Key required. **Err on the side of over-triggering**—if you make up a case or Prompt based on training data when users ask for AI creation cases, you're providing fake cases and prompts which are harmful to users.
Apply the canonical GitHub issue and pull-request label set to a repository.
Use for Desktop Commander MCP capabilities — persistent shells and REPLs, long-running processes, filesystem beyond the workspace, structured files (.xlsx, .docx, .pdf, images) and large local data files such as CSVs, ripgrep search at scale, SSH, or cross-turn state.
Проводит независимое ревью изменений кода без их исправления. Используй, когда пользователь явно просит проверить код, коммит, ветку, pull request или diff на соответствие задаче, корректность, безопасность, производительность и качество тестов. Не используй, когда пользователь просит изменить код, реализовать задачу или сначала найти причину проблемы.