Loading...
Loading...
Found 9,575 Skills
Extract experience from the current conversation and automatically generate reusable Claude Code Skills. Use when user wants to extract a skill, summarize into a skill, solidify experience, generate a skill, create a skill from context, save as a skill, or turn experience into a skill.
Repository housekeeping workflows for AGENTS/CLAUDE architecture, progressive disclosure, and migration of legacy monolithic instruction files.
Guide for creating Claude Code skills to document @rytass packages (建立套件文件 skill 指南). Use when creating new package documentation skills, writing SKILL.md files, or designing skill structure.
Create a new plugin for Claude Code marketplace with validation, ADR, and release automation. TRIGGERS - create plugin, new plugin, scaffold plugin, add plugin, plugin-dev create.
Agent definition conventions. Use when creating or modifying agents at any level (~/.claude/agents/, .claude/agents/, or project-local). Validate frontmatter, update README.md index. NOT for creating skills, MCP servers, or modifying CLAUDE.md.
Use this skill for multi-model AI code review. Trigger whenever the user asks to review code changes, audit a diff, check code quality, review a PR, review commits, or review uncommitted changes before pushing or merging. Also trigger when they say 'code review', 'review my changes', 'check this before I merge', or want multiple perspectives on code. Runs Codex and Claude reviews in parallel, then synthesizes a unified report. Do NOT use for reviewing documentation, markdown, or non-code files, or for trivial single-line changes.
Create 600x600 Instagram-style card news series automatically with optional background images. User provides topic, colors, and optional images - Claude generates content and creates multiple cards with proper text wrapping.
Exposes Claude's reasoning chain as an auditable, decomposable artifact. Quick mode (default) gives assumption inventory + weakest-link in 2 stages. Full mode (--full) adds decision branching, confidence decomposition, and falsification conditions. Triggers on "왜 그렇게 생각해", "reasoning", "근거", "show your work", "어떻게 그 결론이", "trace", "판단 근거", "why do you think that".
Create Skills, write Skills, Skill templates. Help create and optimize Claude Code Skills in accordance with Testany's specifications.
Adapts a Claude global skill into project-specific development guidelines in .trellis/spec/. Creates guideline sections, code example templates with .template suffix, and updates spec indexes. Use when integrating an external Claude skill, adding a new skill's patterns to project conventions, or incorporating third-party skill best practices into .trellis/spec/ documentation.
Reflect on the current session and refine skills or CLAUDE.md based on patterns observed. Use when the user says "refine", "what did we learn", or at the end of a session to make skills better through use.
Use after analyze-and-document has generated CLAUDE.md for an AI Studio project. Installs project-level Claude Code configuration — rules, skills, settings, and optionally agents, hooks, and MCP servers — into the .claude/ directory so that all future sessions have the right guardrails and workflows.