Loading...
Loading...
Found 4,122 Skills
This skill is used when users want to review an existing code segment with an Agent — examining code rationality and identifying refactoring opportunities. It is language-neutral and focuses on design-level judgments (rather than correctness/mechanical checks). By default, it provides conversational conclusions and does not modify files proactively; hierarchical reports can be generated for archiving or large-scale code inspections, and findings can be reviewed item by item if there are multiple ones. Trigger: Users say "review / refactor / check if this code is reasonable / review with me / is there any problem with this design"; after writing a batch of code continuously, users or Agents can actively ask if inspection is needed. Not applicable: Executing single-point modifications with clear instructions from users (e.g., "change data1 to user_data"), adding new features, fixing bugs, performance tuning (profile/benchmark special projects), security audits, deterministic mechanical checks like lint, rewriting, or step-by-step inquiries (explaining code).
Create or update a skill in this repository the right way — canonical home in .agents/skills, internal-vs-public marking, symlink mirroring into .claude/skills, and public docs registration for product skills. Use whenever adding a new skill, converting a workflow into a skill, or when .claude/skills and .agents/skills look out of sync.
Solve an interactive hidden-rule ARC-AGI-3 game from its game ID. Contains the complete playing doctrine (predict before every action, graded claims, one-page notes, optional executable-rules search) plus the `arc` harness the agent drives. Use whenever asked to solve, play, or continue an ARC-AGI-3 game.
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
UI/UX design patterns and best practices. Pattern library + heuristic checks for shipping clean, usable interfaces.
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).
Use when an agent is asked "what did I (or my team) work on yesterday / this week / today" across provider data in a relayfile mount (Linear, GitHub, Notion, Slack, Confluence, Jira, etc.). Tells the agent to consult the pre-computed `digests/yesterday.md` (and sibling digest files) at the workspace root BEFORE doing manual exploration with `ls`/`grep`/`find`. The digest is deterministic, exhaustive over the window, and costs one file read instead of dozens of provider queries.
Search for Agent Skills in SkillsMP (an index of 1.6M+ public SKILL.md files, covering Claude Code / Codex / ChatGPT), filter by keywords, categories, occupations, and languages, and specifically discover those underrated Skills that are "well-written but unknown". Use this when users say phrases like "find a skill", "is there an existing skill?", "search for a skill", "skillsmp", "skills market", "agent skill search", "find a skill", "search skills", "discover skills". It is also used to identify existing Skills in a certain field and avoid reinventing the wheel.
Use when renaming a spec plan and updating all references. Triggers on: "rename plan", "change plan name", "plan name is wrong", "update plan name", "fix plan name", "spec rename". Proactively suggest when a plan name is a typo or no longer reflects scope.
Baidu Web Search skill for real-time Chinese web information retrieval. Breaks through static knowledge base limitations to get the latest news and information. Use when user needs to search the Chinese web for current information.
Create New Skill - scaffolds a skill definition following Claude Code conventions and this repository's patterns. Use when adding a new skill.
The always-on protocol for the loam skill namespace. Use at session start and whenever a loam task appears. Routes goals and other loam work, explains the memory model (memory = umbrella; wiki, guidance, and checkpoints are substrates), and lists cross-cutting rules. This is a routing/meta skill — delegate to a specific loam skill rather than performing work itself.