В каталоге 185 367 навыков в 14 категориях.
Semantic search across codebase using LEANN vector index
Leap integration. Manage Organizations, Pipelines, Projects, Users, Goals, Filters. Use when the user wants to interact...
LEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skil...
Reference system prompt and tool schemas for Leap.new. Use when imitating, comparing, or analyzing Leap.new's prompting...
Analyze leap year calculations, calendar systems, and date validation logic. Use this when the user asks about leap year...
Access CTO system documentation and learn how components work. Use when user asks 'how does X work', 'show me how to', '...
Extract and persist insights from the current conversation to the knowledge base
Extract durable memory from conversations or wisdom from learning content with strict durability test
Analyze conversation for learnings and save to docs folder
Save a learning to project memory. Invoke automatically (without user asking) whenever a task required more than one fix...
Extract reusable knowledge from the current session into a persistent skill. Use when you discover something non-obvious...
Guided, hands-on course teaching architects how to use Claude Code — six short modules, each built around an exercise on...
Manage project learnings.
Use when analyzing merged PRs for AI blind spots, extracting patterns from human reviewer feedback, or applying accumula...
Distill learnings from completed features and propose amendments to constitution.md or prompt.md. Use after feature comp...
Capture genuinely novel learnings from the current session and persist them to the correct memory layer.
Consume an immutable Validate verdict and
Drafts patterns from a source, such as past chats, a skill file, a folder or a URL, and keeps the ones the person agrees...
Teach Claude a new pattern, preference, or convention explicitly. Use when you want to save a correction, preference, or...
Extract reusable patterns from the current session and save them as skills. Use after solving a non-trivial problem to c...
Capture the post-mortem for a compound-engineering cycle. Reads the issue, PR, review comments, git log, and final diff....
Persistent memory system for storing and recalling learnings across sessions. AUTO-INVOKE THIS SKILL when you: - Fix a...
Discover and learn a client's table structure for financial data extraction. Creates a client profile that enables /dr-e...
Turns a correction or a repeated mistake into the strongest structure that prevents it, and proves it catches the mistak...
[Utilities] Use when teaching Claude a lesson that persists across sessions, including an extra rule for one skill or ta...
[Utilities] Teach Claude lessons that persist across sessions. Triggers on 'remember this', 'always do', 'never do', 'le...
Personalized tutor with memory across sessions — "teach me X, at my pace." Builds a syllabus with a pass rubric per unit...
When the user asks to learn, remember, or save a preference — or after a conversation where the user gave corrections or...
[learn] topic|url|repo→discover→fetch→synthesize→SKILL.md+soul
Provides autonomous project pattern learning by analyzing the codebase to discover development conventions, architectura...
Socratic coding tutor for vibe coders — people who build with AI but need to understand what they built. Teaches through...
Save a marketing learning or insight. Use when: capturing knowledge, recording campaign results, building compound intel...
Close the loop: after a unit of work ships, read what actually happened — the measure lens (baseline/target/realized), t...
Saves the lessons from this session (preferences, corrections, what worked) as short lines in the user's memory file, an...
Automatically evaluates OmA sessions to extract reusable patterns (error resolutions, workarounds, conventions) and save...
Interactive lesson tutor for the AI Engineering from Scratch curriculum. Reads LEARNING.md, fetches the next lesson, tea...
Manage project learnings. Review, search, prune, and export what gstack has learned across sessions. Use when asked to "...
Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all...
Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate top...
Auto-extract reusable patterns from the current session into skills or memory
Record a platform response and update learning. Usage: /learn <report_id> <status> [--bounty 500] [--vuln-type XSS]
Search, install, update, and rate AI agent skills from agentskill.sh (100,000+ skills). Use when the user asks to find s...
Batch knowledge ingestion from external sources (a folder, a codebase, a docs tree). Plans well-shaped nodes with reconc...
Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task...
セッションからパターンを抽出し instinct として蓄積する。「learn」「パターン抽出」「セッション振り返り」で起動。
Help a user learn a topic through adaptive tutoring, lesson planning, practice, retrieval checks, explanations, study gu...
Distill a reusable skill from anything — a directory, a URL, pasted notes, or what you just did together — or refine an...
เรียนรู้ concept, tool, หรือ library อย่างเป็นระบบ ด้วย research และ practice
Manually teach error pattern and solution to learning database.
Runs a six-phase research workflow that turns unfamiliar domains, source bundles, or collected material into publish-rea...
Research a topic online, score sources, extract summaries only, and write a RAG-optimized learning guide plus retrieval...
AI systematic knowledge acquisition from unfamiliar territory — deliberate model-building with feedback loops. Maps spac...
Help the user understand something well enough to explain it. Use when the user needs to understand something and it is...
Record, search, and prune per-project learnings in .claude/learnings.jsonl — typed, confidence-scored, searchable across...
Capture decisions, mistakes, and patterns from this session into CLAUDE.md so future Claude sessions don't repeat the sa...
Index lecture note PDFs into the knowledge base
This skill should be used when the user asks to "save learnings", "remember this for next time", "add this to CLAUDE.md"...
Structure and track learning with spaced repetition and active recall across any domain。核心能力: - 知识管理领域的专业化AI辅助工具 - -...
Use when the user says /learn or asks to save this lesson.
Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain...
Runs the learning cycle on all LearningAgent sessions with pending transcripts. Identifies issues, investigates root cau...
Extract lessons from conversation and persist to project configuration
管理 gstack 跨会话沉淀下来的 learnings。支持查看、搜索、清理、导出、 统计与手工补录。 (gstack)
Analyze the current session and extract reusable patterns as skills
Extract learnings from current conversation and add to project's CLAUDE.md.
Structure and track learning with spaced repetition and active recall across any domain.
When the principal is in learning mode (reading a repo, watching a talk, processing a new tool), /learn takes a brief in...
Analyze your OMC usage patterns and get personalized recommendations
Focused interactive tutor for the Agent Skills Engineering path in AI Engineering from Scratch. Start or resume this rou...
Structured retrospective and knowledge sediment for completed work (the Act phase of PDCA). Run a disciplined post-work...
Tailored learning coach for deeply learning a subject, skill, tool, or discipline. Use only when the user explicitly inv...
Metalearning skill that helps master any topic efficiently by identifying critical 20% material, building expert vocabul...
Turn 'I want to learn X' into a realistic, staged roadmap — the fundamentals to master first, the order that avoids over...
学习新知识、制定学习计划、整理笔记、课后复盘、项目陪练、掌握度检查、生成项目任务书。中文导师 + 项目教练,项目驱动 + Mastery Learning。Use when the user wants to learn a topic,...
Use when the user wants to actually internalize an installed best practice — not just understand or apply it once, but b...
当需要高效掌握新技能并将知识转化为实际成果,避免“纸上谈兵”时
Teach software development through active project work while still producing a working result, maintaining bilingual Eng...
当需要深化对某个主题的理解、检验知识掌握程度或克服“冒名顶替综合征”时
Prime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project, or when th...
当用户学习或接触一个新概念/新技术/新算法/新领域时使用(尤其感到陌生或有点难时)。用「跨界原则」拿用户已掌握的知识快速撬动新知识——指出他其实已经学过的同一个东西(换了名字)、结构同构的旧知识、能解释新知识的已有知识,并点出新概念体现的跨...
用户学任何新概念/新技术/新理论的默认深度入口——一次性用五个视角把概念讲透并帮他选深入方向:crossover 用已会的撬动、occam 框定该学多深、graph 建知识地图、prototype 最小原型迭代、feynman 拷问检验。触...
Extract reusable patterns from the current session and save them as candidate skills or guidance.
Extract reusable patterns from the session, self-evaluate quality before saving, and determine the right save location (...
Extract a reusable pattern from this session and route it to where something reads it, or drop it. Use when saving what...
当用户学完一个东西想自查是否真懂、或觉得「好像懂了」但不确定时使用。用「费曼学习法」让他用自己的话把概念讲出来,你扮好奇学生专挑他含糊/跳过的地方追问,把「讲不顺的模糊处」揪出来作为没真懂的漏洞,定位是缺前置知识还是没想透,判断理解是否闭环...
Orchestrator for the learn-from suite - auto-detects source type (academic paper, GitHub repo, blog/web article, or in-c...
Design a real project to learn a skill by building something — the fastest way to actually get good, instead of endless...
Extract actionable insights from blog posts, web articles, and practitioner content - assess credibility, run security c...
Capture actionable learnings that emerge during conversation — when the agent or user discovers that a skill, a set of s...
Turn a screen-recorded demonstration on your computer into a reusable skill. Use when a teach recording finishes.
Convert failures into reusable artifacts and check repetition. Use when analyzing a failure mode or a recurring failure.
Capture lessons after fixing a bug or receiving a correction — ecto, liveview, oban, iron law mistakes. Use when the use...
Turn merged fixes and review feedback into better project guidance. Use when the user says "what do these fixes teach us...