Browse 182,820 skills across 14 categories.
Invoke when an implementation attempt produces a failure signal (test failure, compile error, wrong output, crash, perf...
Customize your own agent — add capabilities, install packages, add MCP servers, edit code or CLAUDE.md. Use when the use...
Auto-deploy and migrate to ensure 100% permanence and independence
Explain bounded local trace diagnosis reports and suggest explicit next commands.
Use descriptive names for functions, variables, and classes that explain their purpose Use when documenting code and API...
Use this skill when writing, reviewing, or refactoring code to ensure it is self-documenting. Apply these checklists to...
Apply self-documenting code practices through good programming style and evaluate class design for abstraction quality....
Protects the individual practitioner's own judgment and self-efficacy when working with an AI thinking partner: a Think-...
Design a mastery experience sequence that systematically builds student confidence in a skill they avoid. Use when stude...
Framework for improving Claude configuration (skills, agents, commands). Use when analyzing work patterns, proposing new...
Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work ses...
Self-improvement skill for autonomous intelligence enhancement, skill installation, and capability optimization
The single config quality skill. Two modes: (1) Default — review/wire pending self-improvement proposals. (2) Audit — an...
Improve an existing skill or repository through isolated proposals, reproducible evaluation and evidence-based acceptanc...
Use when the user asks Codex to set or run a goal for iterative self-improvement, skill improvement, prompt optimization...
Improve reusable agent workflows with reflective experiments, value checks, and local pattern memory.
Darwin Gödel Machine patterns for self-improving AI agents with open-ended
Analyze the codebase to find hard-coded thresholds, defaults, and timing constants, then convert them into self-evolving...
Use when generating a single installable agent that should keep learning, track sources, refresh research, propose repai...
Create self-explanation prompts that deepen understanding of worked examples, texts, or diagrams. Use when students read...
Apply when executing the self-extension workflow. Six steps from a mistake to a merged rule, with CI gates and CODEOWNER...
Create self-extracting Bash scripts that embed any payload (archives, executables, configs) using base64 encoding. Use w...
구현 결과를 plan 기준으로 반복 검토하여 품질을 끌어올리는 review-fix-verify-commit 루프. material finding 소진까지 반복한다. "self-feedback loop 돌려", "피드...
Address exposure bias in video generation by training on self-generated sequences, achieving 17 FPS real-time performanc...
Use this skill when ready to compute the final self-assessed grade for submission. Triggers include: "self grade", "fina...
Continuous learning framework — learn from work, organize knowledge, build feedback loops. Use when: recording lessons,...
Autonomous diagnose-research-fix-verify loop — up to 5 attempts before human escalation. Use when: test failing, error,...
Autonomous error recovery — detect failures, diagnose root cause, apply fixes, and resume without stopping
Auto-recover OpenClaw when health goes offline, gateway token mismatch (1008) appears, Telegram stops replying, or brows...
Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY...
Automatically diagnose and fix broken workflows, failing scripts, errors, and bugs without giving up. Trigger when a scr...
Self-healing codebase system. Monitors runtime errors, test failures, and build breaks. Automatically diagnoses root cau...
CI-only self-healing workflow using gh-aw (GitHub Agentic Workflows) for active runtime recovery on pull requests and sc...
Load when the person wants to run or own apps on their own machine, replace a subscription (Netflix, Google Photos, Drop...
Run a single test file under both native and self-hosted cx and compare outputs. Use when diagnosing a self-host-only re...
Use when asked to make a project self-hostable, package an app for Docker, write a docker-compose setup, document self-h...
Use for local LLM fallback, failover, and Ollama health.
Self-hosted AI — run your own LLM inference, image generation, speech-to-text, and embeddings. No cloud APIs, no SaaS su...
Chat with a companion that knows your notes folder (a journal, an Obsidian vault, any .md or .txt files) and every earli...
GitHub Actionsセルフホストランナーの設計、セットアップ、セキュリティ管理を行うスキル。 インストールから運用、トラブルシューティングまでの完全なライフサイクル管理を提供する。 Anchors: • GitHub Action...
Use when an "enable observability" card targets self_hosted - a minimal Grafana LGTM stack (Loki, Grafana, Tempo, Mimir...
Captures learnings, errors, and corrections to enable continuous improvement. Activates when a command fails, the user c...
Automatically improve and fix bugs in the oh-my-gemini project itself
Capture durable user feedback into the governing skill/doc, or propose creating a new skill when no suitable one exists,...
Crystallize a wasteful thinking/behavioral loop into the cheapest durable artifact so it never recurs — routes a frictio...
Bootstrap and operate a self-improving agent workspace. Scaffolds .learnings/ and memory/ directories, captures errors a...
Review the current or user-selected agent session(s) for evidence-backed improvements to documentation, skills, code, co...
Transforms simple user requests into enriched descriptions with traceable findings. Use when interpreting vague user int...
Autonomous evolutionary code improvement engine with tournament selection
Extract lessons from the current session and route them to the appropriate knowledge layer (project AGENTS.md, auto memo...
Write self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for...
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch,...
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails...
Enables agent self-reflection and learning from mistakes through systematic skill updates. Prioritizes updating existing...
Capture user feedback and corrections to enhance repository documentation and skills. Transforms conversational feedback...
Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corre...
Continuously improve AI workflows and capabilities. Use when reflecting on process, identifying friction, or after compl...
CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and qualit...
Role assignment for Claude Agent
轻量自我改进记录技能。用于把错误、用户纠正、知识缺口、功能诉求写入 `.learnings/`，并在每天回顾时将高价值经验提升到 AGENTS.md / SOUL.md / TOOLS.md / MEMORY.md。适用于“避免重复犯错、沉...
捕获学习内容、错误和纠正以实现持续改进。使用场景：(1) 命令或操作意外失败时，(2) 用户纠正 AI 时（'不对，这样错了...', '实际上应该...'），(3) 用户请求不存在的功能时，(4) 外部 API 或工具失败时，(5) AI...
Review affiliate campaign results and improve strategy. Triggers on: "review my results", "what went wrong", "how to imp...
Use when self-reflection + Self-criticism + Auto-learning from corrections + Self-organizing memory. Agent evaluates its...
自我反思 + 自我批评 + 自我学习 + 自组织记忆。智能体评估自己的工作，捕捉错误，并永久改进。适用于以下场景：(1) 命令、工具、API 或操作失败时；(2) 用户纠正你或拒绝你的工作成果时；(3) 你发现自己的知识过时或不正确时；(4...
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistake...
Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learning...
Continuous improvement through error tracking, lesson learning, and feedback integration
Captures learnings, errors, and corrections to enable continuous improvement. Review before major tasks.
Captures and maintains learnings, errors, and corrections. Use when a command fails, the user corrects an assumption, a...
Curate the agent's own memory into durable project knowledge. Reviews Claude Code auto-memory (MEMORY.md and its topic f...
Low-noise self-improvement skill. Captures learnings, errors, and corrections into a local `.learnings/` cache layer. Ne...
Use this skill to turn execution feedback into reusable operational knowledge.
Understanding and using StickerNest's self-improving AI system. Use when the user asks about AI self-improvement, prompt...
Am I investigating, or just confirming what I already believe? Self-correcting research methodology combining blind work...
Self-learning system — log mistakes/wins, run retrospectives, promote patterns to hard rules, and coach on workflow qual...
Autonomous self-learning loop for OpenClaw agents. Auto-captures memories, creates skills from experience, extracts less...
Capture a hard-won "golden path" from the current session as a reusable Agent Skill, so future sessions start already kn...
Continuous self-improvement through systematic logging, pattern detection, and behavioral updates. Use when: the owner c...
Autonomous skill generator that learns new technologies from the web. Use when, users want to learn about a new library/...
Autonomously research any technology, library, framework, or API. Discovers official documentation, extracts key informa...
Automatic self-learning system that captures user feedback and updates project rules in real-time
Memory sidecar for agent work: recall before tasks, record learnings after tasks, review recommendations, optional backp...
Use when starting any task in a project - keeps CLAUDE.md instruction file current with high-level project state, prompt...
Maintain my own autonomy systems — crons, flags, backups.
当个人希望提升自身在职业或社会中的不可替代性，以应对环境变化和不确定性时
Use when auditing self-media videos, scripts, covers, subtitles, voiceover, product links, account copy, comments, artic...
分析单篇、系列、周度或月度自媒体数据并形成可执行复盘。用于读取平台后台截图、CSV、表格、公开链接或用户提供的数据，计算关注效率和深度互动，比较同平台基线，归因选题、标题、封面、开头、结构、发布时间、标签和行动，并输出加码、改包装、再适配、...
为单篇或多平台自媒体创作澄清需求并生成可确认的创作简报。用于用户只给一句话选题、一个链接、一份素材、一个产品或模糊创作要求，需要确认目标受众、内容目标、核心判断、角度、深度、调性、证据、禁区和平台差异时。纯数据分析、已确认方向后的改稿和细节...
将自媒体创作里程碑保存成文件，管理版本、核验路径、生成完整发布包并更新内容索引。用于保存平台第一版完整成稿、多平台合集、短视频脚本、分镜、定稿、发布包和复盘报告，或用户说“保存一下、整理交付、归档、生成发布清单”时。标题微调、删一句和临时候...
把账号定位和业务目标转成可执行的自媒体内容策略。用于账号冷启动、重新定位、制定内容配比、规划系列栏目、建立选题池、安排周度或月度内容日历、评估产能和确定平台分工。单篇内容写作或纯数据复盘不使用此 Skill。
通用自媒体内容生产与经营工作流。用于自媒体内容创作、选题策划、热点或竞品研究、多平台改写、短视频脚本、数字人视频、动画解说视频、YouTube 与抖音视频号小红书多平台视频发布、发布包、公众号草稿、内容数据分析、周复盘、月复盘和继续未完成任...
将已确认的母题、证据和创作简报写成平台原生内容。用于 X 短帖、长帖或线程，小红书图文，微信公众号文章，视频号、抖音或小红书视频发布文案，YouTube 标题、描述、章节、标签和缩略图方案，以及同一母题的多平台适配。强调各平台独立设计标题、...
把已确认的母题或文案转成可直接拍摄、录屏或交给视频工具制作的视频方案，也支持在用户确认肖像与声音权利并完成平台手动上传后制作数字人视频，以及用合成配音和 AI 绘制画面制作无真人出镜的动画解说视频（科普、历史、品牌故事）。用于视频号、抖音、...
安全追踪热点、研究关键词和拆解竞品内容，并将结果转成原创选题和证据包。用于用户要求找热点、看趋势、分析爆款、研究竞品账号、拆标题或开头、比较内容结构、发现评论需求和判断时效窗口。只做公开信息研究和只读采集，不自动互动、发布或使用主账号登录态...
把已确认终稿的视频成片发布到 YouTube、抖音、视频号、小红书等平台。用于用户说“发视频、同步发布、上传 YouTube、发到抖音视频号小红书、定时发布”等场景。按平台核对视频版本、封面、字幕、标题描述和 AI/版权声明，生成逐平台发布...
把已确认的公众号终稿 Markdown 排版并写入微信公众号草稿箱。用于用户说"发布到公众号、写入草稿箱、公众号排版、换个排版主题、发小绿书图片消息"等场景。自动上传封面与文内图片，支持多主题与自定义 CSS、多账号和 server 模式。...
Beginner-friendly reverse-engineering workflow for Self Modifying Code. Use it to collect evidence, choose static or dyn...
Proactive self-monitoring of infrastructure, services, and health. Tracks disk/memory/load, service health, cron job sta...