Agent skills

Other skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
21,420 found
2,8332,880 · page 60 / 447
continuous-learning-v2Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves…majiayu000contract-clause-analyzerAnalyze construction contract clauses. Identify risks, obligations, and key terms using NLP.majiayu000contract-clause-extractorExtract and analyze key clauses from construction contracts. Identify payment terms, change order procedures, dispute resolution…majiayu000contract-risk-scanner-ukAnalyze UK property conveyancing and pensions contracts to extract key terms, identify legal risks, compare against standard…majiayu000contractor-matching-aiAI-powered contractor matching and selection for construction projects. Analyze contractor capabilities, past performance…majiayu000contrast-checkerCheck color contrast ratios for WCAG compliancea5c-aiwritescontrol-systems-and-dynamicsClassical control and system dynamics for engineered systems — feedback and closed-loop control, transfer functions and block…majiayu000convening-expertsConvenes expert panels for problem-solving. Use when user mentions panel, experts, multiple perspectives, MECE, DMAIC, RAPID, Six…majiayu000conversation-knowledge-extractor深度分析当前对话窗口内容,智能识别对话类型(学术写作、学术探讨、编程任务等),提取关键知识点、方法论、个人习惯、常见错误,并结构化输出为详细的可复用知识库文档。特别针对学术写作场景进行深度记录(修改前后对比、写作偏好、习惯模式)。触发词:"总结这次对话"、"提…majiayu000conversion-diagnostic-kitStructured approach for investigating funnel issues across e-commerce experiences.majiayu000meta-promptingAgents optimizing prompts for other agents (Chain of Thought, Tree of Thoughts).majiayu000copilot-docsConfigure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot…majiayu000copywrite-expertsTalk to Copywrite Experts about their expertise. Copywrite Experts provides authentic advice using their mental models, core…majiayu000researchFind authoritative answers from official docs, RFCs, standards, and academic sources — never from blogs or opinionsmajiayu000COREPersonal AI Infrastructure core. The authoritative reference for how PAI works.majiayu000core-researcherDeep research and information gathering specialist for thorough investigation, pattern analysis, and knowledge synthesismajiayu000cosmicFuturistic sci-fi aesthetic with dark themes, vibrant neon accents, and immersive spatial elements.bergsidecosmiconfig-setupSet up cosmiconfig for hierarchical configuration loading from multiple sources and formats.a5c-aiwritescost-analysisBreak down costs by category (fulfillment, payment, marketplace)majiayu000cost-density-net-rr-calculator計算交易成本對風險報酬比的非線性衰減影響。將固定佣金與點差整合為「成本密度」指標,揭示停損大小與策略效率的雙曲線關係,識別「獲利事件視界」閾值。majiayu000cost-explainExplain all costs in human terms. Always compare with real-world equivalents. Recommend cheapest that works.majiayu000counselExpert simulation for code guidance and style. Triggers on "code like [expert]", "what would [expert] say", "idiomatic", "best…majiayu000couple-weekly-reportGenerate weekly relationship health report showing affect ratios and repair rates for both partners across 3 weeks (current + 2…majiayu000covariant-fibrationsRiehl-Shulman covariant fibrations for dependent types over directedmajiayu000coveApply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions…majiayu000coveApply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions…majiayu000cozy-wholesome-moodCozy, cute, wholesome, relaxing, and peaceful mood direction for Blender assets and scenes.arjun988cpr-letter-drafter-andrew-birdWrites the formal letter you send before suing someone in a civil case in England & Wales — the Letter Before Claim that starts…lawve-aicqrs-implementationImplement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models…sickn33cqrs-implementationImplement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models…wshobsoncrabwalkReal-time companion monitor for OpenClaw agentsmajiayu000ultrathinkDeep thinking mode - approach problems like a craftsman, obsess over details, and create elegant solutionsmajiayu000crankHands-free epic execution for Codex using wave-based sub-agents and lead-side validation. Triggers: "crank", "run epic", "execute…majiayu000crankFully autonomous epic execution. Runs until ALL children are CLOSED. Loops through beads issues, runs /implement on each…majiayu000cre-financingCRE Financing analysis suite — 3 specialist skills for lender identification, quote comparison, and term sheet assembly for…majiayu000create-assistantCreate and configure Vapi voice AI assistants with models, voices, transcribers, tools, hooks, and advanced settings. Use when…majiayu000create-assistantGuide users through creating custom assistants via interactive dialogue.majiayu000create-intent-mapTrain LoRA adapters for converting natural language queries into structured QuerySpec JSON.majiayu000create-postmortemCreate a blameless postmortem when the user asks to write a postmortem, document what went wrong, analyze an incident, or run a 5…majiayu000writescreate-table-classifierTrain vision models to predict optimal Camelot extraction strategies for PDF tables.majiayu000create-tech-radarCreates tech radar entries with opinionated but balanced technical analysis following the BYOR (Build Your Own Radar) structure.…majiayu000Creating ExpertCreate new domain expert with expertise file and workflows. Use when adding new technology or domain area.majiayu000creating-opencode-agentsUse when creating OpenCode agents - provides markdown format with YAML frontmatter, mode/tools/permission configuration, and best…majiayu000crest-competeCompetitive analysis ending in a clear positioning call — where to play, how to win. Use when asked to "analyze competitors"…jeremylongshorewritescrest-reconStrategic context reconnaissance — read existing roadmaps, OKRs, competitive docs, and briefs to establish context before…jeremylongshorewritescrest-roadmapBuild a product roadmap with sequenced bets and explicit tradeoffs. Use when asked to "build a roadmap", "prioritize the backlog…jeremylongshorewritescrisis-detectorIdentify early warning signals of potential PR crises through pattern recognition, escalation triggers, and risk assessmentmajiayu000crisis-response-protocolHandle mental health crisis situations in AI coaching safely. Use when implementing crisis detection, safety protocols, emergency…majiayu000writes
← Prev60 / 447Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going