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 62,644codex 9,699cursor 6,852copilot 2,269windsurf 126cline 82
CategoryWorkflow & Productivity 11,684AI & Agents 4,965Data & Analytics 4,693Code Review & Quality 2,936Security 2,762Backend & API 2,480Design & Presentation 2,329Documentation 2,157Content & Marketing 2,001Testing & QA 1,723DevOps & Cloud 1,266Databases 1,124Frontend 1,015Business & Finance 706Media & Video 507Other 21,420
21,420 found
4,8494,896 · page 102 / 447
thinkStrategic analysis, adversarial validation, executive council debate, and discovery mode for complex decisionsmajiayu000thinkStrategic analysis, adversarial validation, executive council debate, and discovery mode for complex decisionsmajiayu000think-brainstormGood-faith divergent brainstorming for achieving a goal. Validates assumptions, then spawns brainstormers running different…majiayu000think-deliberateAdversarial deliberation process for making decisions. Spawns advocate agents for each option who argue their cases before a…majiayu000think-diagnoseAbductive reasoning about causes. Takes a phenomenon, separates observations from interpretations, then spawns diagnosticians…majiayu000thinkCollaborate on problems by pressure-testing assumptions, surfacing constraints, identifying trade-offs, and proposing feasible…majiayu000thinkApply Reflective Thought Composition (RTC) for deep analysis of complex problems. Use when facing complex tasks requiring…majiayu000think-reflectRetrospective learning from a completed experience. Takes a project, incident, decision that played out, or time period; gathers…majiayu000think-reframeProblem redefinition before problem solving. Takes a stated problem, extracts its premises, then spawns reframers applying…majiayu000think-tankCollaborative exploration and reasoning frameworks. Use when ideas need shaping, decisions need analysis, or requirements need…majiayu000thinking-circle-of-competenceKnow the boundaries of your expertise and operate within them. Use when evaluating opportunities, making decisions outside your…majiayu000thinking-dual-processApply Kahneman's Dual-Process Theory to recognize when to trust intuition vs engage deliberate analysis. Use for high-stakes…majiayu000thinking-effectuationStart with means, not goals; co-create with partners; leverage contingencies. Use for startup strategy, innovation projects, and…majiayu000thinking-fermi-estimationMake order-of-magnitude estimates for unknown quantities by decomposing into known or estimable factors. Use for capacity…majiayu000thinking-first-principlesBreak complex problems into fundamental truths by questioning assumptions and rebuilding from irreducible components. Use for…majiayu000thinking-five-whys-plusEnhanced root cause analysis with explicit bias guards and stopping criteria. Use for incident post-mortems, bug investigations…majiayu000thinking-frameworksCollection of mental models and decision-making frameworks (first principles, 5 whys, SWOT, Occam's razor, Pareto, inversion…majiayu000thinking-inversionApproach problems backward by identifying paths to failure, then systematically avoiding them. Use for risk identification…majiayu000thinking-kepner-tregoeSystematic rational process for complex problem analysis, decision making, and risk assessment. Use for high-stakes engineering…majiayu000thinking-leverage-pointsIdentify where small changes can have large effects using Donella Meadows' hierarchy of system intervention points. Use for…majiayu000thinking-lindy-effectFor non-perishable things, future life expectancy is proportional to current age. Use for technology selection, evaluating…majiayu000thinking-map-territoryRecognize limits of mental models and diagrams. Use when models diverge from reality, debugging expectation mismatches, or…majiayu000thinking-modesExtended thinking modes for deeper analysis. Use when user says 'think', 'think hard', 'ultrathink', 'super think', or 'mega…majiayu000writesthinking-occams-razorApply parsimony principle to prefer simpler explanations with fewer assumptions. Use for hypothesis selection in debugging…majiayu000thinking-oodaRapid decision-making loop for dynamic situations. Use for incident response, competitive scenarios, time-sensitive decisions…majiayu000thinking-opportunity-costEvaluate decisions by what you give up, not just what you gain. Use for resource allocation, prioritization, build vs. buy…majiayu000thinking-pre-mortemImagine a project has failed and work backward to identify why. Use at project kickoffs, before major decisions, or when optimism…majiayu000thinking-probabilisticExpress confidence in ranges, update predictions with new information, and track calibration over time. Use for project…majiayu000thinking-reversibilityClassify decisions by reversibility and match decision process to decision type. Use for technology choices, architecture…majiayu000thinking-second-orderThink beyond immediate consequences to second and third-order effects. Use for strategic decisions, policy changes, and avoiding…majiayu000thinking-socraticSystematic questioning framework to deepen understanding, challenge assumptions, and uncover hidden beliefs. Use for requirements…majiayu000thinking-systemsAnalyze problems as interconnected systems with feedback loops, emergent behavior, and non-linear effects. Use for debugging…majiayu000thinking-theory-of-constraintsIdentify and manage the bottleneck; improvements elsewhere don't matter until the constraint is addressed. Use for performance…majiayu000thinking-via-negativaImprove by removal rather than addition. Focus on what to stop doing, eliminate the negative, and subtract complexity. Use for…majiayu000thought-based-reasoningUse when facing complex reasoning tasks - multi-step math, logic puzzles, decisions with tradeoffs, problems where direct answers…majiayu000thought-partnerCollaborative thinking partner for exploring ideas, challenges, and decisions. Use when the user says "think through", "explore"…majiayu000thought-partnerCollaborative thinking partner for exploring ideas, challenges, and decisions. Use when the user says "think through", "explore"…majiayu000three-match3-MATCH gadgets and non-backtracking geodesics for 3-SAT via colored subgraph isomorphism.majiayu000threejs-scene-setupStand up a three.js scene: import maps and the three/addons path, the Scene/PerspectiveCamera/WebGLRenderer trio, the…gamedev-skillsticket-summarizeSummarize a support ticket thread into key points and action items.majiayu000ticket-triagePull open [Gorgias](https://composio.dev/toolkits/gorgias) support tickets and triage them by urgency, category, and sentimentmajiayu000time-series-decomposerDecompose time series into trend, seasonal, and residual components. Use for forecasting, pattern analysis, and seasonality…majiayu000time-series-forecasterTime series forecasting with ARIMA, Prophet, LSTM, and statistical methods. Activates for "time series", "forecasting", "predict…majiayu000tipkit-generatorGenerate TipKit infrastructure with inline/popover tips, rules, display frequency, and testing utilities. Use when adding…rshankraswritestldr-routerRoute to appropriate tldr analysis depth based on querymajiayu000todisteluRiita-asian todistelun suunnittelu ja arviointi oikeudenkäymiskaaren (4/1734) 17 luvun asianosaisen kuuleminen), todistusteemat…akunikkolatoimeksiantoUuden toimeksiannon, jutun tai asian aloitus ja aineiston haltuunotto suomalaisessa juridisessa työssä. Käytä tätä skilliä AINA…akunikkolatoken-checkUse when the user asks about token usage, session cost, or wants to check optimization effectiveness.majiayu000writes
← Prev102 / 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