Agent skills

AI & Agents 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
4,965 found
4,3214,368 · page 91 / 104
prerender-automationAutomate Prerender tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQprintautopilot-automationAutomate Printautopilot tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQprocedural-modelingProcedural asset creation for rocks, buildings, vegetation, roads, terrain, pipes, cables, and sci-fi panels using Geometry Nodes…arjun988process-capability-calculatorProcess capability analysis skill with Cp, Cpk, Pp, Ppk calculations and specification compliance assessment.a5c-aiwritesprocess-economics-estimatorProcess economics estimation skill for capital costs, operating costs, and profitability analysisa5c-aiwritesprocess-fmea-generatorProcess Failure Mode and Effects Analysis (PFMEA) skill for manufacturing risk assessmenta5c-aiwritesprocess-mining-analyzerProcess mining skill for event log analysis, process discovery, and conformance checking.a5c-aiwritesprocess-planningSkill for manufacturing process planning including operation sequencing and work instructionsa5c-aiwritesprocess-simulation-modelerDiscrete event simulation skill for process modeling, scenario testing, and optimizationa5c-aiwritesprocess-street-automationAutomate Process Street tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQprocfu-automationAutomate Procfu tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQproduct-managerSenior PM agent with 6 knowledge domains, 30+ frameworks, 12 templates, and 32 SaaS metrics with formulas. Pure Markdown, zero…sickn33Product StrategyA comprehensive skill for product strategy — covering frameworks, opportunity sizing, prioritization, roadmap building, OKRs, and…cosmicstack-labsproduction-schedulerProduction scheduling optimization skill with constraint handling, changeover minimization, and due date managementa5c-aiwritesproductlane-automationAutomate Productlane tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQperf-profilerUse when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.composio-communitygsd:profile-userGenerate developer behavioral profile and create Claude-discoverable artifactsdavepoonwritesprogressive-estimationEstimate AI-assisted and hybrid human+agent development work with research-backed PERT statistics and calibration feedback loopssickn33project-bubble-automationAutomate Project Bubble tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQproject-detectProjeye girdiginde tech stack'i tespit et, uygun skill ve agent'lari aktive et. Kullanim: /project-detectvibeevalproject-developmentThis skill covers the principles for identifying tasks suited to LLM processing, designing effective project architectures, and…sickn33promethee-evaluatorPROMETHEE (Preference Ranking Organization Method for Enrichment Evaluation) skill for outranking-based multi-criteria analysisa5c-aiwritesprompt-engineering-researchSystematic prompt engineering methods for AI-assisted academic research workf...brycewang-stanfordprompt-engineeringPrompt templates, few-shot examples, chain-of-thought, structured output, evalsvibeevalprompt-libraryA comprehensive collection of battle-tested prompts inspired by…sickn33prompt-lookupActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use…foryourhealth111-pixelprompt-version-managementManage prompt versions, run A/B tests across agent prompts, track performance regressions, and safely roll out prompt changes in…cosmicstack-labsproofly-automationAutomate Proofly tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQprotect-mcp-governanceAgent governance skill for MCP tool calls — Cedar policy authoring, shadow-to-enforce rollout, and Ed25519 receipt verification.sickn33protocol-builderSkill for building standardized research protocolsa5c-aiwritesproxiedmail-automationAutomate Proxiedmail tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpsychbull-meta-analysis-methodsUse when computing effect sizes and fitting the meta-analytic model for a Psychological Bulletin manuscript — effect-size…brycewang-stanfordpsychbull-moderators-and-biasUse when explaining heterogeneity and probing robustness in a Psychological Bulletin meta-analysis — moderator/subgroup analysis…brycewang-stanfordpsychbull-theory-integrationUse when turning the synthesis results of a Psychological Bulletin manuscript into a genuine theoretical contribution —…brycewang-stanfordpublic-plugin-builderActivate when the user wants to build a Claude plugin, create a Claude skill, make a Claude agent, structure a Claude Code…davepoonpublic-plugin-packagingUse when packaging this meta-agent for public Codex plugin registration, Claude Code installation, GitHub release, one-line…agentlas-aipuppeteer-skillGenerates Puppeteer scripts for browser automation, scraping, and PDF generation. Triggers on: "Puppeteer", "headless Chrome"…sickn33pushbullet-automationAutomate Pushbullet tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpushover-automationAutomate Pushover tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpymatching-decoderMinimum-weight perfect matching decoder skill for surface code error correctiona5c-aiwritespymeasure-automationPyMeasure laboratory automation skill for instrument control and automated measurement sequencesa5c-aiwritespymol-visualizerPyMOL molecular visualization skill for structure rendering and analysisa5c-aiwritespyscf-quantum-chemistryPySCF quantum chemistry skill for molecular calculations, coupled cluster, and multireference methodsa5c-aiwritespythia-event-generatorPythia event generation skill for proton-proton and lepton collisions at high energiesa5c-aiwritesPython Tkinter Inference GUI with Model and Tokenizer SelectionCreate a user-friendly Python GUI using Tkinter that allows users to load a trained Keras model via a file explorer and select a…ECNU-ICALKPyTorch Character-Level Transformer with 8-bit VocabularyImplement a PyTorch Transformer model using nn.Transformer without manual weight initialization, and a text-to-tensor conversion…ECNU-ICALKPyTorch Configurable Transformer Training with Best Model CheckpointingImplements a PyTorch Transformer model with configurable layer dimensions and attention masking, and a training loop that retains…ECNU-ICALKPyTorch模块多头交叉注意力机制集成针对PyTorch中的特征增强模块(如Counter_Guide_Enhanced),将其内部的单一交叉注意力机制替换为多头交叉注意力机制,以提升模型对双模态特征的表达能力和交互深度。ECNU-ICALK
← Prev91 / 104Next →
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