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
4,2734,320 · page 90 / 104
pinme-shareUse this skill when the user wants to share, publish, or upload a static result through PinMe, especially by generating a static…glitternetworkpipedrive-automationAutomate Pipedrive CRM operations including deals, contacts, organizations, activities, notes, and pipeline management via Rube…davepoonpipedrive-automationAutomate Pipedrive CRM operations including deals, contacts, organizations, activities, notes, and pipeline management via Rube…sickn33pipeline-crm-automationAutomate Pipeline CRM tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpiping-stressSkill for piping system stress analysis per ASME B31a5c-aiwritesplacekey-automationAutomate Placekey tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQplacid-automationAutomate Placid tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQplain-automationAutomate Plain tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQplasma-etch-controllerPlasma etching skill for anisotropic nanostructure patterning with selectivity and profile controla5c-aiwritesplasmic-automationAutomate Plasmic tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQplaterecognizer-automationAutomate Platerecognizer tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpldi-experimentsUse when designing or auditing a PLDI evaluation — choosing defensible benchmark suites and baseline compiler configurations…brycewang-stanfordplisio-automationAutomate Plisio tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQPlot CatBoost Feature Importance with Custom StylingGenerates a Python function to train a CatBoost model on a DataFrame and plot feature importances. The plot must display feature…ECNU-ICALKpm-soulUse when preserving product intent, acceptance criteria, decision memory, open loops, roadmap context, or the product-manager…agentlas-aipnasnexus-openaccessUse to settle PNAS Nexus's open-access decisions — confirm the gold-OA model and the article processing charge (APC), check…brycewang-stanfordpodc-artifact-evaluationUse when an author expects an artifact-evaluation or badge track at ACM PODC and needs redirecting — PODC has NO artifact track…brycewang-stanfordpodc-experimentsUse when building the evidence for an ACM PODC paper — where "evidence" is a proof, not a benchmark. Covers matching upper and…brycewang-stanfordpodc-reproducibilityUse when making an ACM PODC paper's result independently checkable — reproducibility for a proofs venue, not an artifact venue.…brycewang-stanfordpodc-topic-selectionUse when deciding whether a distributed-computing result belongs at ACM PODC or should be routed to DISC, SPAA…brycewang-stanfordpods-artifact-evaluationUse for the PODS analogue of artifact evaluation — there is no systems artifact track at this theory symposium, so this skill…brycewang-stanfordpolar-billingThis skill should be used when working on Polar billing system, Stripe integration, subscription lifecycle, checkout flows, or…fcakyonpolars_row_wise_ensemble_median_3_stepCalculates the row-wise median of model prediction columns in a Polars DataFrame using a strict 3-step eager evaluation pattern…ECNU-ICALKpolis-protocolCoordinate multi-vendor AI agents as a self-improving team — a learning router assigns work by track record and citizens can…sickn33polygon-automationAutomate Polygon tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpolygon-io-automationAutomate Polygon IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpolymer-characterizationSpecialized skill for polymer materials analysis including molecular weight distribution, thermal transitions, crystallinity, and…a5c-aiwritespom-literature-positioningUse when positioning a Production and Operations Management (POM) manuscript within an operations conversation — against the…brycewang-stanfordpom-topic-selectionUse when deciding whether an operations-management project fits Production and Operations Management (POM), which POM Department…brycewang-stanfordpoptin-automationAutomate Poptin tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpostgrid-automationAutomate Postgrid tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpostgrid-verify-automationAutomate Postgrid Verify tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQposthog-automationAutomate PostHog tasks via Rube MCP (Composio): events, feature flags, projects, user profiles, annotations. Always search tools…davepoonposthog-automationAutomate PostHog tasks via Rube MCP (Composio): events, feature flags, projects, user profiles, annotations. Always search tools…sickn33power-analysis-calculatorSkill for statistical power analysis and sample size calculationa5c-aiwritespower-bi-dax-optimizationComprehensive Power BI DAX formula optimization prompt for improving performance, readability, and maintainability of DAX…githubpower-bi-performance-troubleshootingSystematic Power BI performance troubleshooting prompt for identifying, diagnosing, and resolving performance issues in Power BI…githubpower-platform-mcp-connector-suiteGenerate complete Power Platform custom connector with MCP integration for Copilot Studio - includes schema generation…githubPPO Agent for Multi-Parameter Tuning with Discrete ActionsImplements a PPO (Proximal Policy Optimization) agent and environment for tuning multiple continuous parameters using a…ECNU-ICALKPPO Multi-Parameter Optimization AgentImplements a PPO agent and environment for optimizing multiple parameters where each parameter has three discrete actions…ECNU-ICALKpr-precheckUse when the user invokes `/pr-precheck <repo> <topic>` or — implicitly, before any other skill opens a pull request — to check…vouchdevprd-authorALIAS · 别名 Skill。v2.1 起合并到 `prd`。保留本文件仅用于兼容老 SOP 引用。charliehzmprd-precheckALIAS · 别名 Skill。本 Skill 在 v2.1 起被合并到 `prd-implementation-precheck`。 保留本文件仅用于兼容老 SOP 引用;新代码应改用主 Skill。charliehzmpre-mortem-facilitatorPre-mortem analysis skill for prospective hindsight and failure mode identificationa5c-aiwritesprecedent-transaction-analyzerM&A precedent transaction analysis skill with deal sourcing and premium analysisa5c-aiwritesprecoro-automationAutomate Precoro tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQprediction-monitorMonitor prediction monitor operations. Auto-activating skill for ML Deployment. Triggers on: prediction monitor, prediction…jeremylongshorewritesPreferred Workstyle Analysis using Lippit and Lippit's ModelAnalyzes a user's preferred consulting role from Lippit and Lippit's Guidance model by defining all roles, summarizing user…ECNU-ICALK
← Prev90 / 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