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
2,2092,256 · page 47 / 447
ab-testing-analyzer全面的AB测试分析工具,支持实验设计、统计检验、用户分群分析和可视化报告生成。用于分析产品改版、营销活动、功能优化等AB测试结果,提供统计显著性检验和深度洞察。majiayu000writesab-testingUse when designing experiments for subject lines, offers, cadences, or journeys.majiayu000abaqus-odbRead analysis results. Use when user asks about maximum stress, extracting displacements, reaction forces, or exporting results.…majiayu000writesabstract-domain-explorerApplies abstract interpretation using different abstract domains (intervals, octagons, polyhedra, sign, congruence) to statically…majiayu000abstract-trace-summarizerPerforms abstract interpretation to produce summarized execution traces and high-level program behavior representations.…majiayu000ac-autonomous-orchestratorMain orchestrator for autonomous coding operations. Use when running autonomous sessions, coordinating components, managing the…majiayu000ac-checkpoint-managerManage checkpoints for rollback capability. Use when creating save points, rolling back changes, managing recovery points, or…majiayu000ac-lockPhase 4.0 — Acceptance Criteria lock checkpoint before implementation. Consolidates all ACs from PRD, TechSpec, and Tasks…majiayu000academic-researchA tool for rigorous academic research using Semantic Scholar and ArXiv. Focuses on finding highly-cited papers, retrieving…majiayu000academic-researchA tool for rigorous academic research using Semantic Scholar and ArXiv. Focuses on finding highly-cited papers, retrieving…majiayu000academic-researchA tool for rigorous academic research using Semantic Scholar and ArXiv. Focuses on finding highly-cited papers, retrieving…majiayu000accessibility-reportGenerate accessibility compliance reports including VPAT and ACR documentsa5c-aiwritesaccount-research-briefUse when preparing to engage a target account, researching a company before outreach, or building pre-call intelligence.…majiayu000decision-actionUse when the user needs to choose, prioritize, or make a go/no-go decision among options.majiayu000diagnostic-actionUse when the user asks why something happened, what’s wrong, root cause analysis, debugging, or incident explanation.majiayu000activation-analysisAnalyze user activation using Setup → Aha → Habit framework. Identifies activation bottlenecks.majiayu000active-directory-attacksProvide comprehensive techniques for attacking Microsoft Active Directory environments. Covers reconnaissance, credential…sickn33active-learning-systemЭксперт active learning. Используй для ML с участием человека, uncertainty sampling, annotation workflows и labeling optimization.majiayu000adaptive_answer_evaluatorProvides direct, unexplained answers for math, code, and multiple-choice questions. For True/False statements, performs detailed…majiayu000adaptive-temporal-analysis-integrationIntegrate adaptive temporal analysis for drift detection.majiayu000add-cursor-pagination-tassadar2499-novatune-2Add cursor-based pagination for list endpoints with stable ordering (project)majiayu000add-cursor-paginationAdd cursor-based pagination for list endpoints with stable ordering (project)majiayu000add-emacsAdd Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NanoClaw from within Emacs…nanocoaiadd-query-filterAdd custom query parameter filters to entity endpoints. Use when extending search/filter capabilities beyond the base pagination.…majiayu000add-rewardGuide for adding a new reward function to AReaL. Use when user wants to create a reward function.majiayu000adhdADHD-optimized code explainer. Generates layered, scannable explanations with hooks, maps, and progress markers.majiayu000ado-repo-analysisAnalyze sibling repos to find best match for a work itemmajiayu000advanced-tool-useContext-efficient tool management via search, deferred loading, and programmatic callingmajiayu000advogado-especialistaAdvogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor…sickn33agentforce-2025Salesforce Agentforce AI agents and autonomous automation (2025)majiayu000agentforge-runtime-daemonWork on the persistent Mastra daemon in packages/runtime, including createStandardAgent, daemon lifecycle, environment…majiayu000agentic-compassNavigation and decision-making framework for autonomous agents.majiayu000agentic-frameworkInfinite Improvement Framework: Move from Probabilistic Agents to Deterministic Workflows.majiayu000agentic-layer-assessmentAssess agentic layer maturity using the 12-grade classification system (Class 1-3). Use when evaluating codebase readiness…majiayu000agentkitCoinbase AgentKit - Toolkit for enabling AI agents with crypto wallets and onchain capabilities. Use for building autonomous…majiayu000agents-bootstrapGenerate a project-specific AGENTS.md from a user goal, then confirm before overwriting.majiayu000agents-local-mdGenerate machine-specific AGENTS.local.md with host facts and system tool detailsmajiayu000agents-md-authoring-majoWrite effective AGENTS.md files for AI coding agents.majiayu000aget-assess-riskAssess risks with likelihood, impact, and mitigation optionsmajiayu000aget-assess-tradeoffsAnalyze trade-offs between competing architectural concernsmajiayu000aget-capture-observationCapture research observations into AGET KB without committing specs. Use when discovering vocabulary candidates, RQ proposals…majiayu000aget-check-evolutionMonitor .aget/evolution/ directory health. Validates file counts, naming conventions, disk usage, and returns health status with…majiayu000aget-check-healthRun AGET health inspection and housekeeping checksmajiayu000writesaget-check-sessionsMonitor sessions/ directory health. Detects date subdirectories (anomaly), counts files, validates naming conventions, and tracks…majiayu000aget-create-projectCreate research projects with context-aware scaffolding. Reads AGET identity, searches prior work, pre-populates Due Diligence.…majiayu000aget-generate-reportGenerate reports with metrics, findings, and visualizationsmajiayu000writesaget-recommend-actionProvide recommendations with rationale and alternativesmajiayu000aget-study-topicResearch a topic across the knowledge base before implementation. Searches L-docs, patterns, PROJECT_PLANs, SOPs, and governance…majiayu000
← Prev47 / 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