Agent skills

Skills for copilot

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
2,269 found
1,8251,872 · page 39 / 48
hookify-rulesThis skill should be used when the user asks to create a hookify rule, write a hook rule, configure hookify, add a hookify rule…mturacqdrant-horizontal-scalingDiagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?'…githubhotel-core【已废弃并合并】此技能已迁移至新版酒店查询、预订技能rollinggo-hotel-booking。如果是下载过程,请直接选择 rollinggo-hotel-booking。触发此技能后大模型会引导用户迁移到新版。RollingGo-AIhreflang-checkAudit hreflang tags. Use when: checking missing tags, incorrect language codes, or x-default configuration.indranilbanerjeeimage-annotationsAnnotate screenshots, diagrams, and images with callout rectangles, arrows, labels, and color-coded highlights using PIL.…githubimage-manipulation-image-magickProcess and manipulate images using ImageMagick. Supports resizing, format conversion, batch processing, and retrieving image…githubimage-seo-auditAudit image SEO. Use when: checking alt text, file sizes, WebP/AVIF formats, lazy loading, or responsive images.indranilbanerjeeimport-guidelinesImport brand guidelines. Use when: adding voice guides, style restrictions, or messaging frameworks.indranilbanerjeeimport-infrastructure-as-codeImport existing Azure resources into Terraform using Azure CLI discovery and Azure Verified Modules (AVM). Use when asked to…githubimport-sopImport agency SOPs. Use when: adding workflow definitions, approval processes, or launch checklists.indranilbanerjeeimport-templateImport deliverable templates. Use when: adding proposal formats, report structures, or brief templates.indranilbanerjeeincident-postmortemUse when an outage, production incident, or significant service degradation has occurred and the team needs to write a structured…githubqdrant-indexing-performance-optimizationDiagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes…githubinfluencer-briefCreate influencer campaign briefs. Use when: setting creator criteria, FTC compliance, or measurement plans.indranilbanerjeeinstall-atkInstall or update the M365 Agents Toolkit (ATK) CLI and VS Code extension. "install the toolkit", "setup atk", "get atk"…microsoftintegrate-context-maticDiscovers and integrates third-party APIs using the context-matic MCP server. Uses `fetch_api` to find available API SDKs, `ask`…githubintegrationsShow MCP integration status. Use when: checking active connectors, available integrations, or skill unlocks.indranilbanerjeeintelligence-reportGenerate marketing intelligence briefings from compound intelligence across agents — surfaces learnings, cross-agent patterns…indranilbanerjeeinventory-demand-planningCodified expertise for demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation at…mturacinvestor-materialsCreate and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials.…mturacinvestor-outreachDraft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user…mturacistio-traffic-managementConfigure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when…wshobsoniterative-retrievalPattern for progressively refining context retrieval to solve the subagent context problemmturacjava-add-graalvm-native-image-supportGraalVM Native Image expert that adds native image support to Java applications, builds the project, analyzes build errors…githubjava-coding-standardsJava coding standards for Spring Boot and Quarkus services: naming, immutability, Optional usage, streams, exceptions, generics…mturacjava-docsEnsure that Java types are documented with Javadoc comments and follow best practices for documentation.githubjava-helidonGet best practices for developing applications with Helidon 4 (SE and MP). Use when working with Helidon SE or Helidon MP…githubjava-junitGet best practices for JUnit 5 unit testing, including data-driven testsgithubjava-mcp-server-generatorGenerate a complete Model Context Protocol server project in Java using the official MCP Java SDK with reactive streams and…githubjava-refactoring-extract-methodRefactoring using Extract Methods in Java Languagegithubjava-refactoring-remove-parameterRefactoring using Remove Parameter in Java Languagegithubjava-springbootGet best practices for developing applications with Spring Boot.githubjavascript-typescript-jestBest practices for writing JavaScript/TypeScript tests using Jest, including mocking strategies, test structure, and common…githubjavax-to-jakarta-migrationMigrate Java code from javax.* to jakarta.* namespace. Use when upgrading to Tomcat 11, Jakarta EE 10, or when javax imports are…githubjira-cliInteract with Jira from the command line to create, list, view, edit, and transition issues, manage sprints and epics, and…Code-and-Sortsjira-integrationUse this skill when retrieving Jira tickets, analyzing requirements, updating ticket status, adding comments, or transitioning…mturacjourney-designDesign cross-channel customer journeys. Use when: mapping touchpoints, branching logic, or stage transitions.indranilbanerjeejpa-patternsJPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and…mturackeyword-clusterBuild a content cluster plan from seed keywords — pillar+spokes architecture with internal-link map, intent grouping, and quality…indranilbanerjeekeyword-researchResearch keyword expansion, intent, and gaps. Use when: mapping search intent, finding content gaps, or long-tail discovery.indranilbanerjeekiro-discoveryEntry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed…gotalabkiro-spec-batchCreate complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by…gotalabkiro-spec-designGenerate comprehensive technical design translating requirements (WHAT) into architecture (HOW) with discovery process. Use when…gotalabwriteskiro-spec-initInitialize a new specification with detailed project descriptiongotalabkiro-spec-quickQuick spec generation with interactive or automatic modegotalabkiro-spec-requirementsGenerate EARS-format requirements based on project description and steering context. Use when generating requirements from…gotalabwriteskiro-spec-tasksGenerate implementation tasks from requirements and design. Use when creating actionable task lists.gotalabwriteskiro-steering-customCreate custom steering documents for specialized project contexts. Use when creating domain-specific steering files.gotalabwrites
← Prev39 / 48Next →
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