Context & AI engineering
25,745 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
nibzard/skills/skills/claude-thread-publisher Skill
2★ repoPublish Claude Code conversation threads as static HTML pages hosted on GitHub Gists, with shareable gistpreview links. Use when the user asks to share, publish, or delete a Claude Code thread.
The same file is in 2 other repositories
nibzard/skills/skills/claude-thread-publisher/skills/claude-thread-publisher Skill
2★ repoPublish Claude Code conversation threads as static HTML pages hosted on GitHub Gists, with shareable gistpreview links. Use when the user asks to share, publish, or delete a Claude Code thread.
nibzard/skills/skills/skill-creator Skill
2★ repoCreate new Agent Skills interactively or from templates. Use when user wants to create, generate, scaffold, or build a new skill, or mentions creating skills, writing skills, skill templates, skill development.
nibzard/skills/skills/skill-creator/skills/skill-creator Skill
2★ repoCreate new Agent Skills interactively or from templates. Use when user wants to create, generate, scaffold, or build a new skill, or mentions creating skills, writing skills, skill templates, skill development.
avivsinai/skills-marketplace/plugins/skill-authoring/skills/eval-skills Skill
2★ repoEval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against a per-case bar, and let the gaps drive the edits. Use when the user wants to test/eval/improve/harden a skill, says "this skill keeps producing X / keeps missing Y", or hands a skill plus cases with a bar for what good looks like. Pairs with write-skills (the authoring principles every fix obeys). Judgment-first and harness-free — prefer skill-creator for harness-based benchmarking, variance analysis, or description-optimization loops.
The same file is in 1 other repository
Skm install linked agent skills
weiox/skm/skills/skm-install-linked-agent-skills Skill
no license2★ repoUse when a user pastes a GitHub repo URL, `skills.sh` link, `owner/repo@skill` reference, or local git path for an external skill package and wants it imported into `~/.skm/vendor` with `Codex` and `Claude Code` entrypoints rebuilt automatically.
weiox/skm/skills/skm-organize-agent-skills Skill
no license2★ repoUse when local skills for Codex and Claude Code are scattered across `~/.agents/skills`, `~/.claude/skills`, `~/.codex/skills`, or ad-hoc folders and you want to consolidate them into a single source of truth under `~/.skm` while keeping tool-specific symlink entrypoints.
weiox/skm/skills/skm-release-agent-skill-pack Skill
no license2★ repoUse when a local agent skill pack is ready to become a standalone GitHub repository and you want to validate its structure, frontmatter, and release readiness, then generate a first-release checklist.
weiox/skm/skills/skm-sync-agent-skills Skill
no license2★ repoUse when the declared skill layout under `~/.skm` and the live entrypoints in `~/.agents/skills` or `~/.claude/skills` may be out of sync, and you want to rebuild missing links while removing stale or unmanaged symlinks.
Collaborative engineering agent
kinhluan/skills/.agent-skills/collaborative-engineering-agent Skill
2★ repoUnified SDLC skill for Agentic Project Management, GitOps/SecOps, and Dialectical Review loops.
kinhluan/skills/.agent-skills/kubernetes-orchestration Skill
2★ repoKubernetes deployment and orchestration patterns
kinhluan/skills/.agent-skills/research-workspace-standard Skill
2★ repoStandardized directory structure and artifact management for agentic research. Ensures consistent data flow across all agent platforms (Gemini, Claude, Antigravity).
kimtth/ms-fabric-skills-dev-starter/.agents/skills/fabric-api-discovery Skill
no license2★ repoDiscover Fabric APIs, OpenAPI specs, item schemas, and best practices using the Fabric MCP Server. Use when exploring available Fabric workloads, looking up API specifications, finding item definition formats, or managing OneLake files programmatically. All MCP tools run locally for reference.
kimtth/ms-fabric-skills-dev-starter/.agents/skills/fabric-data-agent Skill
no license2★ repoDesign, configure, evaluate, and govern Microsoft Fabric Data Agents for natural-language Q&A over Lakehouse, Warehouse, Power BI semantic model, KQL database, mirrored database, ontology, or Microsoft Graph data. Use when the user asks for Fabric data agent, conversational analytics, NL2SQL, NL2DAX, NL2KQL, data-agent instructions, example queries, agent evaluation, publishing, sharing, governance, diagnostics, or ALM.
kimtth/ms-fabric-skills-dev-starter/.agents/skills/powerbi-consumption-cli Skill
no license2★ repoThe ONLY supported path for read-only Microsoft Fabric Power BI semantic model (formerly "Power BI dataset") query interactions. Execute DAX queries via the MCP server ExecuteQuery tool to: (1) discover semantic model metadata (tables, columns, measures, relationships, hierarchies, etc.) and their properties, (2) retrieve data from a semantic model. Triggers: "DAX query", "semantic model metadata", "list semantic model tables", "run EVALUATE", "get measure expression".
troyjthomas/ios-agent-skills/skills/mcp-setup Skill
2★ repoSet up the complete MCP stack for iOS development with Claude Code. Covers Figma MCP, Sosumi (Apple Docs), XcodeBuildMCP, and Apple's Xcode MCP Bridge. Use this skill when starting a new project, setting up a new machine, or when Claude Code can't access Apple documentation, build your project, or render SwiftUI previews. This is a one-time setup that makes every subsequent session dramatically better.
troyjthomas/ios-agent-skills/skills/xcode-integration Skill
2★ repoSafe patterns for Claude Code interacting with Xcode projects. Covers .pbxproj protection (critical), XcodeBuildMCP build/test patterns, the RenderPreview visual feedback loop, and when to use terminal Claude Code vs Xcode's built-in Claude Agent. Use this skill throughout the entire build process. The .pbxproj rule alone prevents hours of wasted debugging.
yu-iskw/meta-agent-skills/.claude/skills/mend-agent-rules Skill
no license2★ repoSynchronize CLAUDE.md and AGENTS.md with available agents and skills.
yu-iskw/meta-agent-skills/.claude/skills/mend-agent-templates Skill
no license2★ repoMaintain and synchronize agent templates with their associated skill templates.
yu-iskw/meta-agent-skills/skills/mend-agent-skills Skill
no license2★ repoVerifies and updates the commands within existing Agent Skills to ensure they match the current codebase state.
yu-iskw/meta-agent-skills/skills/meta-agent-skills Skill
no license2★ repoProactively analyzes the codebase and generates specialized subagents and skills to standardize agentic workflows.
The same file is in 2 other repositories
secondorderai/ouroboros/.claude/skills/refactor-agents-md Skill
2★ repoRefactor an AGENTS.md or CLAUDE.md file using the Progressive Disclosure Principle so that only essential, universal instructions stay at root level while domain-specific guidance moves to subsidiary files loaded just-in-time. Use this skill whenever the user wants to restructure, slim down, optimize, or declutter their AGENTS.md or CLAUDE.md file, mentions "progressive disclosure" for agent instructions, says their instruction file is "too long" or "bloated," asks how to reduce token overhead in their agent config, or wants Claude to "only load what it needs." Also trigger when the user says things like "refactor my CLAUDE.md," "split up my AGENTS.md," "organize my agent instructions," or "my AGENTS.md has gotten out of hand."
secondorderai/ouroboros/packages/desktop/resources/agent-browser/skills/agent-browser Skill
2★ repoBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
secondorderai/ouroboros/packages/desktop/resources/skills/builtin/agent-browser Skill
2★ repoUse this skill when the user wants Ouroboros to browse or automate websites in a real Chrome-compatible browser. Prefer it for navigating pages, taking browser snapshots, clicking or filling visible controls, scraping page state, testing web flows, and using CDP auto-connect without asking the user to install npm packages.
scalekit-inc/skills/skills/building-agent-mcp-server Skill
no license2★ repoGuides developers through creating a Scalekit MCP server with authenticated tool access. Use when building an MCP server, exposing Scalekit tools over MCP, or connecting AI agents via LangChain/LangGraph MCP adapters.
The same file is in 4 other repositories
scalekit-inc/skills/skills/express-mcp-server Skill
no license2★ repoBuild a production-ready MCP server using Express.js, TypeScript, and OAuth 2.1 Bearer token authentication via Scalekit. Use when the user wants to build an MCP server with Express.js and needs fine-grained control over HTTP request handling and middleware chains.
scalekit-inc/skills/skills/fastapi-fastmcp Skill
no license2★ repoBuild a production-ready MCP server using FastAPI and FastMCP with OAuth 2.1 Bearer token authentication via Scalekit. Use when the user wants to build an MCP server with FastAPI/FastMCP and needs fine-grained control over authentication middleware and token validation.
scalekit-inc/skills/skills/integrating-agent-auth Skill
no license2★ repoIntegrates Scalekit Agent Auth into a project to handle OAuth flows, token storage, and automatic refresh for third-party services (Gmail, Slack, Notion, Calendar). Use when a user needs to connect to an external service, authorize OAuth access, fetch access or refresh tokens, or execute API calls on behalf of a user.
The same file is in 1 other repository
scalekit-inc/skills/skills/mcp-auth-expressjs-scalekit Skill
no license2★ repoAdd Scalekit OAuth authentication to an Express.js MCP server (TypeScript). Supports two modes: scaffold a new server from scratch, or retrofit an existing Express app. Implements /.well-known/oauth-protected-resource for MCP client discovery, a Bearer-token validation middleware using @scalekit-sdk/node (audience check), and a POST / MCP endpoint using StreamableHTTPServerTransport.
Mcp auth fastapi fastmcp scalekit
scalekit-inc/skills/skills/mcp-auth-fastapi-fastmcp-scalekit Skill
no license2★ repoAdd Scalekit OAuth authentication to a FastAPI + FastMCP server (Python). Use when you need FastAPI-level middleware control over token validation alongside FastMCP tools. Implements /.well-known/oauth-protected-resource, a Starlette middleware that validates Authorization Bearer tokens via Scalekit SDK (issuer + audience), and mounts FastMCP via app.mount.
scalekit-inc/skills/skills/mcp-auth-fastmcp-scalekit Skill
no license2★ repoAdd Scalekit OAuth authentication to a FastMCP server (Python). Use when you need to protect FastMCP tools with OAuth 2.1 Bearer tokens and enforce per-tool scope checks (e.g. todo:read, todo:write). Authentication is added in 5 lines via ScalekitProvider; scope checks use get_access_token() inside each tool.
The same file is in 1 other repository
scalekit-inc/skills/skills/mcp-oauth-fastmcp Skill
no license2★ repoAdd OAuth 2.1 authorization to FastMCP servers using Scalekit provider plugin. Use when building FastMCP servers, when users mention FastMCP authentication, Python MCP servers with Scalekit, or need rapid OAuth integration with minimal code.
The same file is in 3 other repositories
scalekit-inc/skills/skills/mcp-oauth21-scalekit Skill
no license2★ repoAdd production-ready OAuth 2.1 authorization to an MCP server using Scalekit. Use this when you need MCP clients (Claude Desktop, Cursor, VS Code, or any MCP client) to discover your authorization server via .well-known/oauth-protected-resource, and when you need to validate Bearer access tokens (aud/iss/exp/scope) before executing MCP tools.
The same file is in 1 other repository
Production readiness agent auth
scalekit-inc/skills/skills/production-readiness-agent-auth Skill
no license2★ repoWalks through a structured production readiness checklist for Scalekit agent authentication implementations. Use when the user says they are going live, launching to production, doing a pre-launch review, or wants to verify their agent OAuth implementation is production-ready.
scalekit-inc/skills/skills/production-readiness-mcp-auth Skill
no license2★ repoWalks through a structured production readiness checklist for Scalekit MCP authentication implementations. Use when the user says they are going live, launching to production, doing a pre-launch review, or wants to verify their MCP server authentication is production-ready.
scalekit-inc/skills/skills/scalekit-code-doctor Skill
no license2★ repoUse when a user asks to generate, review, validate, or fix any code snippet that uses Scalekit APIs or SDKs. This skill is the single source of truth for Scalekit code correctness — it can generate illustration-quality snippets from scratch (for docs, websites, or integration guides) and review existing code to catch wrong method names, missing parameters, security anti-patterns, and broken auth flows. Covers all four SDKs (Node, Python, Go, Java), raw REST API calls, and both Scalekit product suites — SaaSKit (SSO, login, sessions, RBAC, SCIM) and AgentKit (connections, tool calling, MCP auth). Use when the user says review my Scalekit code, generate a Scalekit example, validate this auth flow, check my SDK usage, fix my Scalekit integration, write a code sample for docs, or anything involving Scalekit code quality.
scalekit-inc/skills/skills/setup-scalekit Skill
no license2★ repoUse when a developer is new to Scalekit and needs guidance on where to start, doesn't know which auth plugin or skill to choose, wants to connect an AI agent or agentic workflow to third-party services (Gmail, Slack, Notion, Google Calendar), needs OAuth or tool-calling auth for agents, wants to add authentication to a project but hasn't chosen an approach yet, or needs to install the Scalekit plugin for their AI coding tool (Claude Code, Codex, Copilot CLI, Cursor, or other agents).
Poorgramer-Zack/copilot-cli-things/plugins/mcp-builder/skills/mcp-builder Skill
2★ repoMCP server development: build, create, and test Model Context Protocol servers in TypeScript or Python. Tool design, input/output schemas, Zod/Pydantic validation, evaluations, stdio/HTTP transport, @modelcontextprotocol/sdk, FastMCP.
Poorgramer-Zack/copilot-cli-things/plugins/plugin-dev/skills/agent-development Skill
2★ repoAgent development for Copilot CLI plugins: .agent.md files, agent frontmatter, system prompts, triggering conditions, tool restrictions, model selection. Use when creating, configuring, or debugging autonomous agents.
Poorgramer-Zack/copilot-cli-things/plugins/plugin-dev/skills/hook-development Skill
2★ repoHook development for Copilot CLI plugins: hooks.json, preToolUse/postToolUse/agentStop/sessionStart hooks, command hooks, event-driven validation, tool blocking, policy enforcement. Use when creating or debugging plugin hooks.
Poorgramer-Zack/copilot-cli-things/plugins/plugin-dev/skills/mcp-integration Skill
2★ repoMCP server integration for Copilot CLI plugins: mcp-config.json, stdio/SSE/HTTP/WebSocket servers, OAuth, tool naming. Use when adding external service connections, configuring MCP, or debugging MCP tools.
Poorgramer-Zack/copilot-cli-things/plugins/skill-creator/skills/skill-creator Skill
2★ repoSkill development lifecycle: create, edit, test, benchmark, and optimize SKILL.md files. Evals, assertions, description triggering optimization, variance analysis, iteration loops. Use when creating a skill from scratch, improving an existing skill, running evals, or optimizing a skill description.
harshitsinghbhandari/domain-expansion/skills/llm-council Skill
no license2★ repoConvene an LLM Council for high-stakes decisions requiring multiple perspectives. Use when the user says "council this", "run the council", "get council input", or asks for multi-perspective analysis on strategic decisions like pricing, positioning, pivots, hiring, or any question where being wrong is expensive. Do NOT use for simple factual questions, writing tasks, or summarization.
harshitsinghbhandari/domain-expansion/skills/llm-forge Skill
no license2★ repoRun existing work through 5 specialist craftspeople who each produce an improved version, then peer-review and synthesize the best into a single improved artifact. Use when the user says "forge this", "improve this", "make this better", "level this up", "refine this", or asks for multi-angle improvement on code, copy, strategy, plans, designs, or any artifact where the current version works but could be significantly better. Do NOT use for decisions (use llm-council), simple edits, or creation from scratch.
obielin/responsible-ai-skills/skills/human-oversight-design Skill
2★ repoUse when designing autonomous AI agents, agentic pipelines, or any system that takes actions without direct user instruction for each step. Must be read before writing any agent orchestration code.
lectral/dnd-workshop/.agents/skills/skill-builder Skill
no license2★ repoCreate or revise repository-local Copilot skills for this project. Use when the user wants a new `.agents` skill, a rewrite of an existing skill, or repository-specific guidance on skill structure, scope, activation, and references.
The-AI-Directory-Company/agents-and-skills/skills/code-generation-prompt Skill
2★ repoStep-by-step prompt engineering template for generating production-quality code from requirements — covering input gathering, constraint specification, output formatting, and iterative refinement.
The-AI-Directory-Company/agents-and-skills/skills/code-review-prompt Skill
2★ repoLightweight quick code review template for fast feedback on small changes — covers correctness, safety, and readability in a single pass without full checklist overhead.
The-AI-Directory-Company/agents-and-skills/skills/create-agent-markdown Skill
2★ repoCreate high-quality AI agent definition files that follow the Agent Skills specification. Produces behavioral prompts with real mental models, decision frameworks, and domain expertise — not generic filler.
The-AI-Directory-Company/agents-and-skills/skills/knowledge-base-article Skill
2★ repoWrite self-service knowledge base articles that resolve customer issues without support contact — with clear titles, step-by-step solutions, troubleshooting trees, and SEO-friendly structure.
The-AI-Directory-Company/agents-and-skills/skills/prompt-engineering-guide Skill
2★ repoDesign, test, and optimize LLM prompts systematically — with evaluation frameworks, chain-of-thought patterns, output formatting, and iteration methodology for reliable AI outputs.
pinkpixel-dev/agentskills-mcp/.codex/skills/skill-creator Skill
2★ repoGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
The same file is in 16 other repositories
kevinaimonster/skill-hub/skills/prompt-engineer Skill
no license2★ repo提示词工程师。帮用户写更好的AI提示词,few-shot/chain-of-thought/结构化提示。当用户说「帮我写提示词」「prompt」「提示词优化」「怎么问AI」「prompt engineering」「提示词工程」「写个system prompt」「怎么让AI回答更好」「优化提示词」「AI指令」「few-shot」「chain of thought」时触发。关键词:提示词、prompt、prompt engineering、提示词工程、系统提示、system prompt、few-shot、chain of thought、思维链、结构化提示、角色设定、指令优化、AI提示、GPT提示词、Claude提示词、LLM、大模型、上下文、context、温度、temperature、token、提示模板、提示框架、CRISPE、CO-STAR
teckedd-code2save/ai-build-tools/cli/skills/context7-mcp Skill
2★ repoThis skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
The same file is in 3 other repositories
teckedd-code2save/ai-build-tools/skills/context7-mcp Skill
2★ repoThis skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
The same file is in 3 other repositories
ks6088ts-labs/skills/skills/skill-creator Skill
2★ repo効果的なスキルを作成するためのガイド。このスキルは、ユーザーがAIエージェントの機能を専門知識、ワークフロー、またはツール統合で拡張する新しいスキルを作成(または既存のスキルを更新)したい場合に使用します。
bcastelino/agent-skills-kit/skills/ai-engineer Skill
2★ repoProduction-grade AI engineering for LLM applications, RAG systems, and agent architectures. Use when building AI features, designing model integrations, or implementing AI safety and monitoring.
The same file is in 2 other repositories
bcastelino/agent-skills-kit/skills/ai-ml Skill
2★ repoAI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features. Use when building AI or ML systems.
bcastelino/agent-skills-kit/skills/ai-product Skill
2★ repoAI product engineering covering LLM integration patterns, RAG architecture, prompt engineering, and production AI systems. Use when building AI-powered product features or shipping LLM applications.
bcastelino/agent-skills-kit/skills/crewai Skill
2★ repoExpert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (s...