Context & AI engineering
25,610 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
AravindS-Wick/aravindhan-skills/skills/library/varlock-claude-skill Skill
no license0★ repoSecure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits
The same file is in 2 other repositories
AravindS-Wick/aravindhan-skills/skills/library/vector-database-engineer Skill
no license0★ repoExpert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar
The same file is in 2 other repositories
Workflow orchestration patterns
AravindS-Wick/aravindhan-skills/skills/library/workflow-orchestration-patterns Skill
no license0★ repoMaster workflow orchestration architecture with Temporal, covering fundamental design decisions, resilience patterns, and best practices for building reliable distributed systems.
AravindS-Wick/aravindhan-skills/skills/library/x-twitter-scraper Skill
no license0★ repoX (Twitter) data platform skill — tweet search, user lookup, follower extraction, engagement metrics, giveaway draws, monitoring, webhooks, 19 extraction tools, MCP server.
AravindS-Wick/aravindhan-skills/skills/mcp-builder Skill
no license0★ repoCreate MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.
AravindS-Wick/aravindhan-skills/skills/mcp-integration Skill
no license0★ repoThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
The same file is in 10 other repositories
AravindS-Wick/aravindhan-skills/skills/plan Skill
no license0★ repoPlanning agent for task breakdown and implementation planning. Use via spawn_subagent with skill='plan' when you need to explore a codebase and design an implementation approach before writing code.
AravindS-Wick/aravindhan-skills/skills/research Skill
no license0★ repoFast agent specialized for exploring codebases and searching for code patterns. Use via spawn_subagent with skill='research' for read-only exploration tasks.
AravindS-Wick/aravindhan-skills/skills/skill-creator Skill
no license0★ 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.
AravindS-Wick/aravindhan-skills/skills/subagent-driven-development Skill
no license0★ repoUse when executing implementation plans with independent tasks in the current session
dd3ok/lucid/skills/lucid Skill
0★ repoAudits stale, unsafe, contradictory, or bloated agent-facing context and produces cleanup plans. Use for prompt debt, obsolete agent instructions, memory cleanup, source-of-truth drift, AGENTS.md-style docs, and skill descriptions, 프롬프트 부채, and 컨텍스트 정리. Do not use for ordinary README edits, general code refactors, linting, summarization, or creating a memory bank.
barcelosvinicius/basic-engineering/plugins/be/skills/proc-context-budget Skill
0★ repoUse when the session feels sluggish, output quality drops, after adding several skills/agents/MCP servers, or to decide whether there is room to add more — audits what consumes the context window (agents, skills, MCP tools, rules, CLAUDE.md) and returns prioritized token-savings recommendations.
barcelosvinicius/basic-engineering/plugins/be/skills/proc-skill-creator Skill
0★ repoUse when a needed domain/process/infrastructure skill is missing, when an existing skill needs significant refactoring, or when expanding the base kit. Meta-skill: discovery process, mandatory structure (SKILL.md + resources), naming, quality criteria, and delivery checklist.
barcelosvinicius/basic-engineering/plugins/be/skills/sec-agent-security Skill
0★ repoUse when building or operating an AI agent / LLM feature, when wiring tools or MCP servers, or when an agent will read untrusted content (web, issues, docs, user files) — the threat model and defenses specific to agentic systems: prompt injection, untrusted-content handling, least agency, approval boundaries, and kill switches.
codezelat/codezela-web-skills/skills/deployment-env-handoff Skill
0★ repoUse when preparing or auditing deployment readiness, Vercel, env vars, .env.example, README, AGENTS.md, migrations, live-domain checks, pushed-vs-deployed status, provider setup, no-secrets audits, or launch handoff.
m00kk/agent-skills-playbook/skills/agent-observability Skill
0★ repoAdds tracing, logging, metrics, and cost tracking for LLM agents and LangGraph workflows. Use when debugging agents, LangSmith, OpenTelemetry, production monitoring, or latency/cost optimization.
m00kk/agent-skills-playbook/skills/agent-redteam-security Skill
0★ repoOffensive security testing for AI agents: prompt injection, indirect injection, tool abuse, memory poisoning, and data exfil paths. Use when red teaming agents, MCP servers, or security review of agentic apps.
m00kk/agent-skills-playbook/skills/browser-agent-automation Skill
0★ repoAutomates web tasks with LLM-driven browsers using Playwright, Browser-Use, or Playwright MCP. Use for browser automation agents, scraping with agents, form filling, or E2E flows described in natural language.
m00kk/agent-skills-playbook/skills/build-mcp-server Skill
0★ repoBuilds production Model Context Protocol (MCP) servers in Python (FastMCP) or TypeScript (@modelcontextprotocol/sdk). Use when the user asks to create an MCP server, expose tools/resources to Cursor or Claude, or integrate APIs via MCP.
m00kk/agent-skills-playbook/skills/create-production-skill Skill
0★ repoAuthors production-grade Agent Skills (SKILL.md) per agentskills.io: frontmatter, progressive disclosure, triggers, and validation. Use when creating a new agent skill, writing SKILL.md, or improving skill discovery in Cursor or Claude Code.
m00kk/agent-skills-playbook/skills/deploy-agent-production Skill
0★ repoDeploys AI agents and MCP servers to production: Docker, serverless, streamable HTTP MCP, secrets, and health checks. Use when shipping agents to prod, hosting MCP remotely, or DevOps for agentic systems.
m00kk/agent-skills-playbook/skills/evaluate-agent-quality Skill
0★ repoCreates regression suites and golden-path evaluations for AI agents: task success, tool correctness, citation faithfulness, and safety refusals. Use when testing agents, CI eval gates, or benchmarking prompt or tool changes.
m00kk/agent-skills-playbook/skills/langgraph-multi-agent Skill
0★ repoDesigns and implements stateful LangGraph workflows with checkpoints, human approval, and tool nodes. Use when building LangGraph agents, state graphs, HITL flows, or migrating chains to graph-based orchestration.
m00kk/agent-skills-playbook/skills/multi-agent-supervisor Skill
0★ repoImplements the supervisor pattern: one orchestrator routes tasks to specialist agents (research, code, data). Use for multi-agent systems, delegating subtasks, LangGraph supervisor, or MCP-backed specialist workers.
m00kk/agent-skills-playbook/skills/rag-agent-pipeline Skill
0★ repoBuilds retrieval-augmented agent pipelines: document ingest, chunking, embedding, vector store, and grounded answers with citations. Use for RAG agents, knowledge bases, pgvector, Chroma, or enterprise doc Q&A.
m00kk/agent-skills-playbook/skills/secure-mcp-server Skill
0★ repoHardens MCP servers with OAuth, scoped tools, input validation, and safe defaults. Use when securing MCP, adding authentication, preventing tool abuse, or reviewing MCP security before production.
Focus-GTS/firefly-services-skills/plugins/firefly-services/skills/firefly-video-model Skill
no license0★ repoProduction-grade Claude Code skills for Adobe Firefly Services — credentials, generation (V3 async), custom models, expand/fill, video, Photoshop API, Lightroom API. Built by FocusGTS from real enterprise FDE work.
Blushyes/skills/skills/image-gen/prompt-seat Skill
0★ repoUse when creating, rewriting, auditing, or testing image-generation prompts where visual hierarchy matters. Triggers include prompt engineering for image models, 生图提示词, prompt 排座位, 主位/前排/后排/禁区, NBP-style prompt structure, character posters, character sheets, technical blueprint boards, low-angle posters, and diagnosing why generated images have confused subject/background/atmosphere priority.
skyswordw/skillport/fixtures/claude-only-skill Skill
0★ repoDemonstrates Claude Code-only skill features that do NOT port to Codex or Cursor. Use this fixture to see skillport flag forking, hooks, model/tool overrides, dynamic injection, and argument substitution.
hive-intel/hive-skills/skills/hive-mcp Skill
0★ repoUse this skill when the user wants to install, configure, connect, verify, or debug Hive MCP in an AI client — Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Gemini CLI, the OpenAI Responses API, or Codex CLI — including "add Hive to X", "Hive tools aren't showing up", 401/auth errors, or hosted-vs-stdio questions. If the user has no API key yet, route to hive-build-onboarding; for calling Hive from app code use hive-build.
whiteknightonhorse/aipush-agent-skills/skills/mcp-server-card Skill
0★ repoFree, open, security-verified agent skills for AEO (Answer Engine Optimization) — make any site ready for AI agents. Live: aipush.app
JordanChoo/acfs-agent-skills/casr Skill
no license0★ repoCross Agent Session Resumer. Convert and resume sessions across Claude Code, Codex, Gemini, and other providers.
JordanChoo/acfs-agent-skills/deep-agents-memory Skill
no license0★ repoINVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
The same file is in 4 other repositories
JordanChoo/acfs-agent-skills/deep-agents-orchestration Skill
no license0★ repoINVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
The same file is in 4 other repositories
JordanChoo/acfs-agent-skills/firebase-basics Skill
no license0★ repoBootstrap and product reference for any Firebase project — CLI login, project selection, MCP wiring, and authoritative Firebase product docs (core concepts, CLI, client/admin SDKs, IaC, IAM/security). Use at the start of work on a Firebase repo, when you need to look up a Firebase product concept, or when setting up the Firebase MCP server. For deploy/rules/secrets discipline see `firebase-stack`. For emulator-backed testing see `firebase-emulator-e2e-harness`.
JordanChoo/acfs-agent-skills/langchain-rag Skill
no license0★ repoINVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
The same file is in 4 other repositories
JordanChoo/acfs-agent-skills/shared-skill-authoring Skill
no license0★ repoCreate or update shared skills for both Claude and Codex from the canonical repo at `~/src/acfs-agent-skills`. Use when adding a new skill, editing an existing skill, fixing skill drift, or installing skills across both harnesses without editing `~/.claude/skills` or `~/.codex/skills` directly.
JordanChoo/acfs-agent-skills/ubs Skill
no license0★ repoRun UBS (Ultimate Bug Scanner) on changed files before committing. Use when: pre-commit quality gate, the user mentions "ubs", "bug scan", "security scan", or when AGENTS.md / CLAUDE.md instructs agents to run UBS before committing. Handles scoping, output parsing, false-positive triage, .ubsignore management, and the fix-rerun loop.
MauroProto/mis-skills/external/anthropics-skills/claude-api Skill
0★ repoBuild, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.
The same file is in 1 other repository
MauroProto/mis-skills/external/anthropics-skills/mcp-builder Skill
0★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The same file is in 42 other repositories
MauroProto/mis-skills/external/anthropics-skills/skill-creator Skill
0★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The same file is in 66 other repositories
MauroProto/mis-skills/external/mattpocock-skills/engineering/setup-matt-pocock-skills Skill
0★ repoSets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
The same file is in 15 other repositories
MauroProto/mis-skills/external/mattpocock-skills/misc/git-guardrails-claude-code Skill
0★ repoSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
The same file is in 18 other repositories
MauroProto/mis-skills/external/mattpocock-skills/productivity/handoff Skill
0★ repoCompact the current conversation into a handoff document for another agent to pick up.
The same file is in 13 other repositories
MauroProto/mis-skills/external/mattpocock-skills/productivity/write-a-skill Skill
0★ repoCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
The same file is in 20 other repositories
MauroProto/mis-skills/external/neondatabase-agent-skills/neon-postgres Skill
0★ repoGuides and best practices for working with Neon Serverless Postgres. Covers setup, connection methods, branching, autoscaling, scale-to-zero, read replicas, connection pooling, Neon Auth, and the Neon CLI, MCP server, REST API, TypeScript SDK, and Python SDK. Use when users ask about "Neon setup", "connect to Neon", "Neon project", "DATABASE_URL", "serverless Postgres", "Neon CLI", "neonctl", "Neon MCP", "Neon Auth", "@neondatabase/serverless", "@neondatabase/neon-js", "scale to zero", "Neon autoscaling", "Neon read replica", or "Neon connection pooling".
MauroProto/mis-skills/external/obra-superpowers/dispatching-parallel-agents Skill
0★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 13 other repositories
MauroProto/mis-skills/external/obra-superpowers/subagent-driven-development Skill
0★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 6 other repositories
MauroProto/mis-skills/external/supabase-agent-skills/supabase Skill
0★ repoUse when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).
MauroProto/mis-skills/skills/design-styles/gpt-tasteskill Skill
0★ repoElite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
The same file is in 13 other repositories
SoulChildTc/soulchild-skills/prompt-gen Skill
no license0★ repo生成高质量结构化提示词。当用户说"帮我写个提示词"、"优化这个 prompt"、"生成 prompt"、 "写一个 AI 指令"、"帮我调一下提示词"、"prompt engineering"、"提示词工程"时使用。 也适用于用户描述了一个模糊的 AI 任务想要提炼成可用指令的场景。 如果当前环境是 OpenCode,生成 prompt 后会询问是否创建为 OpenCode Agent。
Mergemat/agent-readiness-skills/skills/scaffold-agent-docs Skill
no license0★ repoCreates minimal agent-readable project docs without importing a large readiness framework. Use when user wants to set up AGENTS.md, CONTEXT.md, docs/agents, build/test/owner/tool-policy docs, or prepare a repo for coding agents.
Mergemat/agent-readiness-skills/skills/write-agent-brief Skill
no license0★ repoWrites a durable implementation brief for an agent without overfitting to current file paths. Use when user wants to turn context, a bug report, PRD, plan, or conversation into an agent-ready issue, task brief, or implementation contract.
hesprs/harness/skills/smart-delegation Skill
0★ repoGuidelines to help you write code smartly by using workers. Only use
shoji9x9/skills/skills/multiagent-setup Skill
0★ repoマルチエージェント環境(Claude Code / Codex / GitHub Copilot)向けのスキル・ルール・Hooks・ドキュメントのセットアップに必ず使用すること。スキルの作成・更新・削除、ルールの追加・管理、Hooksの設定、CLAUDE.md・AGENTS.md・.github/copilot-instructions.mdなどのドキュメントの整備・整理・分割・集約、プロジェクトのマルチエージェント初期化で参照する。加えて、知識・規約・処理を新たに追加する、またはドキュメントを整理・再配置するときに、それを skill / rule / hook / ドキュメントのどれに落とすか(rule なら paths を最小スコープに、ドキュメントなら基底ドキュメントか個別かを選ぶ)を判断する場面でも必ず参照する。
shoji9x9/skills/skills/pr-finalize-loop Skill
0★ reporauleburro/skills/skills/pr-deep-review-agent Skill
no license0★ repoLaunch a clean-context subagent to perform a deep pull request review. Use when the user asks to launch/run/spawn another agent for PR review, final approval review, clean-context code review, or a review that compares code against local documentation and official internet documentation before reporting whether the PR is approved or changes are required.
tyecode/skills/skills/productivity/handoff Skill
0★ repoCompacts the current conversation into a handoff document so another agent can continue the work. Use when handing off to another agent, starting a new session, or passing work context to another developer.
tyecode/skills/skills/productivity/write-a-skill Skill
0★ repoCreates new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Agent assumption register writer
vibesec-advisory/vibesec-advisory-skill-library/SKILLS/agent-boundary-control-review/skills/agent-assumption-register-writer Skill
0★ repoUse when an agent is about to write files, email, message, publish, deploy, submit, update CRM, store memory, call tools, or produce customer-facing work from ambiguous or inferred intent.