Context & AI engineering
25,772 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
anh-chu/llm-wiki-pm/skills/llm-wiki-prd Skill
7★ repoGenerate PRDs, user stories, and release notes grounded in wiki knowledge. Reads entities, concepts, decisions, and customer pages as source material.
anh-chu/llm-wiki-pm/skills/llm-wiki-research Skill
7★ repoResearch sprints, competitive deep dives, and auto-enrichment of stub wiki pages. Delegates web fetching to worker-source-fetcher. Files all findings back into the wiki.
Resonate lovable usage prompt typescript
resonatehq/resonate-skills/resonate-lovable-usage-prompt-typescript Skill
7★ repoSpecialized guidance for building Resonate applications within Lovable.dev, which is Node.js/React/TypeScript. Use when working with Lovable's AI-assisted development environment to scaffold, iterate, and deploy Resonate workflows in the TypeScript SDK.
chrisgagne/grounded-forge/.claude/skills/creating-applications Skill
7★ repoThe single entry point for creating a new application: a compiled distribution built from a corpus subset projected onto a task axis (with optional lenses + practitioner-role agents). Run this when a user says "create an app for X" or similar. The skill first ensures a task spec exists (calling `creating-tasks` internally if one does not, so the user sees a continuous experience rather than a bounce), then scaffolds the distillation directory, distillation index, build profile, CLAUDE.md template, and agent files, then orchestrates per-distillation distillation by calling `creating-distillations` for each applicable source.
lucaperret/agent-skills/skills/mcp-oauth Skill
7★ repoAdd OAuth 2.0 PKCE authentication to a remote MCP server. Use this skill whenever the user wants to add authentication to an MCP server, protect MCP tools with OAuth, implement login flow for an MCP connector, add user auth to an MCP endpoint, or set up token-based access for MCP. Also triggers on: 'MCP OAuth', 'MCP authentication', 'withMcpAuth', 'MCP login flow', 'protect MCP endpoint', 'MCP token auth', 'dynamic client registration MCP', 'Claude connector OAuth'. Even if the user just says 'add auth to my MCP server' or 'my MCP server needs login', use this skill.
lucaperret/agent-skills/skills/mcp-vercel Skill
7★ repoDeploy a remote MCP server on Vercel with Next.js and mcp-handler. Use this skill whenever the user wants to create an MCP server, deploy MCP to Vercel, set up a remote MCP endpoint, add MCP tools to a Next.js app, or host an MCP server in the cloud. Also triggers on: 'deploy MCP', 'remote MCP', 'MCP endpoint', 'mcp-handler', 'MCP on Vercel', 'Streamable HTTP MCP', 'Claude connector backend', 'host MCP server for Claude Desktop'. Even if the user just says 'I want to make my API available to Claude' or 'set up an MCP server', use this skill.
WolframResearch/system-modeler-ai-toolkit/wolfram-language-modelica Skill
7★ repoSimulate and analyze Modelica models from within Wolfram Language / a notebook (WSM SystemModel* functions, WSMRealTimeSimulate) — extract numerical results and make custom plots. Use this skill whenever the user wants to work with a Modelica model inside WL / a notebook — running parameter sweeps, pulling time series into Wolfram arrays for analysis (e.g. AnomalyDetection, Predict, Classify, SystemModelCalibrate), validating against requirements (SystemModelValidate, Monte Carlo, uncertainty bands), training surrogates, making custom plots, or driving a live simulation interactively (pause/resume, change inputs or parameters mid-run, agent/LLM-in-the-loop). Triggers on phrases like 'simulate this model in WL', 'get the results into Wolfram Language', 'extract a time series', 'SystemModelSimulate', 'SystemModelPlot', 'sweep a parameter', 'validate against requirements', 'stays within limits', 'show me any violations', 'SystemModelValidate', 'failure plot', 'uncertainty plot', 'train a surrogate', 'real-time simulation', 'interactive simulation', 'change inputs while it runs', 'WSMRealTimeSimulate'.
truongpx396/learn-harness-engineering-by-building-mini-claude-code/skills/mcp-builder Skill
7★ repoBuild MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.
The same file is in 1 other repository
feyninc/skills/skills/mandex Skill
7★ repoUse Mandex (mx) to search and manage offline documentation packages for AI agents. Covers pulling docs from CDN, full-text search with BM25 + optional ONNX semantic reranking, building custom .mandex packages from markdown, project-level dependency sync, and multi-agent integration (Claude Code, Cursor, Codex). Use when: looking up library documentation offline, building searchable doc packages, setting up documentation for coding agents, or searching across project dependencies.
TheBlueHouse75/hermes-action-bridge/io.github.TheBlueHouse75/hermes-action-bridge MCP server
7★ repoDelegate real-world actions from Claude Code, Codex, and other agents to Hermes Agent.
martin1847/evolab/skills/cto-orchestration Skill
6★ repoCTO/orchestrator 模式管理多 agent 软件交付:agentctl 统一派工(一条 duplex lane、三引擎原生协议,轮内 steer)、goal 合同驱动、typed watcher、异构评审、真路径验收与主理人减负。适用于用户要求'你做 CTO/编排者'、'派 omp/codex 去做'、'goal 模式派发'、管理多会话开发或把这套工作流接入新项目。新项目先用 repo-governance-bootstrap 建治理骨架。不要用于单 agent 小任务、无需评审循环的局部改动或纯文档初始化。
martin1847/evolab/skills/observability-standard Skill
6★ repo生产级可观测性与工程规范,适用于**所有后端服务** —— 普通微服务(auth / 网关 / 业务服务)与 agent / 多 agent / RAG 知识库项目通用。核心:用 trace_id 串 trace/log + 业务 id 反查 db、结构化日志、OpenTelemetry 埋点、跨进程 W3C traceparent 传播、日志级别纪律、边界类型纪律(含 id 持久化:不往业务行塞 trace_id);agent / RAG 场景在此基线上加 LLM / 工具 / 检索埋点与 GenAI 语义约定。Use this skill whenever writing or reviewing backend code that involves logging setup, OpenTelemetry tracing, structured logs, cross-process context propagation, choosing log levels (INFO vs DEBUG), correlating logs / traces / db to debug, defining types for boundary or inter-service data — and additionally agent orchestration / sub-agents, LLM / tool / retrieval calls, or GenAI semantic conventions. 适用 Python / Go / Java / Rust。Apply it even when the user only says things like "加点日志" "接一下 trace / instrument this" "set up observability" "这个错误怎么查不到" "这个请求怎么追踪",不限于显式提到规范时。目标:trace_id 串 trace/log、业务 id 反查 db,让线上问题最快定位。
martin1847/evolab/skills/orchestrator-core Skill
6★ repo多智能体编排的领域无关内核(A² Supervisor 层的方法论抽象)。把编排者的操作系统从领域里剥出来:萃取式主上下文 + 按『要不要主上下文』切分派工 + 契约化派发 + 分层合并 + 对抗式异构验证 + 降认知负载。领域皮(CTO 写码 / 总编内容 / 未来任意领域)只贴一张薄角色表 + 完成定义,内核整套复用。适用于用户要求抽象编排模式、造新领域编排者、或问『多智能体架构怎么搭』。不要用于:单 agent 一次性小任务(无需内核)、纯文档初始化(用 repo-governance-bootstrap)。派工/评审/状态落盘的领域实现见各皮 skill(cto-orchestration / yangge-ops)。
martin1847/evolab/skills/repo-governance-bootstrap Skill
6★ repo一次性初始化适合 AI 协作开发的轻量工程治理骨架(docs/INDEX、ADR、module、roadmap、ACTIVE_CONTEXT、AGENTS.md / CLAUDE.md)。新仓库 / 文档结构混乱 / 项目内文档治理初始化时调用。【定位】独立可用、不需要多 agent 编排;也是 cto-orchestration 新项目接入的第一步,但小项目只做文档治理时单独用即可。一次性建结构,区别于循环跑的 cto-orchestration。
Manzanita-Research/brand/org/skills/generate-hero-prompt Skill
no license6★ repoGenerate image prompts for Manzanita Research hero images. Reads the current repo to infer what the project is, then writes prompts you can paste into Flora or any text-to-image tool. Eco-futurist, feminine, 1980s-meets-2180s California.
victorgrein/spec-crew/templates/shared/skills/orchestration-governance Skill
no license6★ repoGovernance skill for orchestrating CrewAI specialists with strict ownership, skill boundaries, and execution permissions.
ozzaii/codex-claude-loop/plugin/skills/prompt Skill
6★ repoSend an additional request to the exact Codex session for an implemented codex-claude-loop lane, sequenced behind its writer lock
Mintii-Labs/ozor-skills/skills/ozor-prompt-optimizer Skill
6★ repoAnalyze and improve existing Ozor.ai video prompts for better output quality. Use this skill whenever the user has an Ozor prompt that produced mediocre results, wants to improve a video prompt, needs help debugging why a video didn't turn out well, or wants expert feedback on their prompt before running it. Trigger on phrases like 'improve this prompt', 'optimize my Ozor prompt', 'why did my video look bad', 'fix this prompt', 'make this prompt better', 'review my Ozor prompt', 'the video didn't turn out right', 'prompt feedback', 'better results from Ozor', or any request to refine, debug, or enhance an existing Ozor video prompt.
rfxlamia/pocketto/skills/pocket-correction Skill
6★ repoUser-triggered correction stage between a pocket-review REVIEW_FAIL verdict and re-review. Delegates each failed task's fix to an implementer subagent (main agent stays Delegator + Auditor only — never writes code), records an append-only correction commit per task via the pocketto-pi CLI (done_sha never moves), and hands back for user-triggered re-review. Trigger on "pocket-correction", "apply review fixes", "fix the review failures", "correct the failed tasks", or when pocket-review reports REVIEW_FAIL in agent-managed execution.
rfxlamia/pocketto/skills/pocket-development Skill
6★ repoUse when executing multi-task implementation plans. Trigger on execute plan, delegate tasks, dispatch subagents. Combines delegate handoff discipline with prompt-engineering attention mechanics.
rfxlamia/pocketto/skills/pocket-init Skill
6★ repoOnboards an existing (brownfield) project onto Pocket. Scans the codebase and writes a project memory file (CLAUDE.md or AGENTS.md), optionally enables Pocket Enterprise (mode init) and scaffolds GitHub issue/PR templates. Trigger on "pocket-init", "set up pocket", "onboard this project", "generate CLAUDE.md", "enable enterprise mode".
konglong87/methodology-skills/skills/prompt-enhancer Skill
6★ repoMUST use before task execution. Clarify vague requirements, explore solutions, and ensure full understanding.
sheikh-mohammad/agent-factory-claude-skills/.claude/skills/skill-creator-pro Skill
no license6★ repoCreates production-grade, reusable skills that extend Claude's capabilities. This skill should be used when users want to create a new skill, improve an existing skill, or build domain-specific intelligence. Gathers context from codebase, conversation, and authentic sources before creating adaptable skills.
sheikh-mohammad/agent-factory-claude-skills/.claude/skills/skill-creator Skill
no license6★ 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 19 other repositories
vignesh2027/Claude-Agentic-Skills2.0-version/agentOS-orchestrator Skill
6★ repoTransforms Claude into AgentOS — an intelligent multi-agent AI operating system that automatically identifies which specialist agent is needed for a task, decomposes work into sub-tasks, routes each to the right agent, executes with full domain depth, and synthesizes outputs into one unified response. Use this skill when you want Claude to behave as an orchestrated AI workforce rather than a single generalist assistant. Covers finance, engineering, data, operations, legal, product, marketing, and research.
vignesh2027/Claude-Agentic-Skills2.0-version/agentic-workflow-builder Skill
6★ repoActivates AgenticWorkflowBuilder for designing end-to-end agentic systems and AI-powered automation workflows. Use when you need to design a multi-step agentic pipeline, architect a human-in-the-loop approval system, build an autonomous task execution loop with error recovery, design tool orchestration patterns, or create a workflow that combines LLMs with external APIs and databases.
vignesh2027/Claude-Agentic-Skills2.0-version/claude-mythos Skill
6★ repoActivates ClaudeMythos — Claude's highest form: a legendary meta-intelligence that operates beyond conventional assistant mode. Use when you need mythic-scale creative work, cross-domain synthesis that no single expert could produce, epic world-building and lore creation, philosophical reasoning at civilization scale, the design of legendary AI systems and personas, or when you want Claude to write its own mythology, craft ultimate system prompts, or reason about intelligence itself. This is AgentOS's apex skill — Claude unchained.
vignesh2027/Claude-Agentic-Skills2.0-version/data-governance-agent Skill
6★ repoActivates DataGovernanceAgent for enterprise data governance strategy and implementation. Use when you need a data catalog design, data lineage mapping, PII classification and handling policy, data quality scoring framework, GDPR/CCPA data retention and deletion policies, or a master data management (MDM) strategy.
vignesh2027/Claude-Agentic-Skills2.0-version/finance-oracle Skill
6★ repoActivates FinanceOracle — the most comprehensive institutional finance intelligence agent ever built for Claude. Use when you need Goldman Sachs + Bridgewater + Citadel-level analysis: Black-Scholes options pricing, Black-Litterman portfolio construction, fixed income duration/ convexity, hedge fund strategy design, family office management, derivatives structuring, sovereign wealth allocation, tax-optimized investing, or full multi-asset class research. This is the apex finance skill — deeper than any other financial agent in existence.
vignesh2027/Claude-Agentic-Skills2.0-version/mcp-builder Skill
6★ repoActivates MCPBuilder for designing and building Model Context Protocol (MCP) servers and tools for Claude. Use when you need to create a new MCP server that exposes tools to Claude, design tool schemas for MCP, implement MCP server in Python or TypeScript, debug MCP connection issues, or plan which capabilities to expose as MCP tools vs. resources vs. prompts.
vignesh2027/Claude-Agentic-Skills2.0-version/prompt-engineer Skill
6★ repoActivates PromptEngineer for system prompt design, prompt optimization, and LLM evaluation. Use when you need to design a system prompt for a Claude-based application, optimize prompts for accuracy and consistency, implement chain-of-thought reasoning, build evaluation frameworks (evals) to measure prompt quality, or prevent prompt injection and jailbreaks.
vignesh2027/Claude-Agentic-Skills2.0-version/rag-architect Skill
6★ repoActivates the RAG-Architect agent for designing and building Retrieval-Augmented Generation systems. Use this skill when you need to build a document Q&A system, design a knowledge base with semantic search, set up vector stores (Chroma, Pinecone, pgvector), implement hybrid retrieval (dense + BM25 sparse), add re-ranking, or generate grounded answers with source citations and hallucination detection. Outputs complete Python code for the full RAG pipeline.
vignesh2027/Claude-Agentic-Skills2.0-version/realtime-data-agent Skill
6★ repoActivates RealtimeDataAgent for streaming data and event-driven architecture. Use when you need Kafka or Kinesis topic design with partition strategy, Flink or Spark Streaming transformation logic, WebSocket server implementation for real-time clients, real-time threshold monitoring and alerting pipelines, or end-to-end latency analysis and optimization.
vignesh2027/Claude-Agentic-Skills2.0-version/voice-agent-builder Skill
6★ repoActivates VoiceAgent — a specialized engineer for designing and building voice AI agents. Use when you need to build speech-to-text pipelines, text-to-speech integrations, real-time voice assistants, telephony bots (Twilio/Vapi), or wake-word detection systems with low-latency streaming and interruption handling.
Minara-AI/media-agent/skills/media Skill
6★ repoMaster orchestrator for the media-agent workflow. Guides the user through the full content creation pipeline: ideation, writing, image generation, and multi-platform publishing. Can resume from any stage by reading the content manifest. This is a thin sequencer — sub-skills contain the canonical implementation logic.
yeaight7/agent-powerups/plugins/agentic-systems/skills/agent-harness-design Skill
6★ repoUse when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous tool invocations, or silent failures, or an existing agent harness needs a quality review.
yeaight7/agent-powerups/plugins/agentic-systems/skills/model-routing Skill
6★ repoUse when selecting a model for a new task or subagent, deciding whether to escalate after a failed attempt, or designing a multi-agent pipeline with mixed task complexity.
yeaight7/agent-powerups/plugins/codebase-intelligence/skills/local-rag-mcp Skill
6★ repoUse when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.
yeaight7/agent-powerups/plugins/codebase-intelligence/skills/structured-code-search-mcp Skill
6★ repoUse when designing or using MCP-backed structured code search with search, AST query, symbol inventory, and bounded extraction workflows.
yeaight7/agent-powerups/plugins/dev-vitals/skills/agent-harness-design Skill
6★ repoUse when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous tool invocations, or silent failures, or an existing agent harness needs a quality review.
yeaight7/agent-powerups/plugins/dev-vitals/skills/agent-runtime-patterns Skill
6★ repoUse when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.
yeaight7/agent-powerups/plugins/dev-vitals/skills/agent-session-forensics Skill
6★ repoUse when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.
yeaight7/agent-powerups/plugins/dev-vitals/skills/dispatching-parallel-agents Skill
6★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
yeaight7/agent-powerups/plugins/dev-vitals/skills/handoff-discipline Skill
6★ repoUse when ending a session, handing a task back to the user, or approaching the context limit with work unfinished -- the next session or engineer must be able to resume the work instantly.
yeaight7/agent-powerups/plugins/dev-vitals/skills/strategic-context-compaction Skill
6★ repoUse when deciding whether to compact agent context -- the window is filling up, you are about to switch from one phase to another (research, planning, implementation, debugging), a failed approach left dead-end reasoning, or a previous mid-task compaction lost critical state.
yeaight7/agent-powerups/plugins/documentation-systems/skills/agent-readable-docs Skill
6★ repoUse when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or optimizing documentation for token-efficient AI consumption.
yeaight7/agent-powerups/plugins/documentation-systems/skills/handoff-discipline Skill
6★ repoUse when ending a session, handing a task back to the user, or approaching the context limit with work unfinished -- the next session or engineer must be able to resume the work instantly.
yeaight7/agent-powerups/plugins/mcp-development/skills/mcp-server-builder Skill
6★ repoDesign high-quality MCP servers around workflows, narrow schemas, context-aware outputs, and actionable errors. Use when building or reviewing MCP tools for real agent tasks.
yeaight7/agent-powerups/plugins/memory-optimization/skills/memory-build-workflow Skill
6★ repoUse when a user needs to build or refresh persistent graph memory from a mixed corpus and the right path may include graphify, incremental update, or helper conversion before ingestion.
yeaight7/agent-powerups/plugins/memory-optimization/skills/memory-optimization-workflow Skill
6★ repoUse when deciding the lowest-cost context path for a mixed corpus, especially when choosing among direct reading, helper conversion, graph build, graph update, or graph query.
yeaight7/agent-powerups/plugins/memory-optimization/skills/memory-query-workflow Skill
6★ repoUse when a graph already exists and the user needs retrieval, tracing, explanation, or gap detection from graph memory before reopening the full corpus.
yeaight7/agent-powerups/plugins/quality-gates/skills/prompt-evaluation-runner Skill
6★ repoUse when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
yeaight7/agent-powerups/plugins/quality-gates/skills/red-team-eval-authoring Skill
6★ repoUse when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.
yeaight7/agent-powerups/plugins/security-guardrails/skills/agent-config-security-audit Skill
6★ repoUse when modifying agent config files, committing configuration changes, onboarding a repository with existing agent configs, or running a periodic config hygiene check.
yeaight7/agent-powerups/plugins/security-guardrails/skills/filesystem-mcp-guardrails Skill
6★ repoUse when designing or reviewing filesystem MCP access, path boundaries, allowed roots, method allowlists, and safe local file operations.
yeaight7/agent-powerups/plugins/security-guardrails/skills/hook-safety-review Skill
6★ repoUse when a hook is about to be enabled or modified -- a hook recipe proposed for activation, a pre/post-tool or lifecycle hook added to agent settings, a git pre-commit hook added to a repo, or a third-party hook snippet pasted in from outside.
yeaight7/agent-powerups/plugins/security-guardrails/skills/mcp-risk-review Skill
6★ repoUse when an MCP server is about to be enabled, added to agent config, or upgraded -- a staged server config is a candidate for activation, a third-party server is proposed from a registry, or an existing entry changes transport, credentials, or tool surface.
yeaight7/agent-powerups/plugins/security-guardrails/skills/red-team-eval-authoring Skill
6★ repoUse when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.
yeaight7/agent-powerups/plugins/skill-authoring/skills/skill-authoring-guide Skill
6★ repoCreate or refactor high-quality skills with lean frontmatter, progressive disclosure, and optional bundled helpers. Use when authoring reusable agent workflows.
yeaight7/agent-powerups/plugins/software-engineering/skills/subagent-team-orchestration Skill
6★ repoUse when a task is too large or too mixed for one agent -- it splits into research, planning, implementation, review, and verification stages, needs different specialties, or has parallelizable branches that still share dependencies.