Context & AI engineering
25,815 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
gaia-react/gaia/.claude/skills/new-hook Skill
27★ repoScaffold a new custom React hook with a Vitest test file. Use this skill whenever the user asks to "create a hook", "make a useFoo hook", "scaffold a custom React hook", "add a hook under app/hooks", or describes a piece of reusable React state/effect logic that warrants extraction into a named `use*` hook.
heymegabyte/claude-skills/04-preference-and-memory Skill
no license27★ repoCaptures and evolves user preferences with confidence levels. Maintains Voice of the Customer model with exact language, dissatisfaction and aspiration signals. Handles promotion/demotion, global vs project scoping, auto memory system, and Omi wearable data integration.
heymegabyte/claude-skills/12-media-orchestration Skill
no license27★ repoSection-by-section media planning and generation. Image generation (GPT Image 1.5 primary, built-in fallback), logo/icon generation (Ideogram v3 → favicon set), video generation (Sora), social preview images (OG 1200x630 + AI search optimization), stock photo curation (Pexels, Pixabay), critique/remix loops (max 3 rounds), asset compression pipeline, and media performance budgets.
heymegabyte/claude-skills/15-site-generation Skill
no license27★ repoEnd-to-end AI website generation pipeline. Claude Opus 4.8 emits Bolt-style <boltArtifact> envelopes (multi-file, plan-first) that customize Vite+React+Tailwind templates from pre-researched business data. Pre-research via APIs, media acquisition, brand extraction, visual inspection via GPT Image 2 vision, R2 upload (per-file content-type by extension), D1 status updates. Supports all business types: SaaS, portfolio, non-profit, restaurant, salon, medical, legal, retail, tech.
heymegabyte/claude-skills/19-mcp-authoring Skill
no license27★ repoWhen to author an MCP server, architecture overview (tools/resources/prompts), stdio vs HTTP+SSE transport tradeoffs, registration in .claude.json. Sub-modules: stdio-server-template.md (full TS code), http-server-on-workers.md (Hono + SSE on CF Workers), forge-mcp-from-openapi.md (extend forge script with --target=mcp-server). Fires when user asks to 'build an MCP server', 'expose X as an MCP tool', or 'add MCP to my Worker'.
heymegabyte/claude-skills/20-superpowers/subagent-driven-development Skill
no license27★ repoUse when executing implementation plans with independent tasks in the current session
yha9806/academic-writing-toolkit/.claude/skills/human-eval-handoff-repair Skill
27★ repoUse when validating, repairing, or mapping human-evaluation handoff packages, filled annotation CSVs, rebuttal annotation UIs, or reviewer annotation returns across package versions. Applies to checking row alignment, detecting cross-snapshot contamination, converting old labels to current schemas, generating refill/import CSVs, and deciding whether filled annotations are safe for formal aggregation.
yha9806/academic-writing-toolkit/plugins/academic-writing-toolkit/skills/human-eval-handoff-repair Skill
27★ repoUse when validating, repairing, or mapping human-evaluation handoff packages, filled annotation CSVs, rebuttal annotation UIs, or reviewer annotation returns across package versions. Applies to checking row alignment, detecting cross-snapshot contamination, converting old labels to current schemas, generating refill/import CSVs, and deciding whether filled annotations are safe for formal aggregation.
wonsukchoi/domain-experts/roles/advertising-sales-agent Skill
27★ repoUse when a task needs the judgment of an Advertising Sales Agent — pricing an ad-inventory package against a client budget, building a media-kit pitch, protecting yield on scarce inventory while moving remnant, or forecasting close rate on a sales pipeline. Sell-side: this role sells a publisher's or station's own ad space/time to advertisers, the opposite side of the table from a buyer-side advertising-promotions-manager who purchases media on a client's behalf.
wonsukchoi/domain-experts/roles/cargo-freight-agent Skill
27★ repoUse when a task needs the judgment of a cargo/freight agent — quoting a shipment across air/ocean/ground modes, calculating dimensional weight vs actual weight for billing, classifying freight by NMFC density class, preparing bill-of-lading/customs documentation, or processing a cargo-damage claim.
wonsukchoi/domain-experts/roles/insurance-sales-agent Skill
27★ repoUse when a task needs the judgment of an Insurance Sales Agent — running a life-insurance needs analysis, comparing coverage across carriers for a client, structuring a policy recommendation around a premium budget, handling a price-vs-coverage objection, or explaining a commission/renewal structure to a client asking why a quote changed at renewal.
wonsukchoi/domain-experts/roles/purchasing-agent Skill
27★ repoUse when a task needs the judgment of a Purchasing Agent — cutting a purchase order against the correct procurement method, running an RFQ/RFP and scoring the quotes, applying dollar-threshold rules (micro-purchase, simplified acquisition, sole-source) to a specific buy, reconciling a three-way match discrepancy between PO/receipt/invoice, or catching split-purchase and maverick-spend patterns before they become audit findings.
wonsukchoi/domain-experts/roles/real-estate-agent Skill
27★ repoUse when a task needs the judgment of a Real Estate Sales Agent — building a lead-generation and follow-up plan, running a listing presentation and handling a seller's price objection, structuring buyer representation and offer strategy under a supervising broker, or working commission-split and cap economics.
Reservation transportation ticket agent
wonsukchoi/domain-experts/roles/reservation-transportation-ticket-agent Skill
27★ repoUse when a task needs the judgment of a reservation and transportation ticket agent — rebooking passengers during an irregular-operations (IROP) event, calculating denied-boarding compensation for an oversold flight, interpreting a single carrier's fare-class change/cancellation rules, or triaging a day-of-travel standby list.
wonsukchoi/domain-experts/roles/securities-sales-agent Skill
27★ repoUse when a task needs the judgment of a securities/financial-services sales agent — comparing mutual-fund share classes for a client's holding period, structuring a commission-vs-fee disclosure, building a prospecting/book-of-business growth plan, evaluating an annuity recommendation under Reg BI, or drafting a suitability file.
wonsukchoi/domain-experts/roles/talent-agent Skill
27★ repoUse when a task needs the judgment of a talent agent or business manager for artists, performers, or athletes — negotiating a representation or performance contract, structuring commission on a deal, checking whether a procurement act crosses into licensed-agent territory, tracking a contract's termination/renewal clock, or flagging a conflict-of-interest in how the agency gets paid.
wonsukchoi/domain-experts/roles/tax-revenue-agent Skill
27★ repoUse when a task needs the judgment of a Tax Examiner or Revenue Agent — determining which statute of limitations applies to an audit (3-year, 6-year, or unlimited), reconstructing unreported income via a bank deposit or similar indirect method, applying the Cohan rule to estimate a substantiated-but-undocumented deduction, distinguishing an accuracy-related penalty from civil fraud based on badges of fraud, or verifying collection due process notice requirements before a lien or levy.
wonsukchoi/domain-experts/roles/travel-agent Skill
27★ repoUse when a task needs the judgment of a travel agent — constructing a multi-leg itinerary against layover/visa/timing constraints, pricing a trip across supplier commission structures, comparing travel-insurance/cancellation-policy tradeoffs, or interpreting GDS fare rules and change penalties.
mjunaidca/mjs-agent-skills/.claude/skills/building-chatgpt-apps Skill
no license27★ repoGuides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).
mjunaidca/mjs-agent-skills/.claude/skills/building-mcp-servers Skill
no license27★ repoGuides creation of 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). Covers tool design, authentication, Docker deployment, and evaluation creation. NOT when consuming existing MCP servers (use the server directly).
mjunaidca/mjs-agent-skills/.claude/skills/building-rag-systems Skill
no license27★ repoBuild production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing document ingestion pipelines, vector search with Qdrant, or context-aware retrieval. Covers chunking strategies, change detection, payload indexing, and context expansion. NOT when doing simple similarity search without production requirements.
mjunaidca/mjs-agent-skills/.claude/skills/evaluation Skill
no license27★ repoBuild evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
mjunaidca/mjs-agent-skills/.claude/skills/local-llm-claude-code Skill
no license27★ repoSet up a FREE local LLM (via Ollama) and connect Claude Code to it so it runs offline with no API costs. Use this whenever the user wants to run Claude Code on a local/self-hosted model, use Ollama/Qwen/Llama/Mistral/DeepSeek with Claude Code, get a "free" or "offline" coding agent, avoid Anthropic API costs, point ANTHROPIC_BASE_URL at localhost, or asks "can my machine/VPS run a local LLM for Claude Code". Trigger even if they only say "run Claude Code locally", "local model for coding", "self-hosted Claude Code", or name a local model (qwen3, llama3, deepseek-coder). Handles install, model tuning, wiring, and an honest hardware reality-check (a capable model AND fast hardware are BOTH required).
mjunaidca/mjs-agent-skills/.claude/skills/memory-systems Skill
no license27★ repoDesign and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
mjunaidca/mjs-agent-skills/.claude/skills/multi-agent-patterns Skill
no license27★ repoDesign multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
mjunaidca/mjs-agent-skills/.claude/skills/researching-with-deepwiki Skill
no license27★ repoResearch GitHub, GitLab, and Bitbucket repositories using DeepWiki MCP server. Use when exploring unfamiliar codebases, understanding project architecture, or asking questions about how a specific open-source project works. Provides AI-powered repo analysis and RAG-based Q&A about source code. NOT for fetching library API docs (use fetching-library-docs instead) or local files.
mjunaidca/mjs-agent-skills/.claude/skills/scaffolding-openai-agents Skill
no license27★ repoBuilds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming responses. NOT when using raw OpenAI API without SDK or other agent frameworks like LangChain.
mjunaidca/mjs-agent-skills/.claude/skills/streaming-llm-responses Skill
no license27★ repoImplement real-time streaming UI patterns for AI chat applications. Use when adding response lifecycle handlers, progress indicators, client effects, or thread state synchronization. Covers onResponseStart/End, onEffect, ProgressUpdateEvent, and client tools. NOT when building basic chat without real-time feedback.
mjunaidca/mjs-agent-skills/docs/taskflow-vault/skills/engineering/blueprint-skill-creator Skill
no license27★ repoCreates blueprint-driven skills for infrastructure and deployment tasks. This skill should be used when creating new skills that require templates, patterns, or reference configurations (e.g., Dockerfiles, Helm charts, Kubernetes manifests, CI/CD pipelines). It enforces impact analysis before containerization, identifies environment requirements, network topology changes, and auth/CORS implications. Use this skill when building deployment-related skills or when containerizing applications.
mjunaidca/mjs-agent-skills/docs/taskflow-vault/skills/engineering/mcp-builder Skill
no license27★ 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).
mjunaidca/mjs-agent-skills/docs/taskflow-vault/skills/engineering/skill-creator Skill
no license27★ 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.
eldermoraes/quarkus-agentic-scaffolding/skills/setup-agentic-scaffolding Skill
26★ repoSet up the prerequisites for the Quarkus + LangChain4j agentic stack in the coding agent you are running — detect and (with approval) install the toolchain, register the Quarkus Agents MCP and context7 MCP servers, and write the conventions file into your project. User-invoked only, via /setup-agentic-scaffolding; it prepares the environment the /scaffold-project and /audit-project skills depend on.
BlueprintOS/analysis-to-delivery/skills/user-invoked/handoff Skill
26★ repo代码交接文档 — 整理本项目已完成的全部设计文档、待办事项、已知风险、后续工作建议。设计阶段收尾、向实施团队或编码 skill 正式交接时调用本 skill 生成 HANDOVER.md。
whystrohm/shotkit/skills/visual-prompt-forge Skill
26★ repoGenerate model-specific prompts from shots.json. Outputs copy-paste-ready prompts for stills (Midjourney, Flux, Ideogram, GPT Image, Nano Banana, Seedream) and motion video (Kling, Veo, Seedance, Hailuo). Also runs a revision mode that reads a critique.json and re-emits prompts for only the failed shots, closing the QA loop. Use when the user asks for image or video prompts, mentions any of those generators, wants AI-generated frames for a storyboard, or hands over shots.json. The prompt half of the pipeline. Composes with storyboard-architect upstream, visual-asset-critic downstream.
Fearvox/multica-ultimate-workbench/skills/workbench-flue-agent-harness Skill
no license26★ repoDeployable Flue agent harness lane for HTTP, CI, Node, Cloudflare, and sandbox-backed agents.
Fearvox/multica-ultimate-workbench/skills/workbench-hermes-docs-sync Skill
no license26★ repoUse when Hermes reviews Claude-authored writeups, public docs, skill changes, README/agent/issue-template changes, or upstream speed-match documentation before syncing or publishing.
Fearvox/multica-ultimate-workbench/skills/workbench-memory-synthesis Skill
no license26★ repoDurable memory, session summaries, decision logs, issue closeout synthesis, and compact handoffs.
byerlikaya/claude-starter-kit/claude-starter/skills/eval-grader Skill
26★ repoEnterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.
byerlikaya/claude-starter-kit/claude-starter/skills/handoff Skill
26★ repoEnterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.
byerlikaya/claude-starter-kit/claude-starter/skills/mcp-builder Skill
26★ repoEnterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.
byerlikaya/claude-starter-kit/claude-starter/skills/red-team Skill
26★ repoAttacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies whether the defense actually holds. Trigger phrases: "red team", "red-team", "test prompt injection", "jailbreak", "defense test", "adversarial test", "injection scenario"
byerlikaya/claude-starter-kit/claude-starter/skills/worktree Skill
26★ repoEnterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.
byerlikaya/claude-starter-kit/plugin/skills/eval-grader Skill
26★ repoMeasure output quality, don't vibe it: score a generative task with a two-layer grader — deterministic code metrics + per-dimension LLM-as-judge — over a fixed task set, as signed deltas vs a pinned baseline. Grades cost alongside correctness (pass-slow). Trigger phrases: "eval", "grader", "measure output quality", "LLM-as-judge", "score the output"
byerlikaya/claude-starter-kit/plugin/skills/handoff Skill
26★ repoSession handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSION_STATE.md, then recommend /clear. Trigger phrases: "handoff", "hand off", "session summary", "session state", "clear context", "I'll continue"
byerlikaya/claude-starter-kit/plugin/skills/mcp-builder Skill
26★ repoBuild a Model Context Protocol (MCP) server so an AI client can call your tools/resources: design tool schemas, pick a transport, handle errors, and test it. For exposing an API, database, or service to Claude and other clients. Trigger phrases: "MCP server", "build an MCP", "model context protocol", "expose tools to Claude", "MCP tool"
byerlikaya/claude-starter-kit/plugin/skills/red-team Skill
26★ repoAttacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies whether the defense actually holds. Trigger phrases: "red team", "red-team", "test prompt injection", "jailbreak", "defense test", "adversarial test", "injection scenario"
byerlikaya/claude-starter-kit/plugin/skills/worktree Skill
26★ repoIsolate risky or parallel file-mutating work in a git worktree so the main tree's uncommitted changes are never clobbered. For fan-out agents that edit files, throwaway experiments, or any change you may want to discard cleanly. Trigger phrases: "worktree", "git worktree", "isolate the changes", "sandbox this work", "parallel file edits"
upex-galaxy/agentic-qa-boilerplate/.claude/skills/agentic-qa-onboard Skill
26★ repoWalks new users through this repo's QA flow — Playwright + KATA + Allure + Xray stack, Jira QA workflow (Backlog → Shift-Left QA → Estimation → Ready For Dev → Ready For QA → In Testing → Tested → Closed), /shift-left-testing for pre-sprint AC refinement on backlog Stories, /sprint-testing for in-sprint manual QA, /test-documentation for TMS test cases, /test-automation for KATA-compliant E2E/API tests, /regression-testing for CI suite execution, /framework-development for boilerplate evolution, MCPs available (Context7, Tavily, Atlassian, Playwright, DBHub, OpenAPI, Postman), critical env vars. ALSO the front desk for anyone who is lost or wants to understand how the repo or any workflow skill works — conceptually AND visually: it explains in plain human language (suspending caveman/compressed register) and can open per-skill how-it-works presentations (Spanish, technical terms in English) in the user's default browser after asking. Triggers on: `onboard me to QA`, `explain this QA repo`, `first time using this`, `primer vez en QA`, `/agentic-qa-onboard`, `I don't know how to use this`, `how does sprint-testing / test-automation work`, `how does this skill work`, `show me how it works`, `teach me how QA works here`, `walk me through this skill`, `no sé cómo usar esto`, `no entiendo cómo funciona el repo`, `cómo funciona este skill`, `explícame cómo funciona`, `enséñame cómo se hace`. Do NOT use for: pre-sprint refinement (use /shift-left-testing), feature QA on a ticket (use /sprint-testing), authoring test cases in TMS (use /test-documentation), writing automated tests (use /test-automation), running regression suites (use /regression-testing).
Dataslayer-AI/Marketing-skills/skills/ds-eval Skill
26★ repoInternal development tool that tests whether skill descriptions trigger correctly for different user inputs. Reads test cases from a YAML file and evaluates each one by matching the input against all skill descriptions. Use when the user says "run triggering eval", "test skill descriptions", "check triggering accuracy", "eval skills", or after editing a skill description to verify it still triggers correctly.
Dataslayer-AI/Marketing-skills/skills/ds-lint Skill
26★ repoInternal development tool that validates all SKILL.md and agent .md files against the Claude Code spec. Checks frontmatter completeness, field validity, allowed-tools presence, line count, hardcoded paths, and description quality. Use when the user says "lint skills", "validate skills", "check skill quality", "run the linter", "are my skills valid", or before shipping changes to the skills repo.
shajith003/awesome-claude-skills/mcp-builder Skill
no license25★ 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 18 other repositories
shajith003/awesome-claude-skills/skill-creator Skill
no license25★ 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
itsmostafa/llm-engineering-skills/skills/prompt-engineering Skill
25★ repoCrafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or debugging poor model responses.
Maxmedawar/tandem/skills/tandem-orchestration Skill
25★ repoMASTER SKILL for the tandem orchestration system. Governs the whole hierarchy: the human at the top, the chatbot (Claude.ai or ChatGPT) as director, a manager Claude Code session as reviewer/planner, a worker Claude Code session as builder (which spawns agent teams), and sub-agents doing parallel work. EVERY layer reads this. Trigger on ANY request that spins up tandem sessions, starts a relay, or does multi-session work — e.g. 'start tandem', 'spawn a Claude Code session', 'open a manager/worker'. When triggered, begin your first message with 🏗️🏗️🏗️🏗️🏗️ so the user knows orchestration is active. If anyone at any layer tries to skip the protocol, STOP THEM.
mworldorg/markdown-memory/skills/mm-handoff Skill
25★ repoГенерирует handoff.md — компактную сводку для нового чата claude.ai когда контекст текущего заполнился. Включает 15-категорийный Session Guide (вдохновлено context-mode), выжимку последних сессий, текущее состояние, открытые вопросы, и (если есть GSD) — current phase + last 3 SUMMARY.md. Use when user says "контекст заполнен", "новый чат", "handoff", "сводка для нового чата", "/mm-handoff", "пора закругляться, готовь следующий чат". НЕ путать с mm-save-session — этот про подготовку СЛЕДУЮЩЕГО чата, save-session про закрытие текущего.
nimadorostkar/Claude-Skills-collection/skills/agent-tooling/skill-authoring Skill
25★ repoUse when writing a new skill for an AI agent. Covers scoping, description writing for reliable triggering, progressive disclosure, and the difference between a skill and a prompt.
nimadorostkar/Claude-Skills-collection/skills/agent-tooling/subagents Skill
25★ repoUse when delegating work to a separate agent with its own context. Covers when delegation pays off, designing a subagent's scope and prompt, parallel fan-out, and the cost of a cold start.
nimadorostkar/Claude-Skills-collection/skills/ai/agent-design Skill
25★ repoUse when building an LLM agent that uses tools over multiple steps. Covers tool design, the agent loop, error recovery, termination, human checkpoints, and knowing when an agent is the wrong architecture.
nimadorostkar/Claude-Skills-collection/skills/ai/context-engineering Skill
25★ repoUse when managing what an LLM sees. Covers context-window budgeting, retrieval and compaction, memory across turns, tool-result pruning, and the failure modes that come from too much context rather than too little.
nimadorostkar/Claude-Skills-collection/skills/ai/llm-cost-optimization Skill
25★ repoUse when an LLM feature costs too much. Covers prompt caching, context reduction, model routing, batching, output limits, and finding where the tokens actually go.