Context & AI engineering
25,841 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
aiworkskills/wechat-article-skills/skills/aws-wechat-article-writing Skill
752★ repo公众号写稿|长文写作|文章润色|改写续写 — 公众号长文 AI 写作,从话题或提纲生成完整初稿,支持改写、续写、润色、开头结尾优化,可调 DeepSeek / GPT / Claude 或由 Agent 代写。面向自媒体作者、公众号运营、品牌文案。触发词(**单独触发仅限对已有稿子的修改**):「改写」「润色」「续写」「续一段」「往下写」「接着这段写」「重写开头」「改结尾」「调整语气」「这段润色下」「把这段改活泼点」「优化用词」「用 GPT 重写」「用 DeepSeek 重写」。新写一篇请走 aws-wechat-article-main(main 内部会调用本 skill 生成初稿);需要多环节串联(写+审+排+配图+发)也走 main。
The same file is in 3 other repositories
indranilbanerjee/digital-marketing-pro/skills/add-integration Skill
734★ repoAdd MCP server integrations. Use when: connecting a custom tool, API, or service to the plugin via .mcp.json.
indranilbanerjee/digital-marketing-pro/skills/campaign-orchestrator Skill
734★ repoOrchestrate full campaign lifecycle. Use when: planning, launching, managing, UTM setup, media plan, post-mortem.
indranilbanerjee/digital-marketing-pro/skills/eval-config Skill
734★ repoConfigure content eval settings. Use when: adjusting score thresholds, dimension weights, or auto-reject rules.
indranilbanerjee/digital-marketing-pro/skills/eval-content Skill
734★ repoEvaluate content quality. Use when: scoring drafts, checking hallucinations, or assessing brand voice compliance.
indranilbanerjee/digital-marketing-pro/skills/eval-suite Skill
734★ repoBatch evaluate multiple content pieces. Use when: scoring a content library, campaign assets, or deliverable set.
indranilbanerjee/digital-marketing-pro/skills/prompt-test Skill
734★ repoA/B test content variations. Use when: comparing quality scores across prompt approaches, headline styles, or content versions.
indranilbanerjee/digital-marketing-pro/skills/sync-memory Skill
734★ repoBatch sync session learnings to memory. Use when: persisting campaign insights and performance history across sessions.
Ar9av/PaperOrchestra/skills/literature-review-agent Skill
no license714★ repoAn automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.
Ar9av/PaperOrchestra/skills/outline-agent Skill
no license714★ repoStep 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimental_log.md, template.tex, conference_guidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citation hints. TRIGGER when the orchestrator delegates Step 1 or when the user asks to "outline a paper from raw materials" or "generate the paper structure".
Ar9av/PaperOrchestra/skills/plotting-agent Skill
no license714★ repoStep 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".
The same file is in 5 other repositories
Ar9av/PaperOrchestra/skills/section-writing-agent Skill
no license714★ repoStep 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimental_log.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges everything into the template that already contains Intro + Related Work from Step 3. TRIGGER when the orchestrator delegates Step 4 or when the user asks to "write the methodology and experiments sections" or "fill in the rest of the paper".
The same file is in 5 other repositories
shinpr/claude-code-workflows/dev-skills/skills/llm-friendly-context Skill
708★ repoClarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
The same file is in 2 other repositories
shinpr/claude-code-workflows/dev-workflows-frontend/skills/llm-friendly-context Skill
708★ repoClarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
shinpr/claude-code-workflows/dev-workflows-frontend/skills/subagents-orchestration-guide Skill
708★ repoGuides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.
shinpr/claude-code-workflows/dev-workflows-fullstack/skills/llm-friendly-context Skill
708★ repoClarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
shinpr/claude-code-workflows/dev-workflows-fullstack/skills/subagents-orchestration-guide Skill
708★ repoGuides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.
shinpr/claude-code-workflows/dev-workflows/skills/llm-friendly-context Skill
708★ repoClarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
shinpr/claude-code-workflows/dev-workflows/skills/subagents-orchestration-guide Skill
708★ repoGuides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.
shinpr/claude-code-workflows/skills/llm-friendly-context Skill
708★ repoClarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
The same file is in 2 other repositories
shinpr/claude-code-workflows/skills/subagents-orchestration-guide Skill
708★ repoDevelopment workflows for Claude Code that keep broad exploration focused on the outcome you approved.
The same file is in 1 other repository
Varnan-Tech/opendirectory/skills/claude-md-generator Skill
707★ repoUse when the user asks to generate or update a project's CLAUDE or AGENTS context file from a codebase scan. Writes a focused file under 100 lines containing only the non-obvious build commands, conventions, and gotchas Claude Code needs.
The same file is in 1 other repository
staruhub/ClaudeSkills/skills/Geek-skills-keqian-method Skill
699★ repo胥克谦式AI-Native产品开发方法论。适用于:(1) 使用AI Agent(Claude Code、Codex、Cursor等)进行产品级软件开发,(2) 设计和优化Harness/Skill体系,(3) 文档驱动开发(SDD)流程,(4) 构建自动化质量门禁和eval机制,(5) Token成本优化与缓存策略,(6) 产品人转型开发者的AI编程实践。触发场景包括"帮我设计开发流程"、"怎么降低token成本"、"怎么提高AI编码质量"、"文档驱动"、"质量门禁"、"harness设计"、"单agent vs multi-agent"、"自动化迭代"、"AI产品开发"、"SDD"、"eval机制"等。即使用户只是说"帮我用AI写代码"或"怎么让agent干活更靠谱"也应触发。注意:如果产品是行为开放、用户输入不可穷举的AI-native类型,请改用 xuefeng-method skill。不用于:单个bug修复或小改动(无需方法论)、PRD需求文档写作(用product-manager)。
The same file is in 3 other repositories
staruhub/ClaudeSkills/llm-wiki Skill
672★ repoBuild and maintain a structured LLM-generated wiki for any codebase. Use when the user asks to analyze/understand/document a codebase, build a code wiki, create project documentation from source, or update an existing .llm-wiki. Triggers on phrases like "build wiki", "analyze this codebase", "document this project", "update wiki", "llm-wiki", or when entering an unfamiliar project that has no .llm-wiki yet.
NicholasSpisak/second-brain/skills/second-brain Skill
no license670★ repoSet up a new Obsidian knowledge base with the LLM Wiki pattern. Use when the user wants to create a second brain, initialize a vault, set up a personal knowledge base, or says "onboard". Guides through an interactive wizard to configure vault name, location, domain, agent support, and tooling.
lawve-ai/awesome-legal-skills/skills/lawyerscrib-garry-haas Skill
no license641★ repoLes LLM écrivent du juridique qui ressemble à du juridique sans en être. Formules creuses, attributions vagues, hedging systématique, latin décoratif : un praticien repère ces tics en trois lignes. Un juge aussi. LawyerScrib est un skill pour Claude Code et Cursor qui nettoie ces traces. Il scanne 17 patterns typiques de l'écriture IA appliquée au droit français (conclusions, consultations, notes, mails, actes) et réécrit chaque passage pour retrouver le ton d'un avocat qui argumente, pas d'un modèle qui rédige. Le résultat : un texte engagé, précis, avec des références sourcées et une position claire. Pas un texte neutre qui "reste à disposition pour tout complément".
Privilege sentinel emily cabrera
lawve-ai/awesome-legal-skills/skills/privilege-sentinel-emily-cabrera Skill
no license641★ repoPre-flight privilege and work-product check for legal AI prompts. Use when the user is about to send legal content to a third-party AI surface (ChatGPT, Claude.ai, Copilot, Gemini, etc.) and wants to know whether the prompt risks blowing attorney-client privilege or work-product protection. Returns a SAFE/CAUTION/STOP band with cited factors, a discovery-impact line, and a redacted-safe rewrite.
lawve-ai/awesome-legal-skills/skills/skill-creator-anthropic Skill
no license641★ repoA curated list of awesome Agent Skills for automating legal work
The same file is in 1 other repository
lawve-ai/awesome-legal-skills/skills/skill-creator-openai Skill
no license641★ repoA curated list of awesome Agent Skills for automating legal work
The same file is in 1 other repository
minhnv0807/ai-business-skills/skills/en/03-performance-eval-global Skill
641★ repoUse when marketing numbers look bad and the user needs to know WHY — layered root-cause diagnosis across tracking, delivery, creative, landing page, offer, and audience quality, 5-Whys, regional benchmarks for US, EU, SEA, and LATAM, and a 48-hour action plan. Covers dropshipping ROAS and BE-ROAS. Trigger on 'why is CPA so high', 'my ads are not converting', 'ROAS dropped', 'we are burning budget', 'performance is bad this month', 'diagnose the funnel'. Also use when the user pastes a screenshot of numbers with no question attached. Not for — auditing account configuration and scoring health, see `21-ads-audit-global`; writing a report someone else reads, see `07-marketing-report-global`; turning a raw export into insight, see `13-data-analysis-global`.
The same file is in 1 other repository
minhnv0807/ai-business-skills/skills/en/30-design-master-global Skill
641★ repo138 bilingual AI marketing skills (69 VN + 69 Global) for Claude Code, OpenCode, Codex, VS Code. Four role SOP packs — content, design, performance, leader ops — plus strategy, personal brand, AI avatar, dropshipping, design master, knowledge library. 4 regions (US/EU/SEA/LATAM) + Vietnam 2025-2026. Companion: opa-kit.
The same file is in 1 other repository
nWave-ai/nWave/nWave/skills/nw-agent-creation-workflow Skill
636★ repoDetailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement
The same file is in 4 other repositories
nWave-ai/nWave/nWave/skills/nw-agent-testing Skill
636★ repo5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance
The same file is in 4 other repositories
nWave-ai/nWave/nWave/skills/nw-deliver-orchestration Skill
636★ repoDELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes *deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.
The same file is in 4 other repositories
nWave-ai/nWave/nWave/skills/nw-design-patterns Skill
636★ repo7 agentic design patterns with decision tree for choosing the right pattern for each agent type
The same file is in 5 other repositories
nWave-ai/nWave/plugins/nw/skills/nw-agent-creation-workflow Skill
636★ repoDetailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement
nWave-ai/nWave/plugins/nw/skills/nw-agent-testing Skill
636★ repo5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance
nWave-ai/nWave/plugins/nw/skills/nw-deliver-orchestration Skill
636★ repoDELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes *deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.
nWave-ai/nWave/plugins/nw/skills/nw-design-patterns Skill
636★ repo7 agentic design patterns with decision tree for choosing the right pattern for each agent type
rshankras/claude-code-apple-skills/skills/generators/review-prompt Skill
621★ repoGenerates smart App Store review prompt infrastructure with configurable conditions and platform detection. Use when user wants to add review prompts, request ratings, or implement StoreKit reviews.
rshankras/claude-code-apple-skills/skills/product/product-agent Skill
621★ repoDiscover and validate product ideas, analyze markets, scope MVPs, and optimize app store presence for iOS/macOS apps. Use when user asks to discover, validate, assess, scope, or analyze product ideas, market opportunities, or when they mention "product agent", "app idea validation", "should I build this", "MVP", "market analysis", or "ASO".
rshankras/claude-code-apple-skills/skills/shared/skill-creator Skill
621★ repoGuides you through creating well-structured Claude Code skills with proper modularization, templates, and best practices. Use when creating new skills or improving existing ones.
rshankras/claude-code-apple-skills/skills/swift/memory Skill
621★ repoSwift 6.2 InlineArray and Span types for zero-overhead memory access, fixed-size collections, and safe pointer alternatives. Use when optimizing performance-critical code paths.
artokun/comfyui-mcp/io.github.artokun/comfyui-mcp MCP server
588★ repoMCP server + Claude Code plugin for ComfyUI: run workflows, generate images, manage models & VRAM.
levnikolaevich/claude-code-skills/plugins/optimization-suite/skills/ln-34-benchmark-comparator Skill
587★ repoStandalone engineering skills for Claude Code and Codex: review, audit, optimization, testing, product discovery, architecture, and safe publishing.
The same file is in 1 other repository
anombyte93/prd-taskmaster/skills/handoff Skill
587★ repoPhase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a structured AskUserQuestion multi-option picker for user agency, and dispatches the chosen mode. Mode D (Atlas Fleet) is selectable only when detect_capabilities returns tier=premium (licensed atlas-launcher detected); otherwise it is a locked Atlas Pro teaser. Plan Mode is NOT used (spec section 13.5): AskUserQuestion is the sole user-agency mechanism. Declares HANDOFF complete so EXECUTE can follow.
levnikolaevich/claude-code-skills/io.github.levnikolaevich/hex-graph-mcp MCP server
587★ repoDeterministic layered code graph MCP server with framework overlays and SCIP interop.
levnikolaevich/claude-code-skills/io.github.levnikolaevich/hex-line-mcp MCP server
587★ repoHash-verified file editing MCP server with token efficiency hook for AI coding agents.
sergebulaev/linkedin-skills/.codex-marketplace/linkedin-skills/skills/linkedin-hook-extractor Skill
579★ repoReverse-engineer the hook formula from a viral LinkedIn post URL. Returns which of the 16 canonical 2026 formulas it uses (anaphora, R.I.P., year-pivot, time-anchor, curiosity-gap, contrarian, comment-gate, emotional cold-open, named-gratitude, and 7 more), why it worked, and a blank template. Use to learn from a competitor's post, not to write your own (use linkedin-post-writer).
The same file is in 3 other repositories
sergebulaev/linkedin-skills/skills/linkedin-hook-extractor Skill
579★ repoReverse-engineer the hook formula from a viral LinkedIn post URL. Returns which of the 16 canonical 2026 formulas it uses (anaphora, R.I.P., year-pivot, time-anchor, curiosity-gap, contrarian, comment-gate, emotional cold-open, named-gratitude, and 7 more), why it worked, and a blank template. Use to learn from a competitor's post, not to write your own (use linkedin-post-writer).
The same file is in 3 other repositories
Masriyan/Claude-Code-CyberSecurity-Skill/skills/16-ai-llm-security Skill
no license578★ repoLLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments
The same file is in 1 other repository
tzachbon/smart-ralph/.agents/skills/MCP Integration Skill
566★ 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 128 other repositories
tzachbon/smart-ralph/plugins/ralph-speckit/skills/delegation-principle Skill
566★ repoCore principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.
The same file is in 4 other repositories
ECNU-ICALK/AutoSkill/SkillBank/Common/AwesomeClaudeSkills/mcp-builder Skill
no license551★ 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).
ECNU-ICALK/AutoSkill/SkillBank/Common/anthropics-skill/mcp-builder Skill
no license551★ 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).
ECNU-ICALK/AutoSkill/SkillBank/Common/anthropics-skill/skill-creator Skill
no license551★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update 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.
ECNU-ICALK/AutoSkill/SkillBank/Common/superpowers/dispatching-parallel-agents Skill
no license551★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
ECNU-ICALK/AutoSkill/SkillBank/Common/superpowers/subagent-driven-development Skill
no license551★ repoUse when executing implementation plans with independent tasks in the current session
ECNU-ICALK/AutoSkill/SkillBank/Common/vercel-labs-browser-skills/agent-browser Skill
no license551★ 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.
Agent de correction pédagogique en mécanique
ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/French/agent-de-correction-pédagogique-en-mécanique Skill
no license551★ repoAgit comme un correcteur IA pour des exercices de mécanique/physique. Il évalue la validité de la réponse de l'élève et guide la démarche de résolution sans jamais donner la solution finale, les formules ou les valeurs numériques.