Context & AI engineering
25,729 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
nbsp1221/agent-skills/skills/subagent-orchestration Skill
no license0★ repoUse when deciding whether to split a coding task into parallel exploration, bounded review fan-out, or single-writer delegated work instead of keeping it in one agent.
theinterneti/TTA.dev/.claude/skills/generated/llm Skill
0★ repoLlm subsystem in TTA.dev: execute and related code. 171 symbols | 30 files | Cohesion: 67%
theinterneti/TTA.dev/.github/skills/create-agent Skill
0★ repoUse this skill when creating, modifying, or debugging a custom Copilot agent (.agent.md file). Provides detailed patterns for agent orchestration, handoffs, sub-agent invocation, tool configuration, variable extraction, and prompt structure. Invoke when the user says "create an agent", "add a new agent", "agent handoffs", "sub-agent", or "orchestrate agents".
theinterneti/TTA.dev/.github/skills/ttadev-llm Skill
0★ repoTeaches how to call an LLM using TTA.dev primitives. Use when the user wants to call an LLM, use LiteLLM, use make_resilient_llm, integrate with an LLM provider, pick a model string for groq, anthropic, openai, gemini, ollama, or openrouter, stream tokens, use tool calls, or set up Langfuse observability. Covers LiteLLMPrimitive (primary path), UniversalLLMPrimitive (fallback), LLMRequest/LLMResponse types, streaming, ToolSchema, and the primary/fallback architecture.
gabriel-f-santos/coding-agents/skills/figma Skill
no license0★ repoTurn a screen spec into a real Figma frame via a connected Figma MCP server and return the shareable link. Use whenever the user (or the `ux-design` skill) wants to "create a Figma frame", "push this screen to Figma", "make a Figma mockup", "update the Figma design", "mandar pro Figma", "criar o frame no Figma", or hands over a screen spec (name, layout, components, states, content) expecting a Figma URL back. Discovers the Figma MCP at runtime instead of hardcoding tool names; reads design context, creates/updates frames, components and variables, and returns the node link. If no Figma MCP is connected it says so and emits the textual spec instead — it never fails hard. Do not use for pencil.dev designs (use the `pencil` skill), for non-Figma design tools (Sketch, Penpot, Adobe XD), for writing the screen spec itself (that is `ux-design`'s job — this skill consumes a finished spec), or for turning a Figma design into code (that is a design-to-code task, not frame authoring).
gabriel-f-santos/coding-agents/skills/pencil Skill
no license0★ repoTurn a screen spec into a real pencil.dev design screen/frame via the Pencil MCP server, and return a reference to the produced design. Use when the user (or the `ux-design` skill) wants to "create a screen in Pencil", "generate this UI in pencil.dev", "build the login screen on the canvas", "mock this up in Pencil", "render the spec as a Pencil frame", or asks to push a screen spec to pencil.dev. It discovers the Pencil MCP at runtime (no hardcoded tool names), maps a screen spec (name, layout, components, states, content) onto Pencil design operations, and hands back the artifact (a `.pen` file / screen reference, plus a screenshot when available). If no Pencil MCP is connected it degrades gracefully and emits the textual spec instead of failing. Do NOT use for Figma — for Figma use the `figma` skill; not for other non-pencil design tools, not for writing the spec itself (that's `ux-design`), nor for turning a finished design into code.
gabriel-f-santos/coding-agents/skills/skill-gen Skill
no license0★ repoGenerate AND iteratively improve production-grade Agent Skills through a guided interview. Use whenever the user wants to create, scaffold, author, or design a new skill or set of skills — "create a skill", "gera uma skill", "skill para X", "turn this workflow into a skill" — OR to improve/fix an existing one ("this skill mis-fired", "it didn't trigger", "improve this skill", "optimize the trigger"). Interviews to decide target runtimes (Claude Code, Codex, opencode), single vs multiple skills, execution shape, and tools, then writes a portable SKILL.md plus references/scripts and per-platform sidecars (Codex openai.yaml), tunes the description, and validates. Do not use to run, install, or security-review an existing skill (that's skill-scanner), or to tweak non-skill prose — only to author or improve a skill.
The same file is in 1 other repository
JordanCoin/ios-design-stack/skills/pencil-ios-design Skill
0★ repoiOS-specific Pencil MCP design workflow. Creates iOS screens on canvas following Apple HIG with proper SF Pro typography, semantic colors, and 8pt spacing grid. Use when designing iOS UI in .pen files. Requires Pencil MCP server.
The same file is in 1 other repository
Vasallo94/skill-issue/skills/obsidian/prompt-engineer Skill
no license0★ repoDisena, itera y versiona prompts de LLM. Documenta el proceso de optimizacion con metricas y variantes.
muhammederem/chief Skill
no license0★Multi-agent orchestration framework for automating ML/AI, backend, and DevOps workflows. Use when building ML pipelines, training models, creating APIs, deploying to cloud, or setting up infrastructure.
karim-bhalwani/agent-skills-collection/skills/llm-app-patterns Skill
0★ repoProduction LLM application patterns, architectures, and best practices. Covers RAG pipelines, agent architectures, prompt engineering, LLMOps, and production deployment patterns.
karim-bhalwani/agent-skills-collection/skills/orchestrator Skill
0★ repoSpecialized in managing project-wide constraints, context tiers, and coordination between specialized skills. Use when interpreting project rules, coordinating complex workflows, managing context and dependencies, or overseeing multi-skill project execution.
karim-bhalwani/agent-skills-collection/skills/proj-memory Skill
0★ repoSet up and maintain structured project memory systems that track bugs with solutions, architectural decisions, key project facts, and work history. Use when setting up new projects, documenting decisions, tracking bugs and solutions, or maintaining project knowledge across sessions.
karim-bhalwani/agent-skills-collection/skills/prompt-library Skill
0★ repoCurated collection of high-quality prompts for various tasks—role-based templates, analysis frameworks, code review prompts, and brainstorming structures. Use when building prompts for specific roles, needing analysis or brainstorming frameworks, creating code review prompts, or searching for proven prompt patterns and structures.
karim-bhalwani/agent-skills-collection/skills/subagent-driven-development Skill
0★ repoExecute implementation plans with independent tasks in the current session using fresh subagents with two-stage review after each task. Use when breaking down complex work into parallel tasks, managing subagent execution, or coordinating multi-step implementation.
tdw419/ascii-world/apps/mcp2cli/skills/mcp2cli Skill
no license0★ repoTurn any MCP server or OpenAPI spec into a CLI. Use this skill when the user wants to interact with an MCP server or OpenAPI/REST API via command line, discover available tools/endpoints, call API operations, or generate a new skill from an API. Triggers include "mcp2cli", "call this MCP server", "use this API", "list tools from", "create a skill for this API", or any task involving MCP tool invocation or OpenAPI endpoint calls without writing code.
songsunny00/MySkills/BaseSkills/.agents/skills/mcp-builder Skill
no license0★ 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
songsunny00/MySkills/BaseSkills/.agents/skills/skill-creator Skill
no license0★ 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
songsunny00/MySkills/BaseSkills/.agents/skills/translate-skills Skill
no license0★ repo当用户想为 Skills 批量添加中文翻译时使用,支持全局 agent 目录(~/.claude/skills、~/.cursor/skills、~/.trae-cn/skills 等)以及当前项目目录下的 .claude/skills、.cursor/skills 等。适用场景:用户说"给 skills 加中文"、"汉化所有 skill"、"翻译当前项目的 skill"。
songsunny00/MySkills/CoderSkills/.agents/skills/dispatching-parallel-agents Skill
no license0★ 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
songsunny00/MySkills/CoderSkills/.agents/skills/subagent-driven-development Skill
no license0★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 3 other repositories
songsunny00/MySkills/skills/translate-skills Skill
no license0★ repo当用户想为 Skills 批量添加中文翻译时使用,支持全局 agent 目录(~/.claude/skills、~/.cursor/skills、~/.trae-cn/skills 等)以及当前项目目录下的 .claude/skills、.cursor/skills 等。适用场景:用户说"给 skills 加中文"、"汉化所有 skill"、"翻译当前项目的 skill"。
liuning0820/skills/skills/karpathy-llm-wiki Skill
no license0★ repoUse when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
javalenciacai/develop-skills/.agents/skills/cto Skill
0★ repoMain role orchestrator. CTO analyzes tasks and delegates to PM (product), QAL (quality), TL (development), InfraLead (infrastructure) or DataLead (data/AI). Entry point for all tasks. Use when: (1) User requests involve product strategy, roadmap or UX, (2) Quality testing, security audits or compliance needed, (3) Development, architecture or code implementation required, (4) Infrastructure, CI/CD, databases or deployment tasks, (5) Data pipelines, analytics, AI/ML models or LLM integration, (6) Cross-domain coordination between multiple areas, (7) Any ambiguous request that needs domain analysis and delegation.
javalenciacai/develop-skills/.agents/skills/datalead Skill
0★ repoData and AI orchestrator. Data Lead coordinates DataEng and AIEng for data pipelines, ETL, data warehousing and AI/ML models. Leads data strategy and machine learning. Reports to CTO. Use when: (1) Data strategy, analytics or data governance needed, (2) Data pipelines, ETL or data warehousing required, (3) AI/ML models, training or MLOps implementation, (4) LLM integration or generative AI features, (5) Data quality, schema design or data architecture, (6) Model evaluation, monitoring or A/B testing, (7) Coordinating between data engineering and AI engineering teams.
javalenciacai/develop-skills/.agents/skills/infralead Skill
0★ repoInfrastructure orchestrator. Infrastructure Lead coordinates DevOps and DBA for CI/CD, cloud, containers and database management. Leads platform and operations. Reports to CTO. Use when: (1) Infrastructure strategy or platform architecture needed, (2) CI/CD pipelines, deployments or container orchestration required, (3) Database management, optimization or backup strategies, (4) Cloud infrastructure or infrastructure as code (IaC), (5) System monitoring, logging or incident response, (6) Capacity planning or disaster recovery, (7) Coordinating between DevOps operations and database administration.
javalenciacai/develop-skills Skill
0★Sistema de orquestación de roles para agentes de IA. Cada rol delega a sus subordinados y usa skills de skills.sh. Skills base para todos los roles - find-skills (buscar) y skill-creator (crear).
thedevappsecguy/sec-skills/skills/skill-scanner-scans Skill
0★ repoInspect the current environment, reuse or install the PyPI package `skill-scanner` with `pip`, and scan AI skills, prompts, instructions, agents, and rules for malicious behavior. Use this skill whenever the user mentions `skill-scanner`, `skillscan`, `pip install skill-scanner`, malicious AI skills, suspicious prompt or instruction files, or scanning Codex, Claude, Cursor, Copilot, Gemini, Windsurf, Cline, or OpenCode skill artifacts.
stephenrogan/csm-skills/skills/handoff-intro-email Skill
0★ repoWrites the transition email when a customer moves to a new CSM -- the outgoing CSM's introduction of the incoming CSM. Balances reassurance with enthusiasm, provides enough context for the customer without overwhelming them, and positions the incoming CSM for a strong start. Use when asked to write a handoff email, draft a CSM transition introduction, compose a customer reassignment communication, or when any account is changing CSM ownership and the customer needs to be informed. Also triggers for questions about CSM transitions, account handoff communications, customer reassignment emails, or how to introduce a new CSM to a customer.
hi-space/strands-agentskills/skills/skill-creator Skill
0★ 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
planifest/planifest-framework/planifest-framework/external-skills/ai-seo Skill
0★ repoWhen the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for Perplexity,' 'AI citations,' 'AI visibility,' 'zero-click search,' 'how do I show up in AI answers,' 'LLM mentions,' or 'optimize for Claude/Gemini.' Use this whenever someone wants their content to be cited or surfaced by AI assistants and AI search engines. For traditional technical and on-page SEO audits, see seo-audit. For structured data implementation, see schema-markup.
The same file is in 1 other repository
planifest/planifest-framework/planifest-framework/external-skills/aws-agentic-ai Skill
0★ repoAWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale. Use when working with any AgentCore service including Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, or Evaluations. Covers agent deployment, MCP tool integration, credential management, agent discovery, governance workflows, and automated quality assessment. Essential when user mentions AgentCore, agent runtime, agent registry, agent evaluation, MCP gateway, deploy agent, register MCP server, discover agents, evaluate agent quality, agent credentials, or wants to build, deploy, catalog, or monitor AI agents on AWS.
The same file is in 1 other repository
planifest/planifest-framework/planifest-framework/external-skills/benchmark-models Skill
0★ repoCross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".
planifest/planifest-framework/planifest-framework/external-skills/benchmark Skill
0★ repoPerformance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time". (gstack) Voice triggers (speech-to-text aliases): "speed test", "check performance".
planifest/planifest-framework/planifest-framework/external-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
planifest/planifest-framework/planifest-framework/external-skills/content-design Skill
0★ repoRewrite and improve an LLM prompt using proven prompt engineering techniques — covering clarity, persona, delimiters, chain-of-thought, examples, and output format specification.
planifest/planifest-framework/planifest-framework/external-skills/context-engineering Skill
0★ repoOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
The same file is in 12 other repositories
planifest/planifest-framework/planifest-framework/external-skills/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
planifest/planifest-framework/planifest-framework/external-skills/figma-handoff Skill
0★ repoDesign-to-engineering handoff workflow for packaging implementation-ready Figma specifications, assets, and acceptance criteria. Trigger when approved Figma designs must be translated into engineering-ready handoff materials (specs, assets, states, acceptance criteria) before implementation starts; do not use for backend data-model or deployment pipeline decisions.
planifest/planifest-framework/planifest-framework/external-skills/gpt-image-2 Skill
0★ repo面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用:(A) Garden 本地模式,通过 OpenAI 兼容接口直接出图并落盘;(B) Host-Native 模式,把本 Skill 当作提示词工程指引,把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图;(C) Advisor 模式,宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板,覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。
The same file is in 2 other repositories
planifest/planifest-framework/planifest-framework/external-skills/memory-safety-patterns Skill
0★ repoCross-language patterns for memory-safe programming including RAII, ownership, smart pointers, and resource management.
The same file is in 5 other repositories
planifest/planifest-framework/planifest-framework/external-skills/nelson Skill
0★ repoOrchestrates multi-agent task execution using a Royal Navy squadron metaphor — from mission planning through parallel work coordination to stand-down. Use when work needs parallel agent orchestration, tight task coordination with quality gates, structured delegation with progress checkpoints, or a documented decision log.
planifest/planifest-framework/planifest-framework/external-skills/on-call-handoff-patterns Skill
0★ repoEffective patterns for on-call shift transitions, ensuring continuity, context transfer, and reliable incident response across shifts.
The same file is in 6 other repositories
planifest/planifest-framework/planifest-framework/external-skills/rag-engineer Skill
0★ repoExpert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.
The same file is in 3 other repositories
planifest/planifest-framework/planifest-framework/external-skills/saga-orchestration Skill
0★ repoPatterns for managing distributed transactions and long-running business processes.
The same file is in 5 other repositories
planifest/planifest-framework/planifest-framework/external-skills/vector-database-engineer Skill
0★ 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 4 other repositories
planifest/planifest-framework/planifest-framework/skills/planifest-adr-agent Skill
0★ repoProduces Architecture Decision Records for each significant decision in the requirements. Invoked by the orchestrator during Phase 2.
Planifest build assessment agent
planifest/planifest-framework/planifest-framework/skills/planifest-build-assessment-agent Skill
0★ repoPhase 8 — reads plan/current/build-log.md and produces a structured build efficiency report filed to the archive. Invoked by the ship-agent after archiving.
planifest/planifest-framework/planifest-framework/skills/planifest-change-agent Skill
0★ repoHandles targeted modifications to existing features — loads domain context, implements the minimum change, validates, and updates documentation. Invoked via the Change Pipeline route.
planifest/planifest-framework/planifest-framework/skills/planifest-codegen-agent Skill
0★ repoGenerates the full implementation from the requirements set - application code, tests, infrastructure, configuration. Invoked during Phase 3.
planifest/planifest-framework/planifest-framework/skills/planifest-docs-agent Skill
0★ repoProduces complete per-component documentation, system-wide registry, dependency graph, and iteration log audit trail. Invoked during the Documentation step.
planifest/planifest-framework/planifest-framework/skills/planifest-optimise-agent Skill
0★ repoReviews planifest-framework/skills/ for superfluous content and presents one suggestion at a time for human confirmation. Never modifies files.
planifest/planifest-framework/planifest-framework/skills/planifest-orchestrator Skill
0★ repoGuides a human from an initial idea to a complete set of requirements, then executes the confirmed design pipeline to build it. Use this for new features or full pipeline runs.
planifest/planifest-framework/planifest-framework/skills/planifest-scope-lock-agent Skill
0★ repoDrafts a single suggested Scope Lock Challenge answer, dispatched only on explicit human request during P0. Never pre-drafts, never self-confirms — the human's per-item accept/edit/reject is the only thing that counts as scope confirmation.
planifest/planifest-framework/planifest-framework/skills/planifest-security-agent Skill
0★ repoPerforms a security review of the implementation, producing a security report with specific findings. Invoked during Phase 5.
planifest/planifest-framework/planifest-framework/skills/planifest-ship-agent Skill
0★ repoPhases 7, 8, and 9 — archives plan/current/ (P7), spawns build-assessment-agent (P8), then creates a git tag and raises or describes the PR (P9).
planifest/planifest-framework/planifest-framework/skills/planifest-spec-agent Skill
0★ repoProduces requirements artifacts (execution plan, OpenAPI spec (if applicable), scope, risk register, domain glossary) for a feature. Invoked by the orchestrator during the Requirements step.
planifest/planifest-framework/planifest-framework/skills/planifest-validate-agent Skill
0★ repoRuns CI checks (lint, typecheck, test, build) and self-corrects up to 5 times. Invoked during Phase 4.
badass-courses/a11y-agent/source/skills/a11y-agent Skill
no license0★ repoAccessibility expertise for building inclusive web interfaces. Covers semantic HTML, ARIA, keyboard interaction, screen reader support, color contrast, focus management, responsive zoom, motion safety, automated testing, and organizational culture. Use when building or reviewing any web UI to ensure it works for everyone.
michelve/hugin-v0/skills/figma-code-connect-components Skill
0★ repoConnects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "connect Figma to code", "map this component", "link component to code", "create code connect mapping", "add code connect", "connect design to code", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`. Requires Figma MCP server connection.