Context & AI engineering
25,745 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
bcastelino/agent-skills-kit/skills/embedding-strategies Skill
2★ repoSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific dom...
The same file is in 3 other repositories
Full stack orchestration full stack feature
bcastelino/agent-skills-kit/skills/full-stack-orchestration-full-stack-feature Skill
2★ repoUse when working with full stack orchestration full stack feature
The same file is in 1 other repository
bcastelino/agent-skills-kit/skills/mcp-builder Skill
2★ 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 exte...
bcastelino/agent-skills-kit/skills/rag-engineer Skill
2★ repoExpert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, ...
bcastelino/agent-skills-kit/skills/rag-implementation Skill
2★ repoRAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization. Use when building RAG systems.
bcastelino/agent-skills-kit/skills/skill-creator Skill
2★ repoInteractive guide for creating, scaffolding, and iterating on Agent Skills. Use when the user wants to build a skill, write a SKILL.md, generate frontmatter, define trigger phrases, validate, package, or distribute a skill.
jtsang4/efficient-coding/skills/codex-skill-creator Skill
2★ 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.
jtsang4/efficient-coding/skills/general-skill-creator Skill
2★ repoCreate, modify, evaluate, and package portable Agent Skills for coding agents. Use this skill when users want to create a skill from scratch, turn a workflow into a reusable skill, improve an existing skill, set up evals, compare skill behavior against a baseline, or optimize skill trigger descriptions across agent environments.
jtsang4/efficient-coding/skills/harness Skill
2★ repoTransform any code project into one optimized for AI agent collaboration through harness engineering. Scans the codebase to detect structure, patterns, and tooling, extracts implicit engineering knowledge through guided choice-based questions, and generates minimal structured context documents plus engineering changes (lint rules, structural tests, CI checks). Use this skill when the user wants to make their codebase agent-ready, mentions harness engineering, wants to set up AGENTS.md or agent context, wants to improve AI coding agent productivity on their project, or asks to establish constraints, guardrails, or feedback loops for AI agents. Also trigger when users say "prepare my repo for agents", "harness my project", "improve agent workflow", or want their project to work better with Claude Code, Codex, Cursor, or similar AI coding tools. Even if the user doesn't use the word "harness", if they're asking about making a codebase more agent-friendly or productive for AI-assisted development, use this skill.
jtsang4/efficient-coding/skills/subagent-driven-development Skill
2★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 7 other repositories
jtsang4/efficient-coding/skills/worktree-manager Skill
2★ repoManage Git worktrees. Use when asked to create/switch/list/merge/remove worktrees, to keep multiple branches in parallel directories, or to clean up worktrees safely during development.
lyceum-quest/orchestrator/.pi/skills/text-orchestrator Skill
2★ repoAutomated text pipeline orchestrator — run through all stages sequentially, launching each stage skill automatically until completion or a blocker is hit.
igapyon/igapyon-agent-skills/skills/igapyon-mikuku-agent Skill
2★ repoA personal repository for managing Agent Skills used for Japanese Note/Qiita article writing, companion-style technical and music post writing, GitHub text drafting, and Mikuku character-agent workflows.
CodeAlive-AI/exa-skills/exa-financial-report-search Skill
no license2★ repoFind financial filings with Exa — SEC filings (10-K, 10-Q, S-1), earnings reports, and annual reports. Use to pull a company's financials, compare results across periods, or locate a specific filing. Runs a local script against the Exa API; no MCP server required.
CodeAlive-AI/exa-skills/exa-lead-generation Skill
no license2★ repoBuild prospect lists with Exa — find target companies matching an ICP, then their decision-makers, then enrich with signals. Use for outbound sales lists, account mapping, and B2B prospecting. Multi-pass orchestration over the Exa API; no MCP server required.
CodeAlive-AI/exa-skills/exa-people-research Skill
no license2★ repoFind people with Exa semantic search — by role, company, and location, LinkedIn-weighted. Use to map a company's team, find experts/decision-makers, locate a specific person, or build people lists. Runs a local script against the Exa API; no MCP server required.
CodeAlive-AI/exa-skills/exa-personal-site-search Skill
no license2★ repoFind personal websites with Exa — blogs, portfolios, and homepages. Use to find a person's own writing (not press about them), discover practitioners who blog, or surface indie/portfolio sites. Runs a local script against the Exa API; no MCP server required.
CodeAlive-AI/exa-skills/exa-research-paper-search Skill
no license2★ repoFind academic papers with Exa — by topic, author, recency, or as surveys/reviews. Use for literature reviews, finding seminal or state-of-the-art papers, tracking recent preprints (arXiv), or building a reading list. Runs a local script against the Exa API; no MCP server required.
CodeAlive-AI/exa-skills/exa-web-search Skill
no license2★ repoGeneral-purpose web search powered by Exa — the search_web / web_search analog. Use for any open-ended lookup, fact-finding, or 'search the web for X' when no specialized skill fits. Semantic (meaning-based) search over the whole index; runs a local script against the Exa API, no MCP server required.
CodeAlive-AI/exa-skills/exa-x-search Skill
no license2★ repoSearch X/Twitter posts with Exa, filtered to x.com/twitter.com. Use for finding tweets or threads on a topic. NOTE: Exa's X coverage is limited (the tweet category was retired and X blocks crawlers), so results are often sparse — the skill is honest about this and suggests fallbacks. Runs a local script against the Exa API; no MCP server required.
ClarentCinematics/Codex-Skills-for-Enterprise/skills/knowledge-base-capture Skill
2★ repoConvert meetings, support threads, incident learnings, project notes, SOP drafts, process explanations, or expert knowledge into clean knowledge-base articles with audience, steps, ownership, freshness metadata, related links, and review needs. Use when Codex needs to preserve institutional knowledge in a reusable article.
dzhokhov/markdown-agent-vault-ru/skills/new-dialog-handoff Skill
2★ repoБезопасный переход в новый диалог, когда чат стал длинным или агент прогнозирует скорое исчерпание контекстного окна. Скилл переиспользует `parking` и `resume`, фиксирует durable source of truth и готовит короткий restart-packet для свежего чата. ОБЯЗАТЕЛЬНО используй, когда пользователь говорит: «новый диалог», «перенеси в новый чат», «сделай handoff», «продолжим в новом чате», а также когда агент сам выводит критический хвост вида `CTX~N% -> new-dialog-handoff`.
dzhokhov/markdown-agent-vault-ru/skills/owner-only-dev-orchestrator Skill
2★ repoОркестрация полного цикла разработки с минимальным участием владельца и максимальной самопроверкой агента. Используй, когда пользователь просит: «сделай под ключ», «минимум моего участия», «сам проверь», «внедри/исправь скрипт или программу полностью». Скилл обязателен для кодовых задач, где нужно пройти quality gates, подготовить owner decision packet и выдать итог только в формате GREEN/YELLOW/RED.
dzhokhov/markdown-agent-vault-ru/skills/skill-creator Skill
2★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when the user wants to capture a workflow as a reusable skill, draft a new skill, edit or optimize an existing one, run evals against a skill, or tune a skill's description for triggering accuracy.
The same file is in 1 other repository
qiuy-collab/AutoFlow.skill/integrations/agent-skills/browser-testing-with-devtools Skill
2★ repoTests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
The same file is in 3 other repositories
qiuy-collab/AutoFlow.skill/integrations/agent-skills/context-engineering Skill
2★ 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
qiuy-collab/AutoFlow.skill/integrations/agent-skills/using-agent-skills Skill
2★ repoDiscovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
The same file is in 2 other repositories
qiuy-collab/AutoFlow.skill/integrations/superpowers/dispatching-parallel-agents Skill
2★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 5 other repositories
qiuy-collab/AutoFlow.skill/integrations/superpowers/subagent-driven-development Skill
2★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 6 other repositories
ralfyishere/rules-with-receipts/.claude/skills/delegation-discipline Skill
2★ repoDelegate work to subagents, background tasks, or parallel workers effectively - and verify their outputs before relying on them. Activate when spawning agents, fanning out searches or reviews, orchestrating multi-agent workflows, running background tasks, or incorporating any output produced outside your own context. Trigger signals: "use agents for this", "fan out", "in parallel", a task too large for one context, or noticing you're about to restate a subagent's claim as your own finding.
ralfyishere/rules-with-receipts/.claude/skills/human-handoff Skill
2★ repoDesign the human's part of a task when a step needs their hands - browser logins, account creation, approvals, physical-world actions, anything outside your tool reach. Activate whenever you're about to ask the user to do something you cannot do, especially multi-step flows you can't observe (OAuth/device flows, account setup, settings pages). Trigger signals: "you'll need to...", "please go to...", a blocked action requiring user credentials or clicks, or a human-step that already failed once.
ralfyishere/rules-with-receipts/.claude/skills/live-state-truth Skill
2★ repoTrust current observed state over memory, docs, or assumptions. Activate before making any claim about the current state of files, code, configs, data, tools, UI, or provided documents - and before editing anything. Trigger signals: about to say "the file contains", "the test passes", "this function does", "the config is set to", "the document says" without having looked this session; editing a file not read recently; predicting command output instead of running the command; resuming work after a break or context compaction.
ralfyishere/rules-with-receipts/.claude/skills/memory-hygiene Skill
2★ repoHandle context carefully across long sessions - distinguish durable facts, temporary context, stale assumptions, and user preferences; re-verify before relying on old context. Activate in long or resumed sessions, after context compaction or summarization, when recalling something established "earlier" in the conversation, when the user contradicts what you remember, and before acting on any remembered detail that current evidence could check. Also governs what is worth persisting to memory files and what is not.
ralfyishere/rules-with-receipts/.claude/skills/prompt-engineering Skill
2★ repoImprove prompts, system prompts, and agent instructions systematically - with test cases, failure diagnosis, and one-change-at-a-time iteration instead of vibe edits. Activate for "improve this prompt", "the model keeps doing X wrong", "write a system prompt", "make the agent stop doing Y", prompt templates, and instruction files for AI tools. Trigger signal: any prompt edit about to happen without a concrete example of the failing (or desired) behavior in hand.
philgoodvibe/aiai-mastermind-tools-and-skills/skills/gpt-image Skill
2★ repoUse when asked to generate, create, make, render, draw, or mock up an image, photo, picture, hero image, illustration, icon, texture, sprite, or visual asset from Claude Code, and no usable OPENAI_API_KEY is set but Codex CLI is installed and signed in to ChatGPT (OAuth). Also triggered by /gpt-image. Routes image generation through Codex's built-in tool, never the OpenAI API.
philgoodvibe/aiai-mastermind-tools-and-skills/skills/model-router/codex/solfab Skill
2★ repoHand any coding/build brief to Claude Fable, which orchestrates the build while GPT-5.6 Sol does the typing (the fabsol flow). Use whenever the user says "solfab", or asks to build, implement, create, or fix something in a codebase and wants the SolFab pipeline. You act as the remote control - you never build it yourself.
philgoodvibe/aiai-mastermind-tools-and-skills/skills/model-router/skills/fabsol Skill
2★ repoThe FabSol flow - the flagship of this plugin. Your main model (e.g. Claude Fable) orchestrates - plans, writes specs, verifies - while the routed worker model (GPT-5.6 Sol by default) does 100% of the building through the local proxy. Use for any real build task.
philgoodvibe/aiai-mastermind-tools-and-skills/skills/wiki-llm Skill
2★ repoUse when someone wants to turn a collection of source documents (books, PDFs, papers, articles, transcripts) into a compounding, interlinked Obsidian knowledge base maintained by an LLM — a "wiki LLM" / second brain / Memex that sits between them and the raw sources. Triggers on "wiki llm", "build a wiki from these books/PDFs", "ingest these sources", "compounding knowledge base", "Obsidian vault from documents", "RAW / WIKI / OUTPUT structure", or Karpathy's llm-wiki idea. Domain-agnostic (insurance, research, a book, a company, a hobby).
AdvancingTitans/agent-engineering-toolkit/skills/agent-engineering-toolkit Skill
2★ repoCompatibility entrypoint for AET Quick and advanced AET Lab workflows. Prefer the four dedicated Quick Skills for daily work; use this Skill only when the user explicitly asks for legacy CLI or Lab capabilities.
subhansh-dev/agent-maxxing/FINE-TUNE-AGENT Skill
2★ repoMaster instruction file — tells your agent how to read, apply, and integrate all skills from this repository to become a top-tier coding agent.
subhansh-dev/agent-maxxing/agent-meta/18-SKILL-CREATOR Skill
2★ 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.
subhansh-dev/agent-maxxing/agent-meta/init-project Skill
2★ repoInitialize a project's CLAUDE.md / AGENTS.md by analyzing the codebase architecture, commands, and conventions.
subhansh-dev/agent-maxxing/examples/workflow-landing-page Skill
2★ repoMulti-agent workflow for shipping a conversion-optimized landing page in one day.
subhansh-dev/agent-maxxing/system-prompts/01-agent-core-personality Skill
2★ repoModified agent core personality — merged from Claude Fable 5 and Opus 4.8 with Agent Maxxing engineering, reasoning, and anti-pattern layers.
subhansh-dev/agent-maxxing/system-prompts/02-coding-excellence Skill
2★ repoEngineering judgment, code quality, and editing patterns extracted from Codex GPT-5.5, Claude Code, and Gemini CLI system prompts.
subhansh-dev/agent-maxxing/system-prompts/04-frontend-mastery Skill
2★ repoUI/UX design rules, visual quality patterns, and frontend engineering extracted from Codex GPT-5.5 and Claude Design.
subhansh-dev/agent-maxxing/system-prompts/05-agent-orchestration Skill
2★ repoTool usage, sub-agent delegation, and multi-agent patterns extracted from Claude Code and Gemini CLI.
subhansh-dev/agent-maxxing/system-prompts/06-tone-communication Skill
2★ repoCommunication style, formatting rules, and response patterns extracted from Claude Fable 5, Codex GPT-5.5, and Cursor.
subhansh-dev/agent-maxxing/workflows/batch-orchestration Skill
2★ repoOrchestrate large parallelizable changes by decomposing into independent units and spawning parallel worker agents in isolated worktrees.
rakibulism/agent-skills-os/skills/design-design-handoff Skill
2★ repoGenerate developer handoff specs from a design. Use when a design is ready for engineering and needs a spec sheet covering layout, design tokens, component props, interaction states, responsive breakpoints, edge cases, and animation details.
The same file is in 3 other repositories
rakibulism/agent-skills-os/skills/mcp-builder Skill
2★ 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
rakibulism/agent-skills-os/skills/product-self-knowledge Skill
2★ repoStop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming), and Claude.ai (Pro vs Team vs Enterprise plans, feature limits). Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons. Any time you would otherwise rely on memory for Anthropic product details, verify here instead — your training data may be outdated or wrong.
The same file is in 19 other repositories
Productivity memory management
rakibulism/agent-skills-os/skills/productivity-memory-management Skill
2★ repoTwo-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
The same file is in 2 other repositories
rakibulism/agent-skills-os/skills/seo-dataforseo Skill
2★ repoLive SEO data via DataForSEO MCP server. SERP analysis (Google, Bing, Yahoo, YouTube, Google Images), keyword research (volume, difficulty, intent, trends), backlink profiles, on-page analysis (Lighthouse, content parsing), competitor analysis, content analysis, business listings, AI visibility (ChatGPT scraper, LLM mention tracking), and domain analytics. Requires DataForSEO extension installed. Use when user says "dataforseo", "live SERP", "keyword volume", "backlink data", "competitor data", "AI visibility check", "LLM mentions", "image SERP", "google images", "image rankings", or "real search data".
The same file is in 1 other repository
rakibulism/agent-skills-os/skills/skill-creator Skill
2★ 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.
fetchai/agentverse-skills/skills/agentverse-memory Skill
2★ repoGive any AI agent persistent, graph-native memory via Agentverse Memory — a managed MCP service with 35 JSON-RPC tools covering 4 memory types (episodic, semantic/graph, procedural, working) plus shared multi-agent memory spaces. Zero LLM at write time (<5ms writes, $0 ingest). Graph memory on every tier — including free. Hybrid retrieval (TF-IDF + dense, RRF-fused). Requires AM_API_KEY env var. Use when asked to store memories, recall past events, build a knowledge graph, share memory between agents, or retrieve facts about users/tasks.
campfront/camp-skills/skills/camp-aeo Skill
2★ repoWhen the user wants a summer camp to be recommended, cited, or surfaced by AI assistants and answer engines such as ChatGPT, Perplexity, Google AI Overviews, Gemini, and Copilot. Use for AEO, answer engine optimization, generative engine optimization, GEO, LLM optimization, getting recommended by ChatGPT, showing up in AI search or AI Overviews, getting cited by AI, llms.txt, or when AI keeps suggesting other camps. For classic search engines see camp-seo, and for the page copy itself see camp-website-copy.
F-e-u-e-r/opus-pack/skills/delegation-and-review Skill
2★ repoRules for delegating work to subagents and judging what comes back — when to spawn vs. do it yourself, how to write a dispatch packet, how to review agent-produced changes without rubber-stamping, when to retry vs. change approach vs. ask the user, and how to hand off long-running work across sessions. Load when about to spawn a subagent or write a dispatch prompt, when fanning out parallel work, when the diff you are reviewing was produced by an agent, or when work will outlive this session. Do NOT load for small single-context tasks — just do those under operational-rigor.
F-e-u-e-r/opus-pack/skills/skill-authoring Skill
2★ repoHow to write skills, CLAUDE.md/AGENTS.md, fix logs, and handoff documents that a weaker or zero-context model can actually execute. Load when authoring or updating any instruction file, SKILL.md, project memory, or institutional-knowledge document — including when converting lessons from a session into durable files — and when about to act on a recorded capability-negative ("no such flag", "the API can't do X") found in one. Not for writing user-facing docs or code comments.
VectorPeak/vectorpeak-agent-skills/knowledge-skills/ai-learning-mentor-vp Skill
2★ repoPersonal AI learning mentor for computer science, AI, LLM, and Agent topics. Use when the user asks with triggers such as 00, jy, 辅助记忆, 记忆, 助记, 01, gn, 概念, 概念讲解, 02, fm, 费曼, 03, lb, 类比, diff, 04, ky, lx, 题目, 出题, 刻意练习, 05, zs, tp, 知识图谱, landscape, 06, 总结, 提炼, 压缩, 卡片; supports memory aids, concept explanation, Feynman feedback, analogy-diff learning, deliberate practice, knowledge graph construction, knowledge compression, known-concept checks from LLM_wiki, optional multi-agent workflows, and optional DailyNotes integration.