Context & AI engineering
26,474 rows, by stacks then stars
2,072 of these skill files have been read, by 1,193 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
LechuanWANG/pm-skill/pm-skill Skill
no license1★ repoCodex skill for AI product PM brainstorming, architecture, prompt discipline, and GitHub prototype research
knowledgeco/handoff-tracker Skill
1★Structured decision handoffs for multi-model orchestration: surface the options, recommend one with honest tradeoffs, leave the choice to the operator — an append-only trail that doubles as a recovery map and a human-authorship record. A model-agnostic AI agent skill. MIT.
tjboudreaux/rosetta/skills/rosetta Skill
1★ repoReconcile every AI coding agent's conversation history (Claude Code, Codex, Gemini, Cursor, Aider, opencode, Cline +11 more) with git & docs into one cited ground truth — and generate ADR/PDR/BDR decision records. Local, deterministic, zero-deps agent skill.
LFTPadilla/agent-dev-kit/overnight-task-kit/skills/multi-harness Skill
1★ repoReplicable agent development system: curated Claude Code/Codex skills + bootstrap for the external tools (GSD, caveman, ponytail) that complete the stack.
xxzxzmai-droid/dify-builder-skills/dify-agent-builder Skill
no license1★ repoCodex/Claude skills for generating Dify agents and plugins
paniolo-ai/scan/.agents/skills/paniolo-config-init Skill
1★ repoThin agent adapters for @paniolo/scan — run the AI Technical Debt Scanner from any coding agent and optionally remediate findings. Portable skill (npx skills add paniolo-ai/scan --all), Claude Code plugin (/paniolo-scan), Antigravity workflow, GitHub Action. Not the scanner source.
Aaryan-Kapoor/coding-agent-handoff Skill
1★Skill that turns a chat conversation (claude.ai / ChatGPT) into a brief any coding agent can build from
yuecao365/agent-codebase-analysis-skill Skill
1★Analyze LLM agent codebases as architecture reports.
Tatendaz/yapui Skill
1★Yap at your UI — live HTML preview with a two-way feedback loop, as a Claude Code skill
hangzhouxiaozhu/agent-sentinel Skill
1★Agent Sentinel:让 AI Agent 跑得更稳、装得更安心、协作更专业的本地保障层。诊断环境、网络与资源;安装前审查第三方 Skill 的恶意或高风险信号;崩溃或上下文中断后提供本地恢复简报。
rahulkolekardev/agentctx/skills/agentctx Skill
1★ repoMake your repo agent-ready for Claude Code, Codex, Copilot, Cursor, and AI coding agents.
pablodiazjorge/prompt-forge/.github/skills/ai-engineer Skill
1★ repoDrop-in toolkit that gives AI coding agents persistent memory across sessions. Agent Skills, cross-session learning loop, and knowledge persistence. Zero dependencies, no backend.
adjcjh777/agent-bus-skills/skills/agent-bus-delegate Skill
no license1★ repoCodex Agent Bus skill family for local multi-agent coordination
Pointa-Labs/who-am-i-skill Skill
1★Who Am I Skill — personality tests ask 60 questions; your machine already heard 8,000 answers. A skill that turns your local AI conversations into an evidence-grounded self-portrait. Local-only, zero deps.
TheColliery/CoalBoard/plugin/skills/coalboard Skill
1★ repoConsensus & debate board for error-not-allowed work: diverse lenses either verify new work before it ships (Generate), or inspect existing work and report findings (Audit/Review). Bounded cost + zero-breakage. Cross-agent - validated on Claude Code + Antigravity. Part of TheColliery.
yaoxiao99/local-memory-skill Skill
1★A fully local Markdown memory system for AI agents. No cloud, no lock-in.
bwdurst/rule-curator Skill
1★Audit and prune the standing rules a project operates under (CLAUDE.md, memory, AGENTS.md, ADRs, conventions) in one whole-corpus pass.
affectionatec/agentic-engineering/skills/agents-md-template Skill
1★ repoDocumentation-first development for AI coding agents — 8 skills: persistent memory, zero-ambiguity specs, append-only decisions, and an independent verification gate. The harness layer for long-running, loop-driven development.
TravorShelby/content-to-prompt Skill
1★Agent Skill for turning reference media into reusable prompt packs, shotlists, video packaging prompts, thumbnail prompts, and content systems.
Shavy72/auto-polish-skill Skill
14 days old1★Factorial design amplification skill for Claude Code — 5x → 10x → +3x staged UI polish with adversarial design judges
t3chnaztea/home-assistant-skills/skills/ha-automations Skill
25 days old1★ repoAgent skills for Home Assistant: connection doctrine, instance mapping, verified automations, and price/LLM-driven triggers. Claude Code plugin marketplace included.
potocibi/skills-manager/skills/skill-manager Skill
1★ repoYour Claude Code skills, deduplicated. Audits 100+ hoarded skills down to the few good ones - merges duplicates, routes tasks to the right skill, gates new installs. Plain English, never deletes, 2-command install.
Codex internal agent orchestration
FairladyZ625/codex-internal-agent-orchestration Skill
24 days old1★Codex internal agent orchestration for projects using Harness Anything.
SYMBaiEX/skills/skills/claude-multi-agent Skill
1★ repoPublic Agent Skills (agentskills.io spec) — portable SKILL.md capability packages
Xerneas216/ProCraft/skills/procraft Skill
23 days old1★ repoCraft reliable prompts for everyday tasks, tool agents, and software work.
Kinghonga/harness-engineering-init Skill
1★A standard agent skill to adopt & sustain the harness-engineering paradigm on any project — scaffold the .harness/ loop, keep it alive, make it self-improving. 在任意项目落地并持续运转 harness engineering 范式的标准 skill。opencode / Claude Code / Codex / Trae.
dimsedra/moatcraft-skills/.agents/skills/agentic-dev-loop Skill
14 days old1★ repoCreate software that is truly your own.
honminhAC/agy-subagents-skills/skills/agents-md-improver Skill
13 days old1★ repoA set of agents and skills for Google Antigravity CLI, focused on software engineering work.
14BryanEspinoza/agent-stack Skill
22 days old1★Skills modulares para asistentes de codificación por IA. Define reglas, flujos de trabajo y estándares técnicos mediante archivos Markdowm.
HiMyNameIsDavidKim/prompt-triwizard-skill/skills/prompt-triwizard Skill
24 days old1★ repoLLM prompt engineering for agent pipelines · Write, refine, and evaluate · 3 output styles: Anthropic · Google · OpenAI · Works with Claude Code, Cursor, Codex CLI, Gemini CLI & more · MIT
Paldom/github-skills/.claude/skills/add-skill Skill
1★ repoAgent Skills for professional GitHub repos - brief, structured, SEO-friendly READMEs that convert visitors into users, plus complete OSS scaffolding: community health files, templates, and discoverability best practices.
2702207741-dev/agent-skills-pipeline/agent-config-reference Skill
1★ repoGoverned, replay-tested agent skills for Codex-style maintainer workflows.
kxdds/sdd-tdd/skills/bootstrap-sdd-tdd Skill
28 days old1★ repoOne skill to bring Spec-Driven + Test-Driven Development (SDD+TDD) to any AI coding agent - OpenSpec x Superpowers bridge for Cursor, Claude Code, Codex, OpenCode, Gemini CLI and more
SiteVisorCloud/bifrost-gateway-integration-skill/skills/bifrost-gateway-ru Skill
24 days old1★ repoBilingual Claude Agent Skill + examples that route every LLM call (OpenAI, Claude, Gemini, DeepSeek, Grok, Perplexity) through one OpenAI-compatible Bifrost gateway for central logging. Python/PHP/Laravel/JS/curl.
ksed8/cc-loopkit/.claude/skills/agent-llm Skill
1★ repoLoopkit for Claude Code - guardrails, hooks, and two loop modes that won't let a task "finish" until it's actually done.
YanhanLi/deai-zh-gpt-style/skills/deai-zh-gpt-style Skill
18 days old1★ repoMake Chinese and mixed Chinese-English text sound more natural by removing formulaic GPT-style phrasing.
bsq415/research-rigor-skill/skills/research-rigor Skill
14 days old1★ repoHuman-led, evidence-gated full-cycle research execution for Codex and Claude Code · 人类主导的科研全流程辅助工具
P-Essonam/clicsdev/skills/clics Skill
16 days old1★ repoAgent skills for Clics: privacy-friendly, cookieless web analytics. MCP server and CLI for AI assistants.
SuperLogicAI/production-agent-design Skill
16 days old1★Architect high-reliability, logic-driven AI agents for production.
CodingCossack/writing-gpt-5-6-prompts Skill
27 days old1★Agent-agnostic skill for writing lean, outcome-led GPT-5.6 prompts across coding agents.
basuev/pi-prompt-refiner/skills/refine-prompt Skill
25 days old1★ repoContext-aware prompt refinement for Pi using GPT-5.6 Luna through a Codex subscription.
hashiruu/agent-experiment/skills/agent-experiment Skill
12 days old1★ repo一个 7×24 小时不间断运行,帮你跑实验、用 Git 维护公开仓库、更新 LaTeX(Overleaf)论文的科研自动化工作流。实测效率提升 25 倍。Claude Code Skill,一条命令装进任意项目。
linellazatin/openclaude-memory/skills/memory Skill
18 days old1★ repoGlobal persistent memory for OPENCODE sessions. Inspired by Claude Code's auto-memory — your agent remembers what it learns, across every session, globally.
izzipizzy/aparser-mcp/skills/aparser Skill
17 days old1★ repoMCP server for the A-Parser HTTP API — drive parsing tasks (SERP, positions, suggests) from an AI agent. TypeScript, stdio, npx.
stone623101-cloud/opencode-commander/plugins/opencode-commander/skills/opencode-commander Skill
25 days old1★ repoCross-host skill for Codex, Claude Code, and Cursor that orchestrates parallel OpenCode agents with optional iTerm2 split panes.
AgentPilotLab/agent-lean-safe-coding Skill
no license1★Windows-safe lean coding skill and plugin package for Codex, Claude Code, and AI agents.
anmolg1997/prepostmortem-skills/ai-incident-analyst Skill
1★ repoPre-mortems and postmortems for AI coding agents: 261 tagged real-world incidents + a 12-class agentic-AI failure model, shipped as Claude Code skills.
avnath13/agentify/agentify Skill
24 days old1★ repoTurn a use case into a grounded agentic system design. An opinionated AI solutions architect as an agent skill.
inbusiness23/fde-skill/skills/fde-copilot Skill
16 days old1★ repoPrivacy-safe forward-deployed engineering skills for Claude Code, Codex, and AGENTS.md-compatible agents
code-wahaha/project-orchestrator-skill/skill/project-orchestrator Skill
23 days old1★ repoAgent-neutral project orchestration skill from idea to delivery
sduhantao-maker/resume-handoff Skill
1★Session-handoff skill for agentic coding assistants — writes a living HANDOFF.md so a fresh agent can continue unfinished work. Checkpoint as you go.
longligooo/pdf-to-editable-word-skill/skills/pdf-to-editable-word Skill
18 days old1★ repoPortable Agent Skill for converting PDF to editable Word/DOCX while preserving layout. Works with Codex, Claude Code, other AI agents, and local CLI.
T0mSIlver/skills/claude-remote-control-server Skill
1★ repoSkills that let a coding agent delegate work to another coding CLI, and keep itself in sync from git.
Paldom/icon-designer-skills/.claude/skills/add-skill Skill
1★ repoAgent Skills that design minimalist app and OSS package icons from a text brief or project context - symmetric logos on dark grey, Apple-style rounded-rectangle backgrounds.
yysxjz/idea-spark-agentic Skill
18 days old1★Agentic variant of the idea-spark skill (microsoft/ResearchStudio): Claude Code sub-agents with WebSearch/WebFetch replace API connectors - no API keys required
yesman-engineer/codebuddy-acp-bridge Skill
12 days old1★Portable Agent Skill for delegating bounded AI-agent tasks to local CodeBuddy through ACP.
motiful/ctx/skills/ctx-adopt Skill
1★ repoThe agent context layer — converge messy multi-session AI-agent work into one lean, LIVING, spec-centered source of truth that doesn't rot. Organize docs by lifetime, keep the spec generative, and let an agent (or a human three months later) build from it.
jasperkong1996xx/prompt-master-for-anything/skills/prompt-master-for-anything Skill
18 days old1★ repoBilingual prompt compiler: one rough idea to Concise Universal + Advanced Max, without invented AI capabilities.
wei63w/skill-monitor/skills/skill-monitor Skill
18 days old1★ repoTrack Agent Skill usage, estimated tokens, Rules/AGENTS.md bloat, and Task/sub-agent startup cost. Install: npx skills add wei63w/skill-monitor
Codex windows sandbox troubleshooting
h8nc4y/codex-windows-sandbox-troubleshooting Skill
22 days old1★Agent skill for Codex on Windows (installable for Claude Code too): triage sandbox startup failures by layer - CreateProcessAsUserW error 5 on the agent execution path, Git Bash/MSYS2 Win32 error 5 incompatibility, elevated setup-helper ACL failures, and config.toml permission tokens that can brick every session.