Context & AI engineering
26,304 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
rogerchappel/agent-runbook-lint-skill Skill
0★Local-first lint checks for agent automation runbooks
Renga154/model-router Skill
0★Difficulty-based model & reasoning-effort auto-routing skill for AI coding agents (Claude Code, Codex, Agent Skills standard). BYOK.
Paldom/mcp-server-skills/.claude/skills/add-skill Skill
0★ repoAgent Skills for designing and implementing Model Context Protocol (MCP) servers - server architecture, tools, resources, prompts, transports, authorization, testing, and deployment.
Paldom/screenshooter/.claude/skills/add-skill Skill
0★ repoSkills for creating polished screen-recording walkthrough and tutorial videos of web apps, with smooth scripted mouse movements, zoom effects, and explanation cards.
TunaSaiko/prepare-project-handoff/plugins/prepare-project-handoff/skills/prepare-project-handoff Skill
0★ repoEvidence-backed, decision-scoped project handoffs for Codex
zhongmaomao/multi-agent/skills/multi-agent Skill
0★ repoAn Agent Skill for dependency-aware parallel work with clear ownership, coordination, integration, and independent verification.
oxfern/codex-first Skill
no license0★Claude Code implementation routing through Codex CLI, with Claude-owned specification, review, and verification.
zheyuanhu2-sketch/repo-reentry/repo-reentry Skill
0★ repoSwitch AI coding agents without losing project memory — verified handoffs, Git-aware checkpoints, and resumable repository state.
cristianmoroaica/bountyverdict/skills/audit-agent-harness Skill
0★ repoSeven x402 decision APIs and installable agent skills for GitHub bounties, CI, skill security, and MCP drift
NicholasSpisak/graph/skills/graph Skill
0★ repoPortable /graph agent skill for Claude Code and OpenAI Codex — drafts agent graphs (nodes, checkpoints, routes: a state machine) for the jobs you run every week, validated mechanically
h8nc4y/agent-handoff-docs Skill
0★Agent skill for Claude Code and Codex: a documentation framework for multi-session, multi-agent development - REQUIREMENTS / as-built ARCHITECTURE / REPORT / living HANDOFF split, START_HERE kickoff files, canonical-source discipline, and task ledgers that double as delegation specs. Bilingual (EN/JA) templates.
dm1681/skills/skills/orchestrate-olympus Skill
no license0★ repoVersion-controlled agent skills and cross-platform installers
yansircc/skill-manager/skill/sm Skill
0★ repoGit-backed SSOT and immutable skill projections for Codex, Claude, Pi, and other agents
edycutjong/linelock/skills/worldcup-linelock Skill
0★ repo🔒⚽ LineLock — pay-per-pick World Cup edge API on Injective x402: the USDC receipt IS the pre-kickoff timestamp; free public CLV ledger, losses included. Injective Global Cup 2026.
gz-ang/fable-legacy Skill
0★Model orchestration doctrine for Claude Code — route tasks across Opus 4.8 / Sonnet 5 / Haiku 4.5 / Fable 5, dispatch parallel subagents, and verify what they report back.
h8nc4y/isolated-worktree-pr-flow Skill
0★Agent skill for Claude Code and Codex: create PRs from a temporary git worktree off origin's default branch when the main checkout is dirty, behind, or shared with other agents - with merge-mode-aware cleanup guards.
ChiJian28/Touchline/.agents/skills/injective-mcp-servers Skill
0★ repoWorld Cup sideline AI agent on Injective — CCTP, x402, MCP, Agent Skills, and binary options in one workflow.
Paldom/stealth-browser-skills/.claude/skills/add-skill Skill
0★ repoAgent Skills for stealthy, human-like browser automation with Playwright and Camoufox — real-browser agentic browsing that evades bot detection.
lestermarch/postgres-ai-experts/skills/azpg-ai-in-database Skill
no license0★ repoComposable AI agents and skills for operating Azure Database for PostgreSQL Flexible Server - PostgreSQL can be used for everything.
archibate/agent-skills/skills/agent-browser Skill
no license0★ repoA curated collection of reusable agent skills for design, research, browser automation, and developer tooling.
Paldom/promptimize/.claude/skills/add-skill Skill
0★ repoAgent Skills for prompt optimization - tune prompts for the latest frontier models like Fable 5 and GPT 5.6, write effective goals and success criteria, and engineer agentic loops that converge.
Mimirs402/bountyverdict-mcp-skill/skills/route-github-agent-decisions Skill
0★ repoAgent Skill for GitHub Actions root-cause diagnosis, safe retries, bounty checks, AGENTS.md audits, and MCP schema drift via x402
kyutomatte/jebi_agent/skill/jebi-agent Skill
0★ repoJEBI AGENT: clean handoff Skill for successor Codex chats
aigeekops/shared-obsidian-brain Skill
no license0★alexclymo/claude-tracker-skills/skills/tracker-audit Skill
0★ repoMarkdown task-tracker system for Claude Code on long, multi-session academic projects
murphy977/3d-eyes/skill Skill
0★ repo👁️ Give your coding agent eyes for 3D — MCP server that renders, inspects, and diagnoses meshes & Gaussian splats. Zero GPU/OpenGL dependency.
yuanGao0816/prompt-rail Skill
no license0★Measured prompt iteration with train/test dual-gate scoring and anti-overfit rails. Agent Skill (SKILL.md).
fcavalcantirj/ralph-brow/skills/ralph-brow Skill
0★ repoClaude Code skill that scaffolds the Ralph autonomous build loop: spec-interview to prd.json ledger to overnight self-driving builds
shihchengwei-lab/session-analytics Skill
0★Agent Skill: weekly self-improvement loop for AI coding agents, analyzing their own local session logs (Claude Code, Codex, and more)
proluct/skill-press/skills/skill-press-polish Skill
0★ repoA factory for Claude Code skills. Nothing ships untested.
CodingCossack/writing-claude-design-prompts Skill
0★Claude Opus and Fable prompt engineering skill for focused frontend design, UI/UX, visual implementation and screenshot iteration
sonu07-star/agent-handoff-skill/skills/agent-handoff Skill
0★ repoPortable evidence-based handoffs for AI agents
stone16/stometa-skills/skills/doc-steward Skill
0★ repoCurated public Agent Skills with promotion evidence, portability checks, and repository-scoped integration guidance
SubliminalCoding/build-it-out/skills/build-it-out Skill
0★ repoHardened Claude/Codex multi-agent build board with sealed contracts and deterministic gates
Optimize claude fable 5 prompts
IchenDEV/claude-fable-5-prompt-optimizer/plugins/claude-fable-5-prompt-optimizer/skills/optimize-claude-fable-5-prompts Skill
0★ repoMoved to IchenDEV/prompt-optimizer-plugins. Historical Fable 5 v1.0.0 repository.
YMIR777/vibecoding-prompt-workflow/skills/prompt-first-workflow Skill
no license0★ repoA first-principles Vibe Coding prompt workflow for AI agents and chat models.
Chulinuwu/skillloom/skills/autonomous-learning Skill
0★ repoPrivate, local-first second brain for AI agents, with shared memory and governed skills across Claude Code, Codex, and your Tailnet.
neilchen2000-pixel/agent-skill-stack/skills/agent-skill-stack Skill
0★ repoBuild a minimal, audited Agent Skill Stack for end-to-end goals, with safe discovery, conflict checks, and runtime routing.
HustleCoding/clear-agent-communication/skill/clear-agent-communication Skill
0★ repoA Codex skill for clear, evidence-based agent communication
Acelogic/sharpemu-agentic-toolkit/skills/sharpemu-nid-swarm Skill
0★ repoEvidence-backed SharpEmu NID swarm, KawaiiDRA, Context Mode, and timestamped visual regression tooling
arkaigrowth/agent-skills/caveman-compress Skill
0★ repoNine production Claude Code skills and one command pack: repo security scanning, LLM-output validators, agent-fleet guardrails, credential hygiene. Deterministic cores, agentic edges.
wu1chenghui/hermes-math-template/skills/agent-memory-architecture Skill
no license0★ repoLiuHHHYuuu/agent-skills/skills/harness-engineering Skill
0★ repoHuman-led judgment and agent-executed harness engineering skills
wakamiya0315/delegate-to-claude/skill/delegate-to-claude Skill
0★ repoA cross-compatible Agent Skill for delegating bounded coding tasks from Codex or Claude Code to a supervised Claude Code Sonnet worker.
p404/monodraw-llm/.claude/skills/monodraw-llm Skill
0★ repoTurn ASCII architecture diagrams into native, editable Monodraw documents with Codex or Claude Code.
craxelfn/claude-to-codex-migrator/skills/claude-to-codex-migrator Skill
no license0★ repoClaude to Codex Migrator: convert Claude skills, plugins, and assistant packages into validated Codex packages.
patrikherak/llm-privacy Skill
0★Agent Skill: reversible PII tokenization — masks personal data before the LLM sees it, restores it in the final answer (SKILL.md, works in Claude Code and any agent)
lniass/social-skills/skills/social-agent-public-workflows Skill
0★ repoAutomate your social media with Handled Agent Skills: guided Facebook onboarding, posting rhythm, approvals, and Social Connect workflows. More platforms coming soon.
flamefalcon7/youtube-transcript Skill
0★Local YouTube transcription skill for AI agents — Whisper-always, self-improving vocabulary memory. No captions, no cloud.
TJCurnutte/cohort-method/.agents/skills/cohort-method Skill
0★ repoCohort Method — portable Agent Skill for multi-agent creative panels, UX swarms, build cohorts, and cross-QC (10 agents / 5 cohorts).
wretcher207/dead-pixel-skills/skills/codex-prompting Skill
0★ repoReusable agent skills from Dead Pixel Design, starting with an agent-agnostic Codex prompt compiler.
h8nc4y/multi-agent-delegation Skill
0★Agent skill for Claude Code and Codex that prevents silent no-op failures when delegating to subagents — mandatory prompt clauses, artifact verification, resume-based recovery, and ledger-as-spec parallel delegation.
avnath13/evalpilot Skill
0★Agent evals on autopilot: find quality bugs in your AI agent, ship a targeted fix, and prove it on a held-out set. Zero-dependency Agent Skill + CLI.
efaimo-ai/efaimo Skill
0★Audit what your agent loads: quality and context cost for MCP servers and Agent Skills
MaikoCode/brainrotshorts-agent-skills/skills/brainrotshorts Skill
no license0★ repoOfficial BrainrotShorts skills for AI agents using the MCP server and REST API.
pecigonzalo/agent-skills/skills/mcp Skill
0★ repoPersonal agent skills
Paldom/terminaltor/.claude/skills/add-skill Skill
0★ repoAgent Skills for recording, sanitizing, and rendering terminal session demos - capture real command walkthroughs with agents, redact sensitive output, and render polished casts for READMEs and docs.
SubliminalCoding/orchestrate-it-out/skills/orchestrate-it-out Skill
0★ repoGPT-5.6 Sol plans; exactly five Claude Fable 5 workers build with mechanical gates.
0xkaveh/debug-orchestrator/skill/debug-orchestrator Skill
0★ repoEvidence-led, security-first debugging skill for coding agents
Paldom/noslop/.claude/skills/add-skill Skill
0★ repoAgent Skills that strip AI writing tells from copy - em dashes, 'it's not X, it's Y' constructions, hedging, and bloat - so text reads like a human wrote it, with evals to verify.