Claude Code skill: turn rough trip plans (or nothing booked yet) into a fact-checked, mobile-first single-file HTML travel handbook (+ PDF).

Agent Kaizen skill for Claude Code & Codex: faithful, identifier-preserving reference for Ableton Live 12 (the DAW), Arrangement & Session views, clips, audio warping & tempo, MIDI/MPE editing, comping, recording, mixing, automation, instrument/drum/effect racks, Max for Live, Push 1 & 2, and Link tempo sync.

Practical agent skills for repeatable workflows and durable product or business context.

Production-grade Agent Skills for Web3 AI agents: 15 workflows, 6 MCP servers, DeFi/NFT/compliance guardrails, and VS Code/JetBrains installers.

Community-curated Hermes Agent skills, workflows, and reusable task automation recipes.

Agent skill: embed a local image/screenshot into a GitHub PR/issue comment automatically — token-only, no browser, private-repo-safe, no CI trigger

Agent Skills for Jellyfin media libraries, naming conventions, metadata IDs, and library maintenance

Bilingual SkillOpt-inspired Codex skill writer for SKILL.md creation, validation gates, bounded edits, and agent skill optimization

INFP-oriented Claude/Agent Skills for deep Chinese longform reading across AI, art & culture, and crypto sociology.

An AI engineering skill suite that takes one idea from Ideate → Spec → Plan → Implement → Verify → Review → Ship — the human owns intent, the agent owns execution, ending at risk-banded draft PRs. Installable across Claude Code, Cursor, Gemini CLI, and more.

Stop paying the king to do clerk work. Cost-aware routing across Claude Fable, Opus, and Sonnet.

Skill agentico para flujos seguros de comprobantes ARCA/AFIP en Argentina.

21 markdown-first software delivery workflow skills for Claude Code, Codex, and compatible agents. Standalone skill kit covering planning, debugging, CI, review, security, rollout, performance, data quality, and post-incident workflows.

Swarming your messy diffs before they reach production.

Walk through AI-written code with interactive HTML sequence diagrams.

Enforce Linux-kernel AI commit attribution (the Assisted-by: trailer) in git. A Claude Code plugin + portable agent skill.

Production-grade AI agent skills — enhanced alternative to addyosmani/agent-skills. 23 lifecycle skills for Define, Plan, Build, Verify, Review, Ship. Works with OpenCode, Claude Code, Codex, Cursor, Gemini CLI.

Random number generator agent skill using Python standard library

Multi-agent Lang-graph framework for autonomous software developement

Loom — a cross-harness, self-improving agent pack (OMP, Codex, Claude Code)

Product + Frontend Design 是一个面向 Codex 的流程型 skill，用来把 UI/UX 请求变成更稳定的两段式协作： Product Design 先定义用户、任务、体验闭环、词汇表、状态和验收标准。 Frontend Design 再把已确认的体验转成布局、层级、文案、交互细节和截图级打磨。 它刻意保持小而清晰。这个 skill 不替代 Codex Product Design 插件，也不替代 Frontend Design skill。它只负责固定两者的协作顺序和质量标准，避免 UI 工作变成功能堆叠或模板化界面。

Local-first CLI to scan, audit, route, and test Codex Skills.

Agent Skill for searchable decision ledgers, rejected approaches, skill/CLI routing, and evidence-based self-reflection

Use local Claude Code from Codex as a second opinion, reviewer, or parallel coding agent.

Personal agent skills, packaged for anyone to steal. SKILL.md format, works with Claude Code.

SciDraw AI scientific illustration skill for research figure generation in Codex and agent workflows

Unofficial port of openai/role-specific-plugins (Codex plugins) to Claude Code, installable as a plugin marketplace

Import Agent Skills from SKILL.md files in Vite.

Agent skills that give AI agents the operational competence of expert practitioners (Salesforce, AWS, GitHub Actions, web). SKILL.md format; Claude Code plugins. Not test-prep — certification is the scaffold and benchmark, not the product.

Create validated 3:4 Xiaohongshu knowledge cards with editorial HTML and slot-matched AI illustrations.

A Claude Code skill that spends extra models only when the risk earns it. One hard question goes to Claude + GPT + Gemini blind and in parallel; Claude judges, and the panel that actually ran is disclosed. Plus plan / context / review / orchestrate / handoff workflows. Runs on the CLI subscriptions already on your machine.

A Claude Agent / CoWork skill that reads, screens and rates applicant CVs from your inbox

Clean up raw video clips before editing: cut silence, transcribe subtitles (any language, Mandarin default), normalize speed, stitch in order. Ships as a Claude Code plugin + CLI for Codex.

One-shot Claude Code plugin to bootstrap an AI-agent documentation system (CLAUDE.md + rules + agent-guide).

CLDR-based Agent Skill for formatting currency, dates, numbers, units, and addresses across 20+ locales. Works with Cursor, Claude Code, and Codex.

Claude Code skill: 论文链接→PDF精读→分类→Zotero入库→Obsidian精读笔记

Certified Kubernetes Administrator (CKA) exam practice environment running locally, powered by Vagrant (VirtualBox) and Ansible.

Scenario-driven failure-mode analysis skill for AI coding agents (Cursor, Claude Code, Copilot, Codex)

Aegis — 12 judgment-style agent skills for secure, production-grade .NET on Azure (security, design, performance, concurrency, observability). Works with Claude Code, Codex, Cursor, Gemini.

Triathlon coach skill for Claude Code: pulls swim/bike/run + recovery data from connected fitness MCP servers (Garmin, Strava, Coros, Whoop, Oura, ...), computes CTL/ATL/TSB, ACWR & 80/20 distribution deterministically, and recommends your next session - with hard safety guardrails.

An agent-agnostic skill that bootstraps a versioned, file-system-based documentation workspace with a per-workspace AGENTS.md that governs the agent from then on.

Peter Zhou: 周伯通和 Peter Pan 的合体，一个面向学生的超级老师综合 skill

Open-source agent skills for Claude Code & the AI-agent ecosystem. Install: npx skills add yarrasys/skills@<name>. First skill: kdbx (per-project/per-env KeePassXC credentials).

An agent with subskills that audits, optimizes, tests, and self-heals agentic skills and prompt-based tools (Claude SKILL.md + Agent SDK / MCP).

Codex skill for AI product PM brainstorming, architecture, prompt discipline, and GitHub prototype research

Pre-delivery evidence gate for 12 AI coding agents: unsupported completion claims stay private until verified.

Don't ship half-baked. Don't ship invisible. — 6 content checks + 3 distribution checks. Pre-release quality gate for Claude Code skills.

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.

Full-stack Claude Code pack for marketers: FTC claim-substantiation, CAN-SPAM, deliverability, privacy & no-fabricated-metrics guardrails + skills for positioning, ad copy, landing pages, email, SEO, A/B tests & analytics, loops & review agents. Not legal advice.

Gives you a snapshot of the architecture of your vibe coded app

A Codex Skill that summarizes Codex Desktop updates, plugin and Skill changes, and not-yet-installed recommendations since the last briefing.

A composable Loop Engineering skill group for Codex and Claude Code - interview your task and emit a top-tier, paste-ready agentic loop (harness). 4 skills: spec, engineering, eval, review.

Replicable agent development system: curated Claude Code/Codex skills + bootstrap for the external tools (GSD, caveman, ponytail) that complete the stack.

Demand-first recommender for agent and Codex skills.

Glyph is a workbench for composing the forms intelligence takes today — and discovering the language it will speak tomorrow.

Fast reflexes, deep memory, no drift.

Agent Skill: build & manage a real hosted website for a user via Make A Website (hosting, domain, HTTPS, analytics, contact form included). agentskills.io standard.

Make every code change reversible. Multi-agent instructions, prompts, and evals for safer reviews, rollbacks, and migrations.

Unofficial Codex skill for HostEurope/KIS inventory and change preparation.

Accessibility guidance for AI coding agents — the complete WCAG 2.2 A/AA checklist (all 55 success criteria) + ADA legal context + a real audit procedure. Portable Agent Skill for Claude Code, Cursor, Codex & Gemini CLI. Fix accessibility properly, don't guess.