RepoKit — a reusable repo standard + /new-repo scaffolder, packaged as a Claude Code plugin

Shape Up for coding agents — with gates the agent can't talk its way past. A Claude Code plugin that runs idea → pitch → build → eval → ship, with PreToolUse hooks that hard-deny a premature EVAL and progress derived from test artifacts instead of self-report.

Install agent skills once across all your AI agents via a shared skills hub (npx skills).

The open OS for building an AI-native company in hard-mode sectors. A 15-chapter Handbook, a 90-term Dictionary, and 24 runnable skills for Claude Code, Codex, Cursor, and Gemini. CC-BY-4.0 / Apache-2.0.

Codex skill for GPT Image 2 generation and editing with an isolated API key

A DESIGN.md standard for type-led technical launch pages.

Checkpoint-workflow plugin for Claude Code: commit, save memories, refresh a source-verified living doc, and emit a post-compaction rehydrate go-block.

Open Claude Code plugins for shipping AI output that's actually good. By Josh Matthews / LogicLeap Ltd.

Agent Kaizen skill for Claude Code & Codex: faithful, identifier-preserving reference for AWS Lumberyard and CryEngine-family tooling, editor, asset pipeline, Cloud Canvas & AWS gems, Lua; entities, components, EBus, slices, prefabs; CGA/CAF/CHRPARAMS animation; MTL materials, shaders; VFX; Wwise/ATL audio. Archived; O3DE successor.

TYPO3 site/project conformance skill — deployable repos (type:project + Docker/Compose): layout, containers, Concourse CI, supply-chain, secrets, Valkey/ofelia. Sibling to typo3-conformance.

库里投篮技术训练体系

Korean business-document skill (docx/pptx/xlsx/hwpx/pdf) with company branding, deterministic office-gate + OfficeCLI render verification - /superoffice for 팀장·경영자

CLI and agent skill for the JobsPipe API: search live job postings and scan a company's tech stack. npx skills add jobspipe/jobspipe-cli

Agent skill for routing small-molecule design tasks to open tools, focused references, and license-aware implementation paths.

🧭 AI Agent Skill for lost-item search using Meihua Yishu — works with Claude, Cursor, ChatGPT & Gemini

Installable Agent Skill for software design review, refactoring, architecture boundaries, testing strategy, debugging discipline, and maintainable coding-agent workflows.

Signal Lens — context-first maintainer PR review (Skill, CLI, Action, optional MCP)

Behavioral execution framework for AI agents — define deterministic, portable skills & agents across OpenCode, Claude Code, Gemini CLI, and Qwen Code.

Runtime seccomp-style per-call capability sandbox for installable agent skills — declare what each skill may touch, enforce it at the call site, trap+log violations.

A template for building your own AI-powered knowledge worker workflow using Claude Code and MCP.

deterministic-design — a Claude Code skill that renders your UI and proves it's balanced + usable: deterministic layout audit + vision-judged usability.

Skills that are authored by me.

Always-on skill pack that stops AI coding agents from claiming work is done when only the code path (not the real behavior) was verified. Portable SKILL.md for Claude Code, Codex, Cursor, and any agent.

🧪 QA Testing Kit — lifecycle-driven Agent Skill for manual & automation testing. Playwright, Selenium, Appium. Generate test cases, automation scripts, locators, test data & flaky analysis. Compatible with Claude Code, Cursor, Kiro, and 40+ agentic clients.

Codex plugin for scientific computing

全球高级定制化 AI 旅游攻略 Skill Pack — 9 skills, zero API key, Hermes/Cursor/Claude compatible

Agent Skill that turns fixed OSS issues into reusable bug patterns, then reviews local code with file/line evidence.

A murder-mystery game for Claude Code, refereed by an AI that genuinely can't see who did it. The culprit is sealed to disk and only revealed through scripted output and forked context.

Scientist agent mode for AI coding agents — hypothesis-driven, evidence-based, uncertainty-aware.

🛒 Мини-исследование закупки по российским маркетплейсам (Ozon, Wildberries, Yandex.Market) — сравнение цен/отзывов, отсев мусора, поиск оригинала. PHP + Playwright, без окон. Agent Skill.

The why behind your code, as plain markdown in your repo. Agent skill to capture decisions, dashboard to browse them.

Local-first prosody analysis skill for voice memos and speech recordings

Agent skill: find & qualify expired/auction domains by SEO metrics via the CatchDoms MCP server (free, no API key).

Agent Skills for Claude (Claude Code / Claude Desktop): Chrome Web Store asset generation, paid-app Stripe licensing with offline-verified keys, and ServiceNow update-set QA + ATF test generation.

Claude Agent Skill: audit a repository's real info and update its README + related docs into a standardized structure — grounded in the repo, never fabricated.

Agent Skill for turning refund, subscription, and billing disputes into clean case packs.

情绪.skill：从授权聊天记录分析情绪模式、关系意义和边界问题，并生成聊天建议与 Obsidian 复盘笔记。仅限非商业使用。

collection of reusable engineering skills for AI coding agents

My Public Agent Skills

delegate-skills — Offload implement / investigate / git tasks to cheaper models. File-based md2idx protocol keeps the main agent's context lean.

🦾 Skills for App Store Connect metadata, screenshots, App Review details, and regional pricing audits

AI agent skill for TestRail REST API - zero dependencies, security-friendly alternative to MCP servers

Planning-first, edit-later. A reusable skill that brings plan-mode behavior to any AI coding agent — preventing premature edits until you approve.

A Codex skill pack for long-running project work

Production-grade SaaS UI skills for AI coding agents (React + Tailwind + shadcn/ui) — Codex, Claude Code, Cursor, OpenCode. One npx command to install.

A lightweight Codex meta-skill for skill routing, Goal/Plan mode selection, and read-only-first safety checks.

Document-driven agent pipeline for software R&D: analyze → plan → review → develop → test. Portable skills for Cursor, Claude Code & Codex.

Loop + Goal Agent Skills by Saido Labs: a Plan-Build-Test-Reflect-Improve project cadence (/loop) and an objective-mode driver (/goal) with persistent .md state. Works in Claude Code and Cowork.

Standardized AI Looping Language

CLI tool for sub2api admin API — covers all 323 admin endpoints

autoskills is a smart meta-skill for Claude Code. It searches both your local skill library and the online ecosystem, scores candidates with a quality rubric, recommends the best fit, and builds persistent memory across projects.

AI agent skills for everything after the AI builds your app — launch, get users, grow. Works with Claude Code, Cursor, Windsurf.

Portable agent skills for building honest AI-tool income systems — the agentic-income brain + affiliate-audit. Claude Code / Cursor compatible.

Evidence-first video understanding skill for Codex: yt-dlp, Douyin SSR fallback, local whisper.cpp, keyframes, OCR, and grounded reports.

Portable Agent Skill and npm CLI for building complete project documentation packs from a brief.

skillet — a package manager for AI agent skills (SKILL.md). Find, install, version & share skills from a Git-backed registry. Zero infra, MCP-native, reproducible.

Agent skill that speaks replies aloud with Kyutai Pocket TTS - fast time-to-first-word, runs on CPU with zero config, clone any voice

Evidence-based meta-skill for creating, judging, and improving agent skills (SKILL.md). Distilled from a 1400+ skill corpus study; 73 citation-verified exemplars.

Teaching AI to reason about design — a perceptual psychology framework for visual communication. 24 heuristics, 8-dimension rubric, MCP server, works with every coding assistant.

Fork français du skill Claude Code « humanizer » (blader/humanizer, MIT) — 33 motifs d'écriture IA adaptés au français