Provider-neutral Agent Skills compiler, validator, projection generator, and safe downstream installer.

Static quality and security checks for SKILL.md-based Agent Skills.

High-speed cross-machine SQLite migration using dump + gzip + local rebuild. Replaces fragile rsync for GB-sized databases.

跨 Agent 的开源学习系统：把内容转化为行动、复盘与个人学习地图

Recover dormant repositories into evidence-backed comeback branches.

testing skill

Claude Code skill that keeps an AI's persistent memory correctly readable by both the AI and a human browsing it in Obsidian

Open-source GEO/AEO/SEO agent skills and plugins for the AutoXEO China-market workflow.

Agent skill: end-to-end app store release campaigns for Apple App Store, Google Play, and Huawei AppGallery — with the full China-market compliance chain (ICP App 备案 / 软著 / AI declaration / privacy labels)

Cross-agent skill for full-stack code-change impact analysis: trace every consumer, make the smallest complete fix, and verify regressions.

Local, reversible context doctor for Codex, ChatGPT Desktop, Claude Code, and Agent Skills.

16 Agent Skills pour transformer une idée en résultat clarifié, construit, prouvé, révisé et livré.

Unofficial, cross-platform Fable-inspired workflow skills for Claude Code and Codex, plus portable GPT prompt templates.

Codex-native diagnostics and configuration hygiene with approval-gated fixes.

Groundledger: MIT agent skills for Claude Code, Cursor & Cowork — grounded blog SEO/AEO, PROBE site SEO, SAFE paid media, SPARK editorial, SNAP social, ORBIT discovery

Two Claude Code skills — poc for fast clickable app mockups (mobile/web with side-by-side RWD preview), and kickstart for clean, scalable project setup.

Portable Agent Skills for deploying apps, open models, and coding agents on app.nz

Codex workspace organizer: AGENTS.md, skills, hooks, custom subagents / Организация окружения Codex.

Own, verify, and explain AI-assisted software changes

Agent skill for discovering and safely adopting skills, plugins, libraries, MCP servers, and open-source projects.

按城市查询中国 AI 创业补贴、算力券、产业园和孵化支持的本地 Agent Skill（preview）

Obsidian learning vault and portable Agent Skill for guided Java LeetCode practice.

Claude Code skills for code and security review of Go, Bash, Vue/TypeScript and PHP — human report plus a re-verifiable agent prompt block

Official Scrappycoco MCP plugin and portable agent skill

Evidence-based whole-repository review Agent Skill — development, validation, and deterministic release workbench

Your agent ships. You stay dangerous. A demanding code coach for Claude Code and Codex.

Repository-centered instructions, skills, memory conventions, client adapters, and lifecycle safeguards for consistent work across AI coding agents.

Local-first relationship memory vault with a headless crm CLI and installable agent skill

Hermes skill for realistic low-angle and high-angle wide portrait photography prompts.

Hidden, on-demand OpenCode subagent for Gentle-AI that orchestrates GitHub Issues, PR reviews, CI/CD diagnostics, traceability, evidence-based validation, and safe pre-merge decisions.

Safety-first Agent Skill for auditing and removing starter, boilerplate, template, and SaaS-kit residue with approval gates, external previews, backups, and rollback evidence.

Auditable AgentTeams multi-agent software delivery with contract-driven Skills.

Skills y herramientas para generar, validar y renderizar diagramas PlantUML

Self-tailoring skill that builds a personal AI knowledge vault for Claude Code or Codex — INDEX/MAP routing engine, git sync, cross-agent skill-linking. With or without Obsidian. No secrets, no personal data.

A beginner-first Skill for building your own VPN with Codex, with all expected costs explained upfront and every payment confirmed by the user.

Turns Claude into your app's worst user: an adversarial client-side chaos-testing skill for Claude Code. Nine personas, a strength dial, and reproducible bug findings.

将员工经验、专家方法和业务需求蒸馏为可安装 Skill 的对话式生成器

Generate AI-driven skills efficiently with a comprehensive toolkit designed for creating, managing, and deploying custom AI capabilities.

Self-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.

Forge: skill architect and builder — six-phase pipeline for designing, scoping, building, and validating agent skills.

Scan AI-related plugins and tools with 13 engines to quickly detect security risks and ensure safe installation before use.

Provide Claude Code with expert guidance to install, configure, and optimize memory-lancedb-pro for long-term AI memory management and retrieval.

Enable AI coding assistants to generate accurate Swift tests using structured testing features tailored to common LLM errors.

Provide and install pre-packaged plugins to extend Claude Code with new skills directly within your Claude environment.

Claude Code plugin to help write TableTest-style JUnit tests in Java and Kotlin

Round-trip CLI for your personal agent skills library — install, push, detect, fork.

Provide Go agent skills for cleaner, idiomatic code across Claude Code, Cursor, Copilot, and more with one install

Self-hosted push + ask-and-wait inbox for AI agents. Deploy your own on Cloudflare's free plan — agents send progress and ask you questions; you answer on your phone.

Two-role workflow for AI coding agents (Claude Code, Codex) over GitHub Issues, Linear or Trello: an analyst files evidence-backed issues, a dev claims and ships them. Race-safe claiming, per-run attribution, pluggable domain rule books.

支援 Codex 與 Claude Code 的通用 Agent Skill，涵蓋需求計畫、測試設計與 Git Diff 審查。

一套可以安装、迁移和持续迭代的人机项目协作章程。

Human-paced stealth browser skill for AI agents — drives CloakBrowser behind Playwright MCP. Works with Claude Code, Codex, Cursor, OpenClaw & any MCP-capable agent. Evidence-gated, authorized browsing only.

The Agent Skill for cross-browser extension development. Teaches AI coding agents to build, debug, and publish for Chrome, Edge, Firefox, Safari, and every Chromium- or Gecko-based browser.

Audit and remediate Claude Code network & telemetry leaks with zero-trace isolation.

Harness engineering, without the engineering. Grows your Claude Code agent config as you work, and prunes it before it rots.

Word search generator, crossword generator, and sudoku generator & solver in one local-first CLI — printable PDF puzzle worksheets, themed word banks, verifiable LLM evals, and agent skills. From the makers of puzzletide.com.

Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.

Read-only Remote MCP for externally grounded AI agent trust receipts.