A Curated Knowledge-Base of AI Agent-Skills

Reusable, secret-free Agent Skills for product & engineering teams — turn messy notes into clean Jira tickets and more. 面向产品与研发团队的可复用 Agent Skills 合集 —— 把杂乱笔记变成规范的 Jira 工单,无需密钥。

Version-aware NgRx development skill for AI coding agents

Evidence-backed office commitment auditing Agent Skill｜协同承诺雷达

Paste a screenshot of any X post, type /x-this, get ready-to-paste replies in your own voice. No scraping, no auto-posting.

Composable AI agents and skills for operating Azure Database for PostgreSQL Flexible Server - PostgreSQL can be used for everything.

OpenClaw / Cursor 社媒运营技能集：热点选题、多平台改写、数据复盘，让内容运营形成可持续增长闭环。

Evidence-first skills and deterministic checks for auditing empirical research

AI-friendly local WeChat Mini Program documentation skill with 3,529 indexed Markdown pages

Intentwright turns rough intent into approval-bound, testable Codex /goal packages through a deep adaptive interview.

A safety-oriented project-memory bootstrap Skill for Windows Codex workflows, with synthetic demos, rollback safeguards, and privacy-scanned tests.

Adaptive Agent Skill for coordinating GitHub repositories across accounts, organizations, tools, and code or non-code work.

Reusable agent skills for automated coding workflows across languages and frameworks.

Structure-first wireframe exploration skill for Claude and other AI agents.

Agent skill: bootstrap & sync five root context docs (AGENTS/PRODUCT/DESIGN/TODO/PROMPT) for Vibe Coding | 项目五文档基建技能：初始化/更新/同步五份根级上下文文档

A curated collection of reusable agent skills for design, research, browser automation, and developer tooling.

An Agent Skill for upgrading UI/UX, visual hierarchy, interaction, and motion in real frontend projects.

Agente Smith — agente de práctica jurídica argentina para Claude Code (Defensoría de Pobres y Ausentes · CABA/Nacional · Jujuy · Salta)

Agent skill for Claude Code and Codex: merge stacked PRs safely with the gh CLI - retarget children before deleting base branches, confirm MERGED state before branch deletion, and recover auto-closed PRs with supersedes PRs.

Any design intent in (text, picture) → execution-ready 3D blueprint out — construction- and 3D-print-verified. Game design · simulation · architecture (3DCP+AI) · interior · landscape.

Portable PRD-first, architecture- and design-system-aware Agent Skills for verified multi-model development across Claude, Gemini, and OpenAI Codex.

Turn creator expertise into a validated knowledge business.

Agent 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.

Agent Skills for authoring Zwift workout (.zwo) files — hard-earned format mechanics from testing against real Zwift. Installable as a Claude Code plugin.

Community agent skills for safe, behavior-preserving refactoring (OpenCode, Claude Code, and any SKILL.md-compatible agent)

Reusable agent skills for Codex, Claude Code, and compatible AI coding agents.

Agent skills, SDKs, and integration docs for Immersive Commons (immersivecommons.com) - Floor 10, Frontier Tower SF. Includes .claude/, .cursor/, .windsurf/ agent configs.

PM planner for scroll-world immersive landing pages -- brand story, scene design, director script

Agent Skill for GitHub Actions root-cause diagnosis, safe retries, bounty checks, AGENTS.md audits, and MCP schema drift via x402

Agent skill for Claude Code and Codex: safely recover from stale 0-byte .git/index.lock files left by sandboxed git on Windows - a five-point pre-delete check, TOCTOU-aware bulk cleanup, and --no-optional-locks prevention.

Personal collection of reusable AI-agent skills for Codex and compatible runtimes

JEBI AGENT: clean handoff Skill for successor Codex chats

Generate static onboarding and architecture documentation for codebases

Skills for refactoring and optimizing React and Vite applications.

Keep secrets out of agent context while giving local commands scoped access.

Skilltopia is a desktop and web app for discovering, reviewing, and installing agent skills. It helps developers browse the public skills catalog, inspect skill details and audit metadata, and manage locally installed global skills from one interface.

Selection Bridge is a lightweight VS Code extension and companion agent skill that lets Codex, Claude Code, and other terminal-based coding agents resolve references like “this selection.” It shares only file and range metadata, then lets the agent read the saved content directly from the local or remote workspace.

Markdown task-tracker system for Claude Code on long, multi-session academic projects

Reusable frontend code review skill with Quick, Deep, and Fix Review modes for Codex, Claude Code, and Cursor.

An evidence-driven, platform-independent Agent Skill for reviewing substantial code modules and cross-file features.

File-native project continuity and engineering standards for coding agents.

From-scratch, event-driven, resident Agent Team harness with durable recovery and inspectable context.

Agent skill: 32 product-design and viral-product principles with ethical guardrails

👁️ Give your coding agent eyes for 3D — MCP server that renders, inspects, and diagnoses meshes & Gaussian splats. Zero GPU/OpenGL dependency.

输入服务范围、工时和成本，算出不亏底价与报价区间，生成三档方案、报价单和客户话术。

Measured prompt iteration with train/test dual-gate scoring and anti-overfit rails. Agent Skill (SKILL.md).

Drop-in OpenAI Codex skill that guides complete beginners from idea to working software through a perpetual loop workflow. 小白循环工作法向导（Codex 版）。Sister repo: loopwork-skill-claude-code

Claude Code skill that scaffolds the Ralph autonomous build loop: spec-interview to prd.json ledger to overnight self-driving builds

Agent Skill: weekly self-improvement loop for AI coding agents, analyzing their own local session logs (Claude Code, Codex, and more)

Claude Code skill + subagent for staged, evidence-gated rolling Splunk Enterprise upgrades across dev, test, pre-prod, and production.

A cross-platform Agent Skill for keeping observations, decisions, actions, and outcomes aligned with reality.

A factory for Claude Code skills. Nothing ships untested.

Agent skill for digital-product design across websites, web apps, iOS, and Android — UX research, journeys, IA, interaction and state design, visual direction, design systems, scored critique, and frontend-ready handoff.

Claude Opus and Fable prompt engineering skill for focused frontend design, UI/UX, visual implementation and screenshot iteration

Makes your AI agent answer like a briefing to a busy, skeptical boss. Conclusion first, no padding, no agreement it doesn't mean.

Cross-client Agent Skill for numbered visual task briefs and completed-delivery HTML reports.

Portable evidence-based handoffs for AI agents

Brand-neutral Microsoft Clarity MCP, warehouse, CLI, and agent skill toolkit

An evidence-led template for turning app reviews into product research hypotheses.