Open Agent Skills for PersonWise

独立、可移植的 Godot 4.7 Codex 技能集合

Portable OpenShift agent skills for OpenCode with MCP-first Day-2 workflows, live API discovery, and offline OCP 4.20 documentation.

The mod pack for AI coding agents. 12 battle-tested skills. One install. Seven platforms.

A portable workflow-governance skill for making high-consequence agent operations authorized, bounded, reversible, and auditable.

Codex skills for incremental YouTube transcript collection, podcast deep analysis, and multi-source topic research.

Original cross-agent skills by J03Fr0st. Repository shell based on mattpocock/skills; no upstream skills included.

MiroFish-derived skill-native simulation for Codex and Claude with local temporal memory and no project-initiated generation API

A Claude agent skill that renders live, clickable UI style previews inline — pick vibes, palettes, components & animations visually instead of from prose.

把扁平信息图按原视觉拆成纯背景、可替换图片和可编辑文本的 Agent Skill

An Agent Skill for auditing crypto product flows for missing states, safeguards, and recovery paths.

Test an agent skill's conversation like code — script-first specs, real sandboxed tmux captures with true ANSI colors, verify-and-sediment loop, capture-once/render-many replays

Cross-platform Agent Skill for evidence-based independent evaluation across Codex, Claude Code, and Agy CLI.

Composable personal Agent Skills for Chinese official documents, engineering, and productivity

Whole-body anatomy and action-coherence quality control for human and hominin images

面向零基础转岗与市场新人的营销 Agent Skill：分析营销案例、训练面试表达、生成图文报告和营销方案。

Scientific research extension for apex-unified - 149 scientific skills for biology, chemistry, medicine, materials research. Powered by Scientific Agent Skills (31.4k star).

Research-first agent skill for source-backed SEO articles, refreshes, and audits.

Opinionated GTD workflow skills for AI agents — mind sweep, inbox audit, weekly review. Pure methodology; no task tool baked in.

Version your team's AI coding standards (skills + rules) as code, auto-sync them into Cursor, Claude Code and Copilot, and keep them fresh with a nudge -> skill -> PR loop. A GitOps-style starter template you can clone in under 5 minutes.

Practical agent skills for shipping real software

Evidence-driven skills that turn customer signals into measurable growth.

근거 중심 공모전 분석·아이디어 기획·제안서 검토용 Codex 스킬 모음

Source-blind simulated-user testing skill for Ego Lite on macOS

A personal collection of reusable AI agent skills.

Design Intelligence Router for AI UI design and vibe coding: interview-first UX, Art Direction, UI Briefs, design-system decisions, and bounded visual critique for frontend agents. 面向前端与 Vibe Coding 的访谈式 UI 设计 Skill。

An evidence-led, approval-gated workflow for producing product videos with ElevenLabs and HyperFrames.

Evidence-driven agent skill for authorized software reverse engineering, technical claim audits, and clean-room reconstruction.

Let your AI agent fetch your invoices from any vendor's billing portal — in the browser you're already signed into. A skill for Claude Code, Codex & ChatGPT.

A collection of skills for working effectively with AI.

Portable toolkit for authoring, validating, and synchronizing generic agent skills.

Intentionally vulnerable AI Agent Skill scenarios for hands-on learning, with detection via uncloak. Education only.

Agent skills for small and local models

Shared project memory across Codex, Claude Code, Kimi Code, Antigravity, and any coding-agent harness.

Memory-safe engineering-peer plugin for Claude Code + Codex: 11 skills, 6 bounded agents, 4 hooks. Claims only what it can prove; closes every turn with one next action.

Agent skill that prosecutes options instead of selling them (Cursor + Claude Code)

Persistent story-production projects for AI-native filmmaking: context, shot lineage, selective revision, and replaceable model adapters.

Cross-agent product exposure monitoring, social metrics refresh, comment sentiment analysis, and verified tracker updates.

Free open agent skills from MeshVault. Plain Markdown, approval-gated, MIT. Private AI staff on hardware you own.

Claude Code skills that gate a change before it's written: reuse what the repo already has, trace invalid state to the contract that produced it, and fix it there — not where the symptom shows up.

Free Amazon listing tools (skills, MCP) — compliant and sellable listings

Evidence-first UI alignment audit skill for AI coding agents (Claude Code / Cursor / Codex): real rendered evidence, typed findings, interactive A/B acceptance — without touching product code.

Turn an old iPad into a low-latency macOS extended or primary display with open-source tools.

A portable skill that helps AI collaborators check important assumptions, handle uncertainty, and choose a sensible next step.

Vibejar agent surface (MIT): CLI + skill + protocol. Paid capture app is $88 once at vibejar.com

NewbieCheng Team 的 Codex Skills 与 Plugin Marketplace：公开直连、一句话安装、Windows/macOS/Linux 校验

LLM-agent pipeline for formulaic alpha discovery on WorldQuant BRAIN, published with the full research archive it produced (archived)

A public library of things worth keeping.

A Design Gate for complex AI agent work: design first, execute second, preserve evidence always.

The "Long-Term Memory" for culinary AI Agents. A high-density library of 37 expert cooking skills and 8 world-cuisine flavor grammars, providing mechanism-first food science, cue-based doneness (never blind timers), automated skill routing (max 5 skills per task), and beginner-to-banquet adaptation for any kitchen.

Runtime-portability linter for agent skills and commands. Zero-dep, model-agnostic.

A Chinese Agent Skill for clearer reading flow, information hierarchy, and natural human writing.

Spec-driven AI development lifecycle for Claude Code — spec-kit + AI-DLC fused, with hook-enforced human-approval gates. Installable plugin + marketplace.

将任意输入改写为保真、紧凑、可执行且可验证的提示词｜Codex Skill + Plugin

Evidence-based Agent Skill discovery, verification, comparison, and installation across hosts.

Validate AI coding assistant skills against the Agent Skills specification (agentskills.io) — a dependency-free validator with fix hints, plus skills for auditing instruction quality and tuning description triggering.

Capture before-and-after evidence for every code change, including pure backend. The before must be captured BEFORE the edit. Agent skill for Claude Code, Codex, Cursor.

GRC skills for Claude Code and AI agents. SOC 2, HIPAA, ISO 27001 — field-tested by Cycore Secure.

Business-neutral Three.js architecture, implementation, audit, and TypeScript SDK skill for Codex.