Governed multi-agent engineering for Codex. Bootstrap the bundled ai runtime and initialize each target workspace; empty workspaces are supported.

An evidence-driven Agent Skills suite for GPGPU performance engineering, from kernels and compilers to memory, resource, and runtime-state management.

GateData agent distribution: one-click MCP installer and Agent Skills for Cursor, Claude Code, and Codex.

Turn chart screenshots into native editable PowerPoint charts with embedded data, CSV export, and honest confidence reports.

Portable AI-agent skills for Claude Code, Codex, OpenCode, and Grok: Fan Solo — multi-agent orchestration, processes, and durable state for Solo (SoloTerm) — plus WebAuthn/passkey browser testing for Stellar smart accounts

Codex skill: turn photos of a real memory into reference sheets, a base frame, and paste-ready Dreamina (Seedance) video prompts

A skill and standing rules that strip AI flavor from writing — by targeting cross-language patterns, not a word list, precisely and in any language. 去 AI 味的 skill 与常驻规则:抓规律而非禁词表,精准不误伤,支持多语言。

Agent skill for authoring production jsonspecs rule packages

Governed Nutanix Prism Central v4 ops: clusters/VMs/storage/DR/LCM, ETag-safe, 47 MCP tools (preview)

Personal agent skills for AI coding tools (Claude Code, Cursor, Codex, Grok). Portable SKILL.md workflows I use day to day.

Create resumable, offline H5 games for Codoop from a plain-language idea — preview, validate, and package game.zip with a separate cover.png.

AI Design OS for agents: contract → direction → generate → audit + visual. Executable de-AI auditor + positive direction cards + Kansei vocabulary, as Skill + MCP + CLI. Apache-2.0.

Global Agent Skill for comparing tokenized-equity routes across CEX spot, perps, and Mantle onchain RWA

Evidence-driven, risk-ranked deep code review skill for Codex and Claude Code

Default-off Caveman mode, companion skills, and Pi-native stats for Pi Coding Agent

Agent skill: long video → viral vertical shorts — transcript-first clips, smart crop, captions, transitions.

Agent Skill for building on Robinhood Chain with Claude, Codex, and skills-compatible agents

focused workflows for building and maintaining aiogram bots

Source-aware BaZi and Chinese solar-term calendar Agent Skill with transparent calculation logic

A deterministic procedural generation toolkit for retro pixel sprites.

开源 AI 产品需求与 PRD Skill：生成产品决策简报、MVP 范围、验收条件、风险和未决问题。

Agent Skill for turning company SOUL into real-case-tested principles and a shared human/AI decision system

Agent skill: auto-generate a beautiful user manual whose screenshots are captured by committed scripts (Playwright for web, Maestro for iOS/Android) — one command regenerates the whole manual, so it never rots

Drive artifacts to book-shape: precommitted denominator, machine-enforced truth, stranger-first surfaces, one-voice scrape, adversarial rounds until a round finds nothing. The applied art distilled from real canonicalization drives, with receipts.

嘴替·画饼包 —— 专治老板画饼：把「明年肯定优先考虑你」翻译成「什么条件、什么时候、怎么兑现」。三档回复 + 画饼话术识别表。Made with 嘴替.skill

Bilingual (中文/English) output-compression skill for coding agents. Benchmarked against caveman and token-diet, and honest about the <1% ceiling.

Local-first project context, verification gates, and repo-scoped MCP for coding agents.

Japanese quality standards for software — first principles and pass/fail grades

Evidence-first Skill for writing, localizing, auditing, and visually validating public GitHub READMEs.

开源云安全事件响应 Skill：证据保全、事件时间线、影响范围、可逆遏制、恢复与复盘。

Agent Skill for deploying an AI-powered paper research radar for any academic field

Agent Skill for creating, validating, and packaging Windows CUR/ANI cursor themes from PNG or SVG.

Agent skill that finds hidden assumptions, risks, edge cases, and cheap validation probes before you build

The Cohesivity agent skill: on-the-fly backend infrastructure for AI agents. Install with: npx skills add cohesivity-org/cohesivity-skill

AI agent skills collection for web systems and app development

Codex skill for Excalidraw MCP App and Excalidraw+ workflows

Skills from Strandic for building software with AI agents, deliberately. Install via npx skills add strandic/skills or the Claude Code marketplace.

Tell your coding agent a topic. It builds you a dojo — a git repo that mentors you to mastery. An Agent Skill for Claude Code, Codex, Cursor, Gemini CLI, opencode, Amp, Zed.

Fidelity and granularity controls for AI coding agents — the judgment a seasoned engineering team would apply, made explicit. Execution control + surface control. Model-agnostic. MIT.

Official ideaLOCKIN plugin marketplace for Claude Code - free skills, steal them

Token-efficient AI agent skills with a warm alien-engineer voice: dense replies, professional commits, and concise reviews.

Codexの/goalを有効化する前に、レビュー可能なcompletion contractを作成・評価するSkill。失敗保存型の評価証拠、pure validation、bounded E2Eを収録（MIT）。

Point your coding agent at a website codebase: it writes user stories into Excel, tests them with Playwright, and writes the bugs back. Works with Claude Code, Codex, Kilo Code, OpenCode and GitHub Copilot CLI.

Agent skill for lab meeting reports, research progress updates, journal club notes, experiment retrospectives, and Markdown-to-Lark publishing.

Governed SolarWinds Orion + PRTG ops: canned SWQL, alert rollup, 31 MCP tools (preview)

Backup of my pi agent configuration: settings, custom skills, and npm dependency manifests.

Operational-hardening playbook for driving codex / opencode / agy headlessly and in parallel — the stdin deadlocks, silent empty reads, SQLite races, and truncated outputs the vendor docs never warn about, each with the one-line fix.

derive a design-system package from an existing codebase

Hermesskills — a curated marketplace & repository of AI-agent skills. OpenClaw-compatible catalog at /catalog/v1/skills.json. 30% of commissions fund public-good AI.

Agent skill: plan a native mobile companion app for an existing website — feature census, API contract design, design-language translation to native idioms, walking-skeleton roadmap. A twin, not a WebView wrapper.

Scene-specific AI workers for Codex and Claude.

zhizhi（知之）— let AI to know what you know. Three commands that find what you don't know you don't know.

A file-based multi-agent system for Claude Code: orchestrator, specialist agents, skills and playbooks as versioned markdown, capped per-agent memory, and a feedback loop. In daily use since March 2026.

Cursor agent skill: evidence-backed 5-year survival & moat forecast for any codebase — Durable/Eroding/At Risk/Terminal verdicts + PDF.

A senior product design partner inside Claude — open-source Agent Skill. From raw idea to validated, shipped, measured, growing product.

A self-improving AI Agent Skill that rewrites vague prompts into senior-level specs before building.

An Agent Skill that converts rough software requests into precise, execution-ready coding-agent prompts.

Local-first agent skills for Cursor & other AI coding agents — 100% on your machine, no cloud, no API keys. Apple-Silicon-tuned (MLX/Metal): local image generation, voice cloning, background music, talking-head video, video→3D splat & printable STL, web-action recording, and Word .docx editing.

Mine your coding-agent session history (Claude Code, Codex, opencode, pi) to discover and build the skills you or your team should create