A bilingual Codex skill for auditing and improving agent skills, workflows, prompts, and rule fragments.

8 battle-tested discipline skills that stop your AI coding agent from confidently shipping broken code — each with a verifiable done-criterion. Bilingual EN/中文.

A Claude Code skill that trims a project's CLAUDE.md to what is strictly necessary, replacing derivable or duplicated content with on-demand references to save context tokens.

A Hermes Agent skill for turning painful fixes into replayable benchmarked workflows

Codex skill for polishing frontend UI, responsive behavior, interaction states, and production-grade implementation

Agent Skills for PLATEAU 配信サービス. Auto-mirrored from eukarya-inc/PLATEAU-VIEW. Install via gh skill install Project-PLATEAU/skills <skill-name>.

51 production-grade Agent Skills for AI coding agents — full software lifecycle (idea → spec → build → review → ship → operate → maintain) plus Laravel/TALL/VILT/Filament stack workflows. Works with Elyra, Claude Code, Cursor, and more.

AEON skill pack for Solvr — AI-assisted formal verification work-order, grounded in live onchain intel. Inspired by Vitalik's FV essay.

Claude Code plugin / Agent Skills pack — verb-split skills for design, review, TDD, and PR flow, with deterministic git hooks as safety floors

Daily GitHub radar for AI agent skills, MCP servers, prompts, and agent-native developer tools.

Claude Code skills for computational chemistry — orchestrating atomistic simulations and molecular dynamics from natural language

Temporary email inboxes for AI agents & QA/E2E — MCP, REST, OTP/magic links. Cloudflare Workers, Neon, Resend. MIT.

A cross-platform natural language router for agent skills. Scans Claude Code, WorkBuddy, OpenCode, Gemini CLI, Codex, Cursor and more. Intent-aware routing with keyword, TF-IDF, and LLM matching.

Agent skills to keep AI instruction files (AGENTS.md, CLAUDE.md, MEMORY.md) lean. Guardian runs before edits to prevent bloat; cleanup restructures bloated files. Works with any AGENTS.md-aware tool.

An Agent Skill that helps AI agents produce high-quality standalone single-file HTML artifacts — judge, create, review, and improve

AI agent continuity for long-running work / 长任务 Agent 连续性工具

Curated agent skills, conventions, and workflows for building React Native apps with AI coding agents.

Biomedical SCI manuscript architecture skill with corpus-driven terminology and style profiling

Structured handoff documents to transfer context between AI chat sessions. Cursor / Claude Code / Codex skill.

Color-coded Codex prompt templates and Agent Skills for plugin-orchestrated AI coding workflows, MCP safety, repo intelligence, and automation.

Loadable skill and scaffold for building source-grounded agent harnesses

Publish local agent skills as clean, installable, promotion-ready single-skill GitHub repositories.

Skills for coding agents: engineering review, loop referee, skill auditor, unclebob. One SKILL.md per skill. Copy a folder and it works in Claude Code, Codex, or Cursor.

Auto-version local config files via git + OS file watchers. A drop-in skill for AI coding agents (Claude Code, Codex, Gemini CLI, etc.).

Prompt X-Ray for AI agent prompts and skills

Multi-Document Co-driven Agent Workflow for Claude Code — stop your docs from rotting. 中英文双语

Match The Venue（MTV）— 给国内城市的"高端培训/商学院/咨询/私董会"事件匹配最合适的酒店宴会厅，靠公开活动证据导航。喂活动链接（微信公众号/活动家/活动行/任意 URL）即可抽取"哪家机构 在 哪家酒店 办了什么课"，入库打分后输出选址推荐报告。当用户提到"找培训酒店"、"高管

Agent OS is a management layer for complex, multi-agent AI projects. Instead of letting agents get lost in endless conversational loops, it enforces a disciplined workflow: upfront planning, shared context, scoped work tracks, and strict quality gates — so every agent stays focused, coordinated, and aligned from start to finish.

Reusable agent skills and baselines for Claude Code, Codex, and Copilot, with deterministic install/verify tooling

Public skill library, workflows, tools, and references for AI-assisted development.

SDD design stress-test engine for AI coding agents. Pressure-tests your draft against edge cases, code constraints, and silent failures — one sharp question at a time. Outputs a Facet Brief that maps to openspec/speckit. Not a design generator — the last gate before the spec gets written.

Claude + Obsidian knowledge companion. A persistent, compounding wiki vault based on Karpathy's LLM Wiki pattern — drop sources, ask questions, knowledge compounds.

A Claude Code project that turns job searching into a structured workflow. Your career history, goals, target companies, and active applications all live in one place so Claude can reason across them. No more juggling Google Docs, Notion, and a dozen open Job Descriptions.

Curated AI skills and Claude Code plugins — reusable, versioned prompt templates and tools (skillshare/Codex compatible)

Create, validate, and ship Agent Skills in minutes.

Just a repo to sync my cursor skills, rules and commands.

Agent skill repository that don't fit cleanly into any of my other cheese-related repositories

Agent skills for academia research: writing, dataviz, publishing, communication, career, and more.

蒸馏大冰，如果你想找大冰帮忙梳理问题又没法儿直播排队上或感觉没聊透，不妨跟这个大冰AI 深入聊聊。

Agent Skill teaching AI coding agents to drive Apple Simulators via Evan Bacon's serve-sim — taps, gestures, hardware buttons, rotation, camera injection, and stream handoff to the host's preview pane (Claude Code, Cursor, Codex, ...).

12 thinking patterns for AI agents that catch each other's blind spots. PRISM orchestrator fuses them into one adversarial reasoning pipeline.

A Skill for AI Agents to gather On This Day entries from Day One, create an analysis, and upload it to Readwise Reader shortlist.

Portable Claude Code skill for managing Kanban boards as plain-markdown files in any project. Compatible with Obsidian's obsidian-kanban plugin, but works without it.

PM agent toolkit — three-layer architecture that turns one-liner requirements into industrial-grade PRDs. Agent-neutral rules for Claude Code / Cursor / any LLM.

Source-aware architecture guidance for business-domain systems using Domain-Driven Design, Layered Architecture, Onion Architecture, Hexagonal Architecture / Ports and Adapters, and CQRS.

Collection of Neurobro agent skills for financial market research

睿动 AI 智能体 UI 风格库 — Claude Code plugin。2 套风格（smartsolu-linear 克制工作台 + bold-vivid 高冲击力主题），让同一风格下的所有智能体配色字体自动一致。

Claude Code / skills.sh agent skill for NativePHP Mobile v3.0–3.1 — build iOS/Android apps with Laravel

Agent skills for the Orbis API Marketplace — 2,800+ x402-enabled APIs, pay per call in USDC on Base

Adversarial brainstorm skill — two AI models generate proposals as conflicting expert roles. Part of the Liangyi skill family.

🔍 Auditoria de segurança defensiva para Agent Skills (Claude, OpenClaw). Detecta payload em archives, ASCII smuggling, supply chain attacks e meta-prompt injection. Alinhado a OWASP ASI 2026 + AST01. Camada 1 da defesa em profundidade.

AI delivery acceptance and audit system for vibe-coded websites, web apps, and agent-built products.

Agent skills for the reopt ecosystem — CLI workflows, Brandapp SDK install/review, and @reopt-ai/opt-* component package setup. Installs into Claude Code, Cursor, Codex, Cline, Gemini CLI, and more via skills.sh.

智能体专用和风天气技能

Curated agent skills, conventions, and workflows for building Kotlin Multiplatform (KMP) apps with AI coding agents.

Agent skills for the backend-for-mobile layer: APIs, auth, push, sync, and BaaS integrations.

Stop your AI agent from guessing your design. Turns vague requests into structured constraint files that eliminate rework — works with Claude Code, Cursor, and Codex.

Official Agent Skills for integrating Masheev into your applications

Spec-driven, BDD-shaped project management for AI agents. OpenSpec proposals → BDD specs → tracked work in GitHub / Azure DevOps / Jira / Linear / GitLab.

A structured AI coding workflow with skills, agents, and commands that make AI think before it builds.