Agent Skill for auditing Stripe checkout attribution, recovery, and funnel observability leaks

AI-HOTDog：面向 Codex 的热点选题雷达，生成带引用的 Top 10 热点和 Top 5 选题。

Evidence-bound GitHub writing skill for AI agents: 18 artifact standards and 7 local workflow packs.

Extensive code review powered by Claude Fable 5 — a skill for Claude Code and Codex. Inspired by openai/codex-plugin-cc.

Zeoel-AI is a production-grade, multi-agent SaaS software engineering agency. Instead of single, fragile LLM prompts that lose context, Zeoel-AI coordinates a complete team of 33 specialized agents (UX designers, database architects, systems engineers, security auditors, QA engineers, etc.) to brainstorm, plan, build, and verify entire software.

A tiny file-backed living loop for durable AI-agent work. Formerly DOP.

Claude Code skill that enforces a consistent README.md + README.tr.md structure — create, audit, fix, and keep the Turkish mirror in sync across 23 rules.

Paymob payment gateway integration skill for Claude Code, Codex & AI coding agents — full offline mirror of developers.paymob.com (116 pages) + cheatsheet: Intention API, checkout, HMAC webhooks, refunds. Egypt, KSA, UAE, Oman

Free Claude Code skill: a scored 10-category production-readiness audit for Python scripts — findings cite file:line, no vague advice.

Lightweight docs/tasks convention and agent skill for repo-local tasks and open questions.

Thy coding agent, in doublet and hose. Same advice, twice the iambic pentameter.

Portable read-only Agent Skill for deep pre-ship adversarial review of code changes, plans, and ship-blocker risks.

Codex skill for preventing vendor marketing and SEO drift in software/API/tool decisions

AI agent skills for Hermes Agent & Claude Code — daily tech research briefings, automation, and more

Small, composable Agent Skills for better agent feedback loops, design judgment, and verification habits.

Agent skill for cleaning Chinese ASR transcripts and translating them into natural English for Codex and Claude Code.

Pressure-test early-stage operations work with sharp, context-grounded questions.

📌 Trusted dependency manager for AI agent skills

WaitSpin public client source, trust boundary, OpenAPI, and provenance.

Book Author Agent Skills

Public reusable skill hub for agent workflows

エージェンティックに動画解析するためのAgent Skills + スクリプト

html-report skill for Claude Code, Codex, and GitHub Pages

Vibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.

Claude Code plugins, MCP servers & skills by CodeCrafters Automation. Includes Change Claude Profile (ccp): hand off / take over work between Claude Code profiles (claude-team ⇄ claude-max) and keep their plugins in sync.

Open agent skills for commerce, marketing, CRM, lifecycle messaging, and integration APIs.

🔗 一个让你所有 Claude Code skill 同时在 Codex 自动触发的 skill（软链共享，非重写）· Install once — make all your Claude Code skills auto-trigger in Codex too, via symlink not AGENTS.md rewrite.

Bộ kỹ năng Business Analysis (BA) đầy đủ cho AI agents — tương thích Claude Code, Cursor, VS Code, Kiro, Gemini CLI và 40+ agentic clients khác. Tự động hóa quy trình BA từ intake, phân tích yêu cầu, viết FRD/SRS, tạo user stories đến đóng gói bàn giao.

Public PDF Vector agent skills generated from @pdfvector/api-docs.

🧠 The discipline layer flagship models run on — dropped into your agent. OpenClaw / Hermes / Claude Code skill.

Daily GitHub trending & community discovery radar as a Claude Agent Skill — scores projects 0–100, renders a Turkish HTML report, and keeps a persistent watchlist.

Audit your survey for biased questions before you send it — a Claude skill + zero-dependency CLI.

A workflow and safety harness: plan, implement, review, and guard AI coding sessions.

Master web/mobile designer as a Claude Code skill: intent-driven, trend-aware, anti-slop gated.

Curated agent skills for Cursor — diagnose, triage, commits, workflows.

Search & download ebooks from Z-Library — a portable Agent Skill (SKILL.md + stdlib-only Python CLI) usable by any AI agent (Claude Code, Codex, Cursor, Gemini CLI…) or from the shell.

A Codex plugin for turning rough ideas into portable static micro-apps with QA and build receipts.

AIにカメラとかマイクとか使わせるAgentSkills

Public Hermes skill export prepared from a private Hermes skill.

Swift development kit for agentic coding: Swift 6/SwiftUI standards, Apple docs lookup with falsification, Xcode-as-MCP-worker operating guide, Apple's Xcode 27 skills via local extraction, and programmatic Instruments analysis

Agent skills for shipping small paper-cut maintenance PRs

Production-grade AI agent skills & MCP servers for the Israeli market — סקילים

Agent-Skills usage guide for SwarmSkill — ERC-8257 swarm coin-trading tool (ID 25, ETH Mainnet). Use, don't copy.

Agent Skills knowledge base for Dwarf Fortress (Adventure + Fortress mode), built from the official wiki — progressive disclosure, no RAG/embeddings, just Markdown + ripgrep.

A Claude Code skill for writing collaborative code review comments

Zero-dependency AI agent skill for universal web search, shopping, jobs, academic, news, media, maps, travel, app search + content extraction, crawling, deep research. 55+ agents supported. No API keys needed.

My curated collection of Claude Code Agent Skills — 21 skills across frontend, Sitecore, AI/agents, devex fundamentals, and personal workflows.

DeepAgents core understandings and developement of advanced ai agents. With memory, skill, tools, subagents, multiagents flow & cababilities etc.

DeepSight 深度推理研究法 v2.5 — 8框架 + 7对抗模板 + 多厂商Council交叉验证。AI驱动的结构化深度研究。

An open-agent skill for committing outstanding git changes into coherent local commits.

Research Agent Skills Collection

Claude/Codex-style skill for turning full-screen Figma links into validated implementation blueprints before writing code.

A manual AI session handoff skill that turns the current coding session into a clean Markdown handoff document for the next AI session.

Evaluate Claude Code skills with cost-weighted A/B performance testing for Claude Code skills — one skill, or several combined. It measures real token cost and blind-judged output quality from live runs.

AI agent skill catalog and yk CLI for installing reusable Claude Code/Codex-ready skills into repos and running workflow tools like PBench, transcripts, and A-share data.

Plan-only multi-model Fusion for Claude Code: Opus 4.8 + GPT-5.5 (Codex) answer in parallel, Opus judges into one executable PLAN. Mythos-tier judgment distilled into the subscriptions you already pay for.

Reusable AI agent skills for governed local workflows

a nightly journal of your AI agent sessions, written in your voice