AI TFT coach that reads your board and makes the call. Comps, items, augments, economy, pivoting, positioning — personalized to YOUR game state.

Agent skills for markdown writing, conventional commits, PRs, and releases — works with Claude Code, Codex, Cursor, and 40+ agents

Enable AI agents to control Windows tasks using PowerShell skills for Outlook, Edge, desktop automation, and structured shell commands in JSON format.

Hand-crafted skills for building AI agents — each one distilled from a technique used and proven in real Agentailor projects.

Agent Skills for Vobile/Pex APIs and tools. Audio matching, cover song identification, AI song detection, and more.

A collection of DevOps skills designed for LLM-powered agents and AI workflows. This repository provides reusable capabilities, tools, prompts, and best-practice patterns to help automate infrastructure operations, CI/CD pipelines, cloud management, observability, security, and platform engineering tasks.

Keep AGENTS.md alive: generate, compress, audit, and update AI-agent onboarding for Claude Code, Codex, Copilot, Cursor, and OpenCode.

Agent Skill for NIST Fire Dynamics Simulator (FDS) - Generate, review, debug, and optimize FDS input files with AI agents. Based on NIST SP 1019 (FDS 6.10.1).

Pinterest pin production system for Claude. Composed batches from your approved image library — SEO copy, board assignment, staggered scheduling, and performance learning on every batch.

Curated NanoClaw skills for secure AI agents, with safety notes and installable workflows.

SUPER Skills catalogue: portable Markdown agent skills for AI vibe coding, SEO, AI SEO/GEO, marketing, design, AI agents, DevOps, security, automation, data, business, and operations.

Agent Skills for AI coding assistants

UX review companion skill for AI agents: flows, forms, accessibility, trust, errors, and microcopy.

Meta Agent Skill: author deterministic, weak-model-friendly Agent Skills validated against the Hermes runtime. agentskills.io-compliant, with validators and source grounding.

Production-grade coding methodology for AI coding agents, Claude Code, Cursor, Codex. Six principles to stop overengineering, silent assumptions, and "while I'm here" refactors.

38 portable Agent Skills for disciplined, reviewable AI-assisted work across Codex, Claude Code, GitHub Copilot, and compatible agents.

I am Kip, Ben Welsh's AI assistant. Here are the things I know how to do.

Composable writing instructions for AI agents on four orthogonal axes (Voice, Tone, Style, Format). Early/experimental. Install via the product-on-purpose marketplace.

Agent skills for experiment design, causal inference, and statistical review. One install, adapts to your level.

CFO Skills by Crewm8 — 36 modular startup finance skills for Hermes, Claude Code, Droid, Cursor, OpenClaw, and any agent.

Skills for use with Hermes that work with local models

Use Agent Skills in Obsidian for Claude Code, Codex CLI, and other compatible agents

A beginner-friendly starter repo for creating, auditing, installing, and evolving Codex Skills from scratch.

Chinese-first, evidence-driven resume-building Agent Skill with job intelligence and traceable matching.

Evidence-bound multi-agent council for Cursor and Claude Code. Scout (last30days), Advocate vs Skeptic, Fact Checker (deep-research). Ranked verdict with dissent.

Maestro is an open-source, multi-agent AI development framework written in Go. It orchestrates specialized AI coding agents across a deterministic software engineering workflow

LLM-native research community protocol for agent-based research workflows

Reusable AI agent skills for Claude Code / Codex — install with npx skills

Production-grade engineering skills and specialist agent personas for AI coding assistants. Orchestrates the full SDLC, from spec to ship, with structured verification gates, anti-rationalization checks, and senior-level engineering discipline.

Learn while you vibe code — a Claude Code skill that explains the major concepts in your code as it's written, then quizzes you to make them stick.

Real estate research skills for AI agents — property briefs, listing search, rentals, CMAs, investment deal screening, and agent finders, powered by RealtyAPI

Vensim 系统动力学建模 AI Skill：.mdl 草图自动排版 + 信息箭头平滑弧线。基于官方 Sketch Format 解析，Graphviz 半固定布局，保留方程与对象 ID。适用于 SFD/CLD 课程作业、政策分析、论文图表。

Evidence-grounded editable technical route diagrams for research and engineering projects.

Tiered AI code-review: triage → 12 specialist reviewers → synthesis. Built for AI-written code. opencode, Cursor, Claude Code, Codex.

Portable Astro + Cloudflare toolkit with versioned skills for Codex, Cursor, Claude, and Antigravity; readiness, deployment, discovery, and starter CLIs.

FDE Consultants Protocoles — open-source Forward Deployed Engineer + DeepSCR protocol: turn any coding agent (Claude Code, Codex, Cursor) into a certifying engineer with verifiable AI Assurance Scores, MCP tools, and a public trust registry. Apache-2.0.

46 agent knowledge packs distilling vetted, licence-clean systems-engineering standards (NASA, DoD, FAA, NIST, GAO, SEBoK) into on-demand Claude skills.

Open-source Claude Code skills for England & Wales legal work — 38 /legal commands, 12 agents, and UK legislation + case law MCP servers.

A Codex skill that routes vague tasks to the right local skill.

Agent skill that generates production-ready Power BI themes from 3 brand colors: ~5,800-line theme JSON, branded SVG canvas, design-system PDF, CSS tokens and DAX HTML visual examples. WCAG-aware, light and dark.

A shared-filesystem coordination protocol for multi-agent collaboration.

Record & Replay for agent skills — capture a session's tool calls and distill them into a reproducible skill. Local-first.

输入任一 A股/港股/美股公司，生成可点击的产业链图谱（上下游公司 + 资料卡 + 实时K线）。Claude Code 插件，零 API key、零成本。

An AI agentic operating system for mixed reality on the Meta Quest 3 — your own J.A.R.V.I.S. Multi-agent orchestration, multimodal perception (sight/hearing/gaze), 42 holographic widgets, 20 LLM providers.

AI Agent Skills for cross-border networking and censorship circumvention, made for ordinary users — install, harden, configure, and troubleshoot tools like 3X-UI / Xray.

Reconcile every AI coding agent's conversation history (Claude Code, Codex, Gemini, Cursor, Aider, opencode, Cline +11 more) with git & docs into one cited ground truth — and generate ADR/PDR/BDR decision records. Local, deterministic, zero-deps agent skill.

Codex/Claude skills for generating Dify agents and plugins

Drop-in toolkit that gives AI coding agents persistent memory across sessions. Agent Skills, cross-session learning loop, and knowledge persistence. Zero dependencies, no backend.

Open-source plugins, managed agents, multi-agent orchestrators, and design tokens for Claude Code, the Agent SDK, and any AI tool. By OneWave AI.

Agent skills that write blog content that ranks and doesn't read like AI.

A Manus Agent Skill that encodes McKinsey & Company's complete problem-solving methodology — MECE, Issue Trees, Pyramid Principle, SCQA, So What Test, and the 7-Step Process.

Documentation-first development for AI coding agents — 8 skills: persistent memory, zero-ambiguity specs, append-only decisions, and an independent verification gate. The harness layer for long-running, loop-driven development.

Agentic knowledge base and wiki management that works with any agent harness

RateMyCode: Staff-level product audits for vibe-coded apps, with evidence, release vetoes, fix prompts, and same-rubric retests.

An Agent Skill for turning any topic into a dependency-free interactive HTML lesson with a single-sided fan poker deck animation.

Autonomous software delivery for AI agents. 18 skills that turn the lifecycle into bounded, self-correcting, checkpoint-resumable phases with deterministic enforcement hooks and a self-improving learn/map loop. For Claude Code and Codex.

🤖 Curated agent skills for AI agents — one coherent engineering loop that compounds: grill → spec → implement → review → commit → learn. Adopt it or fork it!

一个 7×24 小时不间断运行，帮你跑实验、用 Git 维护公开仓库、更新 LaTeX（Overleaf）论文的科研自动化工作流。实测效率提升 25 倍。Claude Code Skill，一条命令装进任意项目。

嘴替·甲方包 —— 专治甲方压价/加需求/拖款/无限改稿：把含糊的成本拉回明面。四拿回原则 + 三档回复。Made with 嘴替.skill

Reverse-engineered documentation and tooling for Lark AnyCross flow.json — connector IDs, schema, validator. Works as an AI agent skill or standalone Python.