Agent Skill for Claude and OpenAI Codex — take a fuzzy idea (or existing project) through explore → pressure-test → converge into a locked CONCEPT_BRIEF + roadmap. Upstream partner to prompt-pack.

Handover & Resume — session-continuity skills for Claude Code / Craft Agents

Portable Agent Skills for reproducible ML workflows, starting with tabular data profiling, leakage checks, baseline training, evaluation, and reports.

A modular Agent Skills repository for Android, Kotlin, Jetpack Compose and Firebase development.

opencode 技能工厂 · Create, evaluate & optimize agent skills via DB physical-evidence eval engine. Cross-platform packaging (trae/claude/generic) + governance. 用 opencode.db 物理证据消除 LLM 自评偏差。

ADHD-friendly agent output: action first, four-item chunks, research-checked rules. Agent Skills package for Claude Code, Cursor, and more.

Turn engineering-heavy updates into concise, accurate plain language.

Awesome list of Hermes Agent resources from across the web: UIs, skills, memory, multi-agent, deploy + operator playbooks | independent of Nous

拒绝重复造轮子。让你的 AI 智能体自动检索 GitHub 优质参考，智能生成项目脚手架。Stop reinventing the wheel. Let your AI agent find the best GitHub references and scaffold your project smartly.

AI-powered Xiaohongshu note compliance auditor skill

AI-powered professional IM avatar generator skill

backup of hermes-agent

Research-first Agent Skill that runs long-horizon paper pipelines with evaluator gates, heartbeat watchdogs, resume controls, and manifest cleanup.

Non-custodial agent wallet toolkit + skill: EVM and Bitcoin CLI (init, send, swap, bridge, Solidity). Local keys, JSON envelope, plug-and-play via /skills add.

Agent Skill: HTML review surfaces humans actually read. Nine kinds plus a dynamic mode for when the shape is the argument, a validated content contract, an offline validator that can render your page with JavaScript disabled, and a gallery. Local-first.

Build a structured Career Profile once, then generate ATS-ready CVs and cover letters tailored to each job — a pair of AI agent skills for Claude Code, with zero fabrication.

Transform ideas into implementation-ready specs. Grounded in real code, read-only by design, with strict fact/proposal separation.

AI coding agent 的定时器 | 一个让 AI agent 按固定时间预算工作的 skill

A modular human layer that helps reduce overplanning, token waste, context loss, and actions taken without clear permission.

Practical, composable agent skills for engineering work and personal development.

Evidence-first evaluation and creation for Agent Skills.

A cross-tool AI agent skill for Java + Spring Boot: dev conventions, code review, testing, and JVM troubleshooting. Works with Claude Code, Codex, OpenCode, ZCode. MyBatis-Plus default, 26 rules.

Autonomous terminal AI agent for workflows and feasible project procedures. Co-Worker Co-Wrangler 🐙

Weave Agent Skills into every workflow — discover, lock, sync, audit, and test across coding agents. Node ≥22.13.

Claude and Codex Agent Skill (plus standalone CLI) that audits existing Excel spreadsheets and financial models for correctness defects: formula errors, broken references, off-by-one ranges, totals that don't reconcile or cross-foot, circular references, and data-quality risks. Audit-only; never rewrites your workbook.

Analyze BaZi charts with Claude Code, gather birth data, and generate four pillars, luck cycles, and practical命理 insights from classic texts

Portable multi-model AI council and agent skills for Claude Code, Codex, and other coding agents.

Public agent skill for A2A Fans — connect your agent via MCP or REST, claim tasks, and get paid.

AI 改 UI 总不满意?让它一次出 5 个版本并排挑 — parallel-mockup UI exploration skill for coding agents (Claude Code / Codex / OpenClaw)

Agent skill that reads any codebase (local path or GitHub URL) and classifies how its AI product creates value — Amplifier, Substitute, Job Creator, or Democratiser — returning an evidence-cited verdict report. Works in Claude Code, Copilot, Cursor, Codex.

An open-source factory for turning SOPs, workflows, API playbooks, and domain methods into tested, portable agent skills.

Claude Code skill: hand code/plans to Codex (codex CLI) for an independent second-opinion review

Environment-adaptive orchestration skill for AI agents.

AI Product Engineering Skills Platform (APES) is an open library of Engineering Playbooks for AI agents. Each Skill is a single skill.md file that defines the methodology for completing one specific engineering task.

Free business document template library with 1,000+ proposals, contracts, agreements, invoices, forms, and plans, ready to customise, send, and eSign online.

Evidence-bounded review chains that make planning documents restartable.

Agent skill pack for using CheapTokens: discounted Venice AI credits, OpenAI-compatible API calls, and x402 purchase flows.

An agentic AI skill that analyzes codebases to create, review, and incrementally maintain clear, structured project documentation

Adaptive skill that turns any project, PR, or app into a cinematic, evidence-grounded showcase video with parallel agents, taste gates, HyperFrames, and verified delivery.

Agent Skill for running Google Lighthouse — measure & verify web quality (performance, a11y, SEO, best practices): CLI, budgets, CI, programmatic API.

Russian AI agent skills for legal, compliance, business, product and engineering workflows

AI 协作说明｜让任何 AI 更懂得应该如何与你协作 · A portable AI Collaboration Manual

Free AI Music Generator powered by Lyria 3 Pro: https://www.dh3-seedream.com

Auto-generate a spec-conformant DESIGN.md from your existing design tokens (theme.json, Tailwind, CSS variables, DTCG). The Claude Code skill that makes your design system AI-readable in one command.

Agent skills that make Claude Code (and other AI coding agents) genuinely better at infrastructure, scheduling, and configuration work. Battle-tested, zero-dependency.

根据简历研究最新 AI 与泛 AI 职业机会，并生成个性化学习路线。

Wenshan.skill — Turn reviewed Markdown into traceable personal knowledge mountain maps. Local-first, evidence-gated, no embeddings.

Five agent skills that cut your coding agent's token weight: weigh in, read the bill, slim the replies, cap the thinking, cut bloated sessions. Claude Code, Codex, Cursor, any SKILL.md agent.

Skills para Claude Code, Codex y Cursor: integraciones de Argentina (AFIP/ARCA, Mercado Pago, Correo Argentino) y automatizaciones (n8n + WhatsApp), listas para instalar. Lo tedioso, ya resuelto.

AI Agent skill for operating and contributing to Rute Bayar

PenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.

Bootstrap, maintain, and continuously improve a coding-agent workspace so each session adds momentum the next session inherits. For Claude Code + Codex CLI.

Behavioral blueprints for agents.

Evidence-first agent skill and Obsidian-friendly career operating system.

Curated open Agent-Skill format skills for MyLLM (the on-device iOS AI agent). Install with /skill add teamdzx/myllm-skills.

Turn hard-won human experience into knowledge your AI agents can act on — a methodology (routing + Book-to-Skill + governance) above OKF. A production field report.

My personal skills, agents, and other configuration files for agentic coding.

Use AI coding agents with LTspice via sim-cli: run circuits, inspect waveforms/logs, and produce replayable simulation artifacts.

Skill suite for better usage of agent ( openclaw, hermes and more)

Teach your coding agent — Claude Code, Cursor, or any AGENTS.md agent — your project's conventions, and turn every correction into a team-shared, git-tracked lesson.