Portable Markdown skill for AI vibe coding with cloud engineering: AWS, Azure, GCP, Terraform, infrastructure as code, networking, containers, and cost optimisation.

Defensive Dependabot triage Agent Skill (Claude Code, Codex CLI, Cursor) — minimal-patched versioning, lockfile parity, exposure mapping, changelog safety interlock. JS/TS — npm, pnpm, yarn, bun.

tnagatomi's Agent Skills collection

Shareable skills and tools for AI agents

Build and refine image prompts with structured variables, bilingual vocab lists, and PromptFill JSON export

Agent-driven EKS to GKE migrations. PSO-grade outcomes, no PSO required.

TRIZ (Theory of Inventive Problem Solving) Agent Skills for Software Engineering workflows.

A public repository sharing some daily usefull skills

A collection of agent skills for AI coding agents.

A collection of agent skills for repository setup, multi-CLI agent workflows, and intelligent context loading.

Agent-neutral Trivy security scanning skill for local vulnerability, misconfiguration, secret, and license scans.

Hermes Agent skill + CLI: turn one raw goal prompt into an isolated optimized Markdown contract + paired ANALYSIS/BOOTSTRAP/RED/GREEN/REFACTOR TDD task-list YAML, with a paste-target /goal handoff — never executes the goal. 12-executor catalog (Claude Code, Codex, OpenCode, Gemini, Cursor, Aider, Pi, Qwen, Goose, Amp, Crush, Hermes).

🚧 BETA · Skills for the handoff → compact → resume workflow. Preserve key session context across compactions, with a confirmation gate on resume.

Canonical Agent Skills library for Claude Code, Cursor, Codex, and other agents.

Agentic tools for developers who lead their AI, not follow it.

Provider-neutral Agent Skill for designing, auditing, and operating multi-agent teams

Reusable Codex skills for creating visual, portfolio-grade GitHub READMEs with a consistent AI Engineering identity.

Agent stuff

PostgreSQL intelligence skill for Claude Code, Codex, Cursor, Windsurf, and local LLM agents

A scoped mentoring skill for codebase understanding and technical distillation.

Open-source agent skills for shipping & operating real infrastructure. First: ec2-docker-host — many apps on one EC2 box with Docker, shared Caddy + DBs, without disturbing neighbors.

AI-first workspace bootstrapper — installs skills, packs, agents, and disciplines into .agents/. Cross-compatible with Claude Code and OpenCode.

Claude/Codex/Hermes skill for README-to-GitHub Pages landing pages via Stitch MCP - GitHub Pages: https://cskwork.github.io/stitch-landing-skill/

Agent Memory Blueprint: public-safe templates, validators, and skill packaging for machine-first long-running agent memory.

A reusable codebase-visualization skill for Claude Code and Codex.

Agent Skill for MR/PR template previews and safe gh/glab submission workflows.

Локальное зеркало docs.aitunnel.ru как Claude Skill — 46 страниц markdown про OpenAI-совместимый API к 100+ моделям ИИ для России без VPN, плюс crawl4ai-скрейпер для регенерации зеркала.

Opportunity workflows for applications, registrations, browser handoffs, and supporting documents.

A focused, production-minded library of 197 clinical-AI and healthcare data-science skills for the OpenClaw agent platform featuring data quality, clinical NLP, big-data ML, explainable AI, drug safety, and regulatory.

Agent skills I use day-to-day.

Enforcement & release-hygiene layer for Cursor agents — blocking git/DB/license guardrails, commit hygiene, and docs-ops.

LegacyDotnetAgentKit is a practical starter kit for agent-assisted legacy .NET modernization.

Skills for writing and auditing CLAUDE.md files in derived/projected directories (symlink views, build caches, mirrors, generated docs). Skills.sh-compatible monorepo + Claude Code plugin.

Public Agent Skills for practical AI workflow governance, guardrails, and safer automation.

Rescue a stuck Claude Code session by trimming the broken tail of its JSONL transcript and resuming cleanly

Engineering discipline for AI coding agents. Spec-driven development, CI/CD, and documentation as composable skills built on the Workflow Router pattern.

Agent + étiquette: a small house of well-mannered agent skills for the skills.sh ecosystem.

自己跑、自己改、自己说了算的简易多 Agent 框架 · Conductor + Sub-agents · Skills + MCP · 多设备同步

A Codex skill for complex AI projects using anchor prompts, phase boundaries, branch windows, and confirmation gates.

Agent skill for safe legacy-code refactoring and maintenance workflows

Prove whether a SKILL.md actually changes agent behavior (with/without) and which CLI harness does a task best — agent-native subagents or CLI. agentskills.io-compatible. Site: https://cskwork.github.io/skill-ab-eval/

Théo's collection of Agent Skills for GitHub Copilot

Universal AI agent skills (Claude Code, Cursor, Codex, GitHub Copilot, OpenClaw). Build once, use everywhere.

A Ryvn CLI agent skill that gates regulated BYOC deployments before they ship

Claude Code × OpenAI Codex, as peers. A skill for cross-model collaboration (delegate / consult / roundtable) with a trace contract and eval suite.

An open protocol for human-AI teaming.

A general-purpose coordination protocol for multiple AI coding agents working on one repository with worktree isolation, structured handoffs, review, testing, and merge readiness

Systematic methodology for optimizing agent skills using deep-learning-style approach. Based on arXiv:2605.23904

⌨️ 123-flow — three number keys to run your AI-coding workflow: 1=do, 2=review, 3=ship. A Claude Code skill/plugin. 三个数字键接管 AI 工作流

Crawls articles from WeChat Official Accounts. Searching the name of any accounts（using personal cookie）gets the content.

High-agency agent skills for executable specs and end-to-end shipping.

A portable Agent Skill that checks project rules, verification paths, review workflow, and done criteria before agentic development starts.

Agent skill that audits and hardens basic security on a Debian/Ubuntu server over SSH with fail-safe rollback for sshd changes.

Rank Java files, methods, and REST API endpoints by a deterministic Composite Hotspot Score (recency-weighted churn × cognitive complexity × JaCoCo coverage gap) to prioritize test generation. Also a Claude Code skill/plugin.

🧭 A Claude skill for translating professional judgment to decision-makers — without losing density. Part of Where Judgment Lands toolkit.

A Claude Agent Skill for writing, reviewing, and refactoring code using Robert C. Martin's Clean Code framework.

Portable multi-agent research workflow skill for Codex, Claude Code, GitHub Copilot, Gemini CLI, and OpenCode, inspired by Agent Laboratory.

Concurrent-agent benchmark suite packaged as a Hermes skill. Markdown REPORT.md output