Gio's personal agent skills for coding agents — small, composable, installable via npx skills@latest add gio-del/skills

Specification-Driven Development for AI agents — 7-role orchestrator with filesystem memory. Works in Cursor, Claude Code, Codex, and 69+ agents via skills.sh.

에이전트가 부르는 audience-of-one 브리프 변환 스킬 — 원문/스냅샷 → motion_brief JSON + 플레이어블 HTML. 문법은 하나, 주제는 pack, 숫자는 snapshot.

Agent Skill for Databricks data engineering best practices

My curated repository of agent skills

将官方技术文档（Docker、K8s、PostgreSQL 等）提取为结构化知识，自动生成可复用的 Agent Skill。支持 URL/目录/本地文件输入。

Creator-lane agent skills from Agentic Creator OS. Install: npx skills add frankxai/creator-skills

A tool-agnostic Agent Skill for writing, reviewing, and refactoring Java unit tests with JUnit 5, AssertJ, and Mockito.

⚒️ Claude Code skill: routes pre-plan work through brainstorming + grilling, with a quality gate and rebuild protocol for existing specs. TDD-verified.

Ganhuo Claude/Agent Skill for Chinese travel planning, live price verification, and booking-ready itineraries

An open standard for making apps steerable, shipped with a reference runtime and a skill that lets a coding agent implement it in your codebase.

Diagnose Mac memory/battery drain; only kill PIDs you've vetted.

Playground rules for predictable AI builders: exact execution, defensive testing, debugging, alignment, and less bloat.

Warp agent skills for release engineering automation — cherry-picking fixes, cutting release candidates, tracking PR status, and posting Sentry/Slack digests.

PgBeam's agent skills

A bounded-delegation engineering workflow for Codex

Publish AI-generated HTML reports and presentations as secure, stable links.

开源 A/B 测试与增长实验 Agent Skill：生成假设、指标、护栏、停止规则和实验复盘。

Assemble and verify a TanStack Start SaaS from a PRD.

Use your repository's GitHub Copilot customization from Claude Code - without committing a single Claude-specific file

opencode plugin — Hermes-style self-improvement loop (port of UniM0cha/claude-self-improving-skills + okdk7788/skill-evolution). Distills learned skills after complex work + GEPA-style measured evolution.

cold-read — blinded evaluation for AI agents. Cold agents (N≥2), pre-registered rubric, manipulation checks, training-data disclosure, independent reconciler. Pollock 2026.

Claude 技能：把 Thariq 的 Finding Your Unknowns 方法论固化为可触发工作流——盲点扫描/访谈/原型/测验 × 未知四象限，把任务中的未知转化为明确决策

PostHog CLI workflows for Claude Code and Codex — schema-first analytics, HogQL, endpoints, and verified symbolication.

Quest 3 Unity XR/MR Agent Skills for verification, spatial UI design, and read-only project audits

A Claude skill that decides whether to build an agent or a workflow, before you build it. The design-time gate, with a deterministic verdict engine.

Thinking framework to guide agents through systematic data analysis.

AI agent workflow template: AGENTS.md, playbooks, trace files, and just turn-test policy checks

ScholarFlow Skills by Zhoy: reusable Agent Skills for literature review, academic writing, figures, bioinformatics, and research deliverables.

A benchmarked control loop that keeps coding agents moving until proof or a real stop.

Cross-agent SKILL.md workflows for product architecture, UX audits, prompt clarity, work synthesis, and hands-on practice.

A GitHub-first project deployment advisor Skill for AI agents

Governed Doris market analytics MCP and Strategic Analytics Skill for safe natural-language analysis

Turn a product idea into an execution-ready PRD package a coding agent can build end-to-end from a single prompt.

Airbnb agent skills (SKILL.md) — search, availability/calendar, prices, cross-OTA comparison and reviews for any AI agent, via StayingAPI. OpenClaw, Hermes, Claude Code, Cursor. MIT-0.

Triage and reply to a PR's unresolved review comments — reply-only, on each reviewer's channel, with you approving every reply.

Read any Trello card with Claude through the browser — no API key, no token, no MCP server. Claude Code plugin + agent skill.

Agent skill for DHIS2 web app & plugin development. Works with Claude Code, Codex, Cursor and 75+ AI coding agents — npx skills add Ebed-meleck/skill-dhis2

Claude Code skills for creating, judging, evaluating, and updating skills and agents

PM-facing AI conversation trace eval skill: north-star metrics, 1-5 scores, red/yellow/green, per-turn quote review

Agent Skill for fast, safe Windows file search through voidtools Everything and ES

Nine character-driven cognitive operating modes (Batman, Ironman, John Wick, Thanos, Jack Sparrow, Joker, Thomas Shelby, Dr Strange, Fight Club) for any AI agent — portable skill with reasoning craft manual, per-mode terminal themes, and cross-agent installer.

Customer-voice research CLI, MCP server, and agent skill documentation for Adlicio.

Focused agent-team coordination skills for deliberation, arbitration, parallel proof, diagnosis, handoffs, integration, and adversarial review.

[Mirror/Mininglamp-OSS] Mininglamp-OSS/octo-spec — Git-native AI coding engineering standard: shared specs, tasks, and project memory in your repo.

One engineering workflow across Claude Code, Codex, Copilot, and Gemini CLI. A portable persona canon, process skills, and safety guardrails, kept in sync by design.

Compile finite goals into compact, auditable Codex execution packages.

Pi skills for recognizing knowledge-base opportunities and deciding what belongs

Open agent skills for the skills.sh ecosystem — browser, docs, mail, media, security, networking, orchestration, and more.

Cross-runtime Agent Skill for accessible dark mode design, implementation, and audits.

Beginner-first agent skills that turn 'I want to learn X' into a 30-day path, tutor loop, projects, and learning memory.

面向专家 IP、创始人与内容创作者的高效表达 AI Skill 系统

Agent skill and Windows/macOS releases for searching and publishing on X through the user's local Twitter Skill session.

AI-importable browser audit tool repo with separated audit tooling and client materials.

Portable agent workflow framework for Codex, Claude Code, and OpenCode—shared project context, focused skills, independent review, and safe updates.

Portable Codex skills for writing source-grounded MEC and UAV-MEC papers

Rebuild images, dashboards, infographics, and slide screenshots as editable PowerPoint files with visual QA and typo review.

日本語実務向けAgent Skills — ベンチマーク実測つき（議事録・社内規程QA・期日ガードレール・稟議・敬語メール）

A structured multi-agent deliberation skill for Claude Code — nine expert seats debate your question across independent rounds, then one synthesis decides with dissent preserved.