Custom agent skills for GitHub Copilot & Claude Code, from Microsoft-ecosystem dev experience (Azure, .NET, M365, Graph).

Reusable SKILL.md agent skills: application planning, adversarial review, and adjudication

Turn any diff into a narrated, step-by-step storyboard you read in the browser — an agent skill.

Human-led judgment and agent-executed harness engineering skills

An Impeccable-style readiness and polish skill for professional open-source repositories.

Flame-graph-style web performance auditing agent skill

通用 Agent Skill：跨平台查找指定视频、高清来源与可授权下载的视频素材，核验许可证并返回直链。

A cross-compatible Agent Skill for delegating bounded coding tasks from Codex or Claude Code to a supervised Claude Code Sonnet worker.

Free source-grounded landing-page skill for Claude Code and Codex, with honest copy, media consent, AEO, RTL, policy pages, and verification.

Agent skill for keeping human-facing product work centred on useful experience while internal machinery stays backstage.

Agent skill: SwiftData test patterns (ModelContainer fixtures, mock repos, @ModelActor tests, Decimal money assertions, import-hash dedup)

Scan AI agent skills for prompt injection, hidden instructions, and leaked credentials. Fully offline — no account, no upload, and it never executes what it scans.

Production-minded Agent Skills for responsive web design, root-cause refactoring, and maintainable app architecture.

A read-only Codex skill for finding duplicate, misplaced, risky, and structurally inconsistent files across Git repositories.

Reusable skills for AI coding agents. Organize any agent folder into a clean, filesystem-first layout.

Agent Skill that preserves user obligations and agent promises across turns

Turn ASCII architecture diagrams into native, editable Monodraw documents with Codex or Claude Code.

Codex plugin with reusable agent skills for product discovery, launch, SEO, sales, and growth

Claude to Codex Migrator: convert Claude skills, plugins, and assistant packages into validated Codex packages.

Claude Code / GitHub Copilot 等向けエージェントスキル集（gh skill installで導入可能）

Self-overcoming skill libraries for AI coding agents. COMPASS synthesizes what's missing; SAGE evolves what underperforms — training-free, evidence-driven.

Agent Skill: reversible PII tokenization — masks personal data before the LLM sees it, restores it in the final answer (SKILL.md, works in Claude Code and any agent)

Personal agent skills

Dependency-free CLI + Claude skill to read, search & draft email on any Zimbra mailbox over IMAP/SMTP. Draft-first and safe; works with any AI agent.

Skills for tracking fast-moving research without drowning in arXiv, benchmarks, and lab updates.

Proportional planning, recovery, and engineering-discipline protocol for Codex, Claude Code, Qoder, and OpenCode.

Agent skill wikis: query 250K+ community wikis (Fandom/Miraheze/wiki.gg) via HTTP API — search, markdown, infobox, images.

Claude-Code-Skill für kompakte deutsche Antworten im Chantal-Slang: 41 bis 69 Prozent weniger Prosa-Tokens, gemessener Benchmark, volle technische Genauigkeit.

Portable Agent Skills for Architecture and Feature Decision Records

Convert official ChatGPT exports into safe local Codex project folders and Markdown transcripts.

Schema-driven Unity Editor package and open Agent Skill for deterministic ScriptableObject localization scanning and validation with Unity Localization.

A Codex and Claude Code Agent Skill that revisits a focused subagent partner at key checkpoints to challenge assumptions before they become actions or answers.

Agent-facing resources for Zoral: AGENTS.md, agent skills, and the zero-auth API map. No key required to browse or buy.

Agent skills for shipping SaaS: product definition, secure build-and-launch, and safe maintenance on Next.js + Supabase + Stripe. For Claude Code, Codex, Antigravity.

Landing page for Skill Desktop — agent skills, without the terminal.

Battle-tested agent skills for engineering workflows — worktrees, task implementation, PR review, Jira/Confluence. For Claude Code, Kiro, and any skill-aware agent.

Automate your social media with Handled Agent Skills: guided Facebook onboarding, posting rhythm, approvals, and Social Connect workflows. More platforms coming soon.

A portable, evidence-led forensic audit skill for Codex, Claude Code, OpenClaw, and Gemini.

A Claude Code skill for goal-driven refactoring — makes a codebase navigable for agents and readable for humans, applied under green tests.

A growing collection of Agent Skills for Claude and other AI coding agents — starting with Design Grammar, a modular UI/UX & product design reference.

马斯克中心的科技新闻叙事写作 Skill：原创改写、短视频口播与多平台适配

Local YouTube transcription skill for AI agents — Whisper-always, self-improving vocabulary memory. No captions, no cloud.

Cohort Method — portable Agent Skill for multi-agent creative panels, UX swarms, build cohorts, and cross-QC (10 agents / 5 cohorts).

Agent-friendly Figma REST API CLI: reproducible reads of files/nodes, asset export, comments and design metadata — with a bundled agent skill for Claude Code / Codex / Cursor.

Skills for turning a topic into lessons, exercises, rubrics, and assessments.

面向4—6岁儿童照护者的事件记录、审慎分析、周复盘与医生客观导出 Skills（仅限非商业使用）

Reusable coding-agent skills for feature delivery, review, and software engineering workflows

Reusable agent skills from Dead Pixel Design, starting with an agent-agnostic Codex prompt compiler.

A portable Agent Skill for safe inspection, planning, conversion, and validation across media, images, documents, archives, structured data, and specialist formats.

Lint Anthropic Agent Skills (SKILL.md) in CI: referential integrity + name/trigger collisions between skills. Language-agnostic, zero-dep.

CLI per demo.istat.it (Demografia in cifre, ISTAT): i form del portale come comandi invocabili, pensata per l'orchestrazione da parte di agenti AI

My AI agent skills collection.

Practical, reusable skills for AI coding agents, beginning with hold-your-horses.

Free, open AI-agent skills from Majarrah Nexus — technical skill review and guided approval walkthroughs for Claude Code, Codex, Cursor, Copilot, and Gemini.

A lightweight project planning framework for agentic workflows - A standalone / optionally-installable module in my Horizon.AIOS Platform

Agent skill for Claude Code and Codex that prevents silent no-op failures when delegating to subagents — mandatory prompt clauses, artifact verification, resume-based recovery, and ledger-as-spec parallel delegation.

Local-first IO contract checker for reusable agent skills

Agent evals on autopilot: find quality bugs in your AI agent, ship a targeted fix, and prove it on a held-out set. Zero-dependency Agent Skill + CLI.

Audit what your agent loads: quality and context cost for MCP servers and Agent Skills

Skills for lab meetings, experiment logs, advisor emails, and paper reading agendas.