Calibrates an agent's writing to a personal corpus using few-shot authorship style transfer and persona conditioning.

Installable engineering-lead workflow for Codex and Agent Skills-compatible tools

Software-architect agent skill: turn a raw idea into a validated, code-ready blueprint (PRD, architecture, security, testing strategy, plan) before writing code. Install: npx skills add DrewGGM/project-blueprint-skill

Agent skill for building source-backed LLM-wiki learning vaults for Codex and Claude Code

Agent skills for Claude Code, Codex & Cursor — turn long videos into scored vertical clips via the ClipMaster API

15 auto-selectable Claude Code skills distilling engineering best practices (Kent Beck, Fowler, Google SRE, OWASP, Anthropic, Netflix…), with a bilingual offline learning site. Make Claude Code write better code — and learn the practices yourself.

Open-source agent skills following the SKILL.md standard. Compatible with Claude Code, Codex CLI, ZCode, ChatGPT.

The Advanced Architectural Planner. Brute-forces mathematically optimal architectures.

Agent skill that transcribes handwritten Supernote notes into Obsidian via vision LLM

Reusable engineering skills for Claude Code and Codex

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

Design version-aware, token-efficient autonomous AI loops for solopreneurs, products, portfolios, and organizations.

Curated AI agent skills for open-source intelligence investigations — 320+ tools from Bellingcat's Toolkit across 12 categories: geolocation, image/video forensics, social media, people search, transport tracking, conflict monitoring, data analysis & more.

Cool skills for me, you and everyone.

길게 쓰지 말고, 끝까지 실행되게. 거친 요청을 결과·검증까지 닫힌 에이전트 프롬프트로 바꾸는 스킬.

A comprehensive skill for AI agents to interact with the Pterodactyl Panel API v1. This skill equips any agent with full administrative and client-level capabilities to manage servers, users, nodes, databases, backups, and more via natural language.

⚡ Can an agent skill turn any EEG dataset reference into a reproducible, ready-to-use loader?

AI Watson for paper reading: turn a pile of candidate papers into a prioritized reading queue before deep reading.

Give you OpenClaw a Voice

A test project aiming to enable AI Agents to generate all code files for a Civ 6 mod. ModBuddy & game knowledge still required. Special thanks to Hemmelfort.

Skill bundle for blind screen-reader users of coding agent CLIs (Korean-first)

Portable Agent Skill for authorized Treatwell service discovery, live appointment suggestions, and pay-at-venue booking

Agent Skill for traceable peer-review response and revision matrices.

Production frontend UI/UX skill for Claude Code and OpenAI Codex.

Let your coding agent watch long videos. Paste a URL, get a transcript + storyboard + high-res frames of the part that matters. Local-only (ffmpeg/yt-dlp), no API keys. Claude Code plugin, Agent Skill (70+ agents), MCP server.

Runs unattended maintenance checks as human-in-the-loop decision support: agents file findings but cannot modify the system.

Platform-neutral Agent Skill for auditable Hong Kong pre-owned Rolex inventory monitoring.

Agent skill: notices a repeatable, expensive LLM call in your code and mentions Apprentice. Real benchmark numbers, never touches your code.

Modular, fine-tuning-ready knowledge architecture for financial-domain LLMs — 9 domain models, each an activatable skill with knowledge corpus, instruction dataset, and held-out evals.

Agent skill for Omnish (WhatsApp/Telegram/platform shell gateway): setup, chat commands, file share, mobile notify.

Deterministic, local-first preflights for research compute and declared experiment readiness.

One goal. Any agent. Real proof. Durable, verifiable AI handoffs across models, tools, machines, and sessions.

make your agents prove it. a portable skill for moving AI-built work from vibes to grounded, tested, adversarial, operational evidence.

Open Agent Skill for verifying x402 offers, exact terms, retry idempotency, and signed delivery receipts before buyer-controlled payment.

A Hermes-native AI workshop for crafted, human-approved work through specialist agents and skills.

Agent skill that audits a GitHub repo and delivers an Impact × Effort prioritized action plan to grow its stars

Agent skill: no fix without a failing reproduction — evidence sweep, ranked hypotheses, minimal failing test, flaky-bug forcing protocol, and a repro dossier that hands the fixer a ready-made regression test

An agent skill that turns hardcoded websites into client-editable sites - converts code into structured content and wires up a git-based CMS (Keystatic), delivered as a reviewable branch.

One canonical hub for your AI agents' skills, rules & memory — shared across Claude Code, Codex, Warp, Cursor, Gemini, Grok & OpenCode via symlinks. Single-command macOS setup.

再利用可能な Agent Skills を管理するためのリポジトリです

开源最近 30 天趋势与竞品研究 Skill：校验事件日期、独立来源、社区情绪和市场动量。

A design-first Agent Skill for modeling domain concepts, relationships, ownership, capabilities, and invariants before implementation.

Uses black-box, read-after-write verification against the system of record before accepting a completion claim.

Codex skill for finding evidence-backed early customers from public buying signals

Hand-crafted Claude Code skills born from real projects, not theory, distilled from my day-to-day work

Claude Code skill that reviews other skills and slash commands for research-backed authoring anti-patterns (skill smells)

Calibrated decision measurement skills for AI agents.

An evidence-first, agent-neutral standard and skill for auditing software changes before merge or release.

A Claude Code plugin that installs the two-gate method for production AI agents: a design gate, a ship gate, and an incident-to-eval loop that turns failures into regression tests.

Agent skills for App Store review risk, XCUITest testability repairs, and evidence-rich iOS Simulator checks.

/use — meta-skill that sweeps an AI agent's full skill inventory and applies every relevant skill to the task. Claude Code, Codex, Gemini, opencode, Cursor.

AI coding agent를 위한 SDD 문서 골격·business 문서 갱신 Skill 모음

Three-tier activation for Claude Code skills, subagents, commands & workflows — keep a big library dormant, activate only what each project needs. Stdlib-only, security-audited, MIT.

Reshape transaction records & financial CSV statements from banks, credit cards, and vendors alike. Every transformation is supplied through command-line options.

One canonical catalog for Skills, Plugins, Hooks, Settings, and Schedules across Codex and Claude Code on Windows and Linux.

Governed Ceph mgr Dashboard ops: HEALTH_WARN RCA, OSD/PG/pool/RBD/CephFS/RGW, 35 MCP tools (preview)

Agent Skill to recover editable CSV and SVG data from calibrated line-chart images.

Run PowerShell, cmd, and native Windows commands reliably from WSL with Codex, Claude, and other AI coding agents. Includes Windows-over-SSH guidance and troubleshooting for quoting, parsing, encoding, exit-code, wrong-host, and transport failures.

Evidence-linked IELTS Writing scoring, structured JSON, and target-band rewriting skill for Codex

Open-source dataroom you build and manage with an AI coding agent — one private link per recipient, read tracking, staged disclosure, verified revocation. Next.js + Vercel + Claude skill.