Public Agent Skills built to the agentskills.io specification — start with terminal-poster (5-cluster reusable infographic system).

Codex skill for compact project-maintenance documentation

Agent skill for pixel-grounded chart data extraction

13 Claude Code Agent Skills for Google Ads (research, planning, build, optimization, reporting) with a premium visual dashboard and a live example per skill.

Scientific figure skill for Codex, Claude Code, and agents. Turn research ideas, paper methods, and grant roadmaps into publication-ready figures. Powered by SciFig (scifig.ai).

Evidence-backed local inventory and safe cleanup for Agent Skills

Agent skills for programmatic trading, analytics, and account operations. DV360 first, multi-DSP and multi-runtime (Claude Code and Codex).

An AI writing skill that preserves meaning and learns your voice across Claude Code, Codex, Cursor, Gemini, Copilot and OpenCode.

Agent skill for turning YouTube videos, playlists, and search topics into timestamped context packs

Official Wavedash plugins and agent skills for AI coding tools.

Comprehensive Unity engine reference for AI agents — C# scripting, URP/HDRP, Shader Graph, game architecture, mobile optimization (1800+ lines, 2022.3–Unity 6). GPL-3.0.

A localized intelligent agent platform suitable for human-machine romance: cclaw (agent side) + eclaw (backend) + wclaw (frontend) + xCrab (AI gateway). 一个适合搞人机恋的本地化智能体（Agent）平台：cclaw（代理端）+ eclaw（后端）+ wclaw（前端）+ xCrab（AI 网关）。懂的都懂！

An opinionated agentic workflow to turn well-defined units of work into shippable code with minimal human input.

Tempest — a cross-harness software factory: opinionated build & QA workflows as portable Agent Skills for Claude Code and pi.

Vertiso Memory plugin for OpenAI Codex: connect the remote, user-owned memory MCP server plus session skills directly, without the store or the CLI. Durable recall, hybrid search, and cross-session handoffs, with browser OAuth and no API key to paste.

Turn real Agent failures into verifiable Skill boundaries and correct-layer fixes.

TARS Answers from Raw Sources — a local-first second brain. Raw immutable captures, FTS5 search, and agent skills that answer with citations.

Free, open-source toolkit (Anthropic Agent Skill) for cancer patients, their caregivers, and anyone organizing treatment — runs the operational side around the doctors: documents, consultations, next steps, second opinions, cross-border care. Not an AI doctor.

The Revenant packs marketplace — Agent Skills packs for Claude. foundation: eight standalone smiths that build, audit, and ship AI-agent artifacts. Always comes back.

Official Cursor plugin for Vertiso Memory: add the remote, user-owned memory MCP server plus the session skills in one step. Durable recall, hybrid search, and cross-session handoffs and checkpoints, with browser OAuth and no API key to paste.

1:1 WorkBuddy port of oh-my-codex — 46 catalog-driven skills (30 active + 16 deprecated), bilingual docs.

A Codex skill for discovering, evaluating, and recommending open-source AI and software capabilities.

One memory. Every AI. Agent skill + Claude Code plugin that teaches AI agents to use the user's MemoryPlugin long-term memory automatically.

Evidence-first AI Agent Skills for growth marketing — multi-channel analytics (SEO, paid media, social, local search, CRM), secure account integration, AI evaluation, experimentation & approval-safe optimization for Claude Code.

Engineer production-ready Codex skills with behavior contracts, quality lint, and forward testing / 将 Skill 构建从 vibe prompting 变成工程化流程

Agent skill: structured, resumable domain-elicitation interviews that emit an OKF knowledge bundle (glossary, tri-temporal events, rules, context map)

Agent skill: long video → highlight/summary story — transcribe once, cut, caption, crop, join.

Agent skill that prevents orphan words and awkward last-line wraps.

Seedance2.5 AI video production skill: short videos, marketing videos, product demos, talking-head B-roll, storyboards, prompts, and continuity QA.

OSCAL-governed guardrails for Agent Skills — dual-evidence admission (static scan + local LLM rubric judge), digest integrity, and OSCAL assessment-results audit trail for LangGraph DeepAgents

One Lark/Feishu agent skill instead of 27 lark-cli domain skills.

Transcript-driven, closed-loop AI editing bridge for Adobe Premiere Pro, built on official UXP APIs

Portable Agent Skill for bean-specific xBloom Studio recipes and guarded local BLE control

Agent Skills for Claude Code: Figma-to-code pipeline, git workflow, doc hygiene automation, and design-engineering tools, built from real use.

The official Vertiso Memory plugin for Claude Code.

Claude Agent Skill for Apple's design language — HIG + Liquid Glass, for app UI, landing pages, code, and Figma.

Browser QA on any site, for anyone - record by clicking, run, schedule, and get reports non-developers can read (Claude Code skill + Textual TUI)

Agent skill that authors engine-valid Transon JSON transformation templates — verified against confirmed samples before any template is returned

5 skills de Claude para gestores de tráfego: spy de concorrentes, gap de mercado, 20 copies em 10min, auditoria 186 pontos, score pré-lançamento. Por @devjuniors7

Review your due Anki flashcards in chat with an AI agent or in the terminal — real v3 scheduler, syncs back to AnkiWeb

Portable Agent Skills for building, operating, evaluating, and governing LLM-Wiki knowledge systems.

Deterministic Playwright QA scout and AI-agent skill that crawls web apps and generates Playwright tests.

A community collection of AI-agent skills for MLatom.

A Codex skill for publication-ready scientific figures, editable SVGs, multi-panel layouts, and figure quality assurance

A production-ready agent skill for designing, validating, packaging, and integrating macOS App Icons and menu bar template images.

Portable dev practices, packaged as skills - that run inside the coding agent you already use (Claude Code, Codex, pi, hermes). Not an agent, framework, or provider layer.

Frontend design skill for Claude Code & OpenCode: interfaces that look designed, not generated. Anti-cliché catalog, font tiers, seeded variation, pass/fail self-review.

Professional Airtable skill for AI agents to design, audit, document, and troubleshoot Airtable bases, schemas, automations, interfaces, integrations, and operational workflows.

Skill agnóstica de agente que orquestra o ciclo Spec-Driven Development com rigor proporcional ao risco (tiers 0/1/2) — spec, plano, TDD, revisão adversarial e destilação de memória. Companion do sdd-scaffold.

Local-first visual workspace for discovering, organizing, and managing AI agents and skills. Scans AGENTS.md/SKILL.md, renders a kanban board + relationship graph.

Portable Agent Skill for Treatwell services, live availability, and fast guest checkout booking

Agent skills: artbureau (Lebedev/Gorbunov design & text review), marketing (verified direct-response canon)

Yan's agent skills collection — Google Trends SEO workflows, AI news, autopilot, and more. For Claude Code / Codex / Cursor.

An LLM wiki for Obsidian: a markdown knowledge base your AI agents compile and maintain under written law. 32 skills for Claude Code and Hermes, a zero-dependency Python CLI, and a vault template governed by an 11-law constitution.

Agent Skills that let AI agents (Claude Code & friends) operate self-hosted apps on your homelab — Proxmox, Docker, Outline wiki, and more

Approval-first Codex workflow for reviewing completed Notion work and turning useful takeaways into reusable records.

Turn public competitor channels into a traceable dataset and evidence-backed strategy report — an agent skill with a zero-dependency demo.

A reusable Agent Skill for keeping Claude Code and Codex aligned through durable project files, handoffs, and workflow memory.

曹PRO AI 原创：检查短视频脚本、文案、封面和60秒内视频，按六项内容指标评分、说明证据并直接改好。