agent-skills
thatjuan/agent-skills
AI agent skills for Claude Code
Instalação
npx convez-ai thatjuan/agent-skills1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
README
A tradução para o português deste README ainda está na fila.
Agent Skills
A curated collection of AI agent skills for Claude Code and compatible agents.
Overview • Skills Catalog • Getting Started • Skill Anatomy • Creating Skills
Overview
Agent Skills are self-contained instruction sets that give AI coding agents specialized capabilities. Each skill defines a complete workflow — from persona construction to execution strategy — that an agent can follow to accomplish complex, multi-step tasks autonomously.
This repository is designed for use with the skills CLI. Install individual skills or the entire collection into your project, and your AI agent gains new abilities instantly.
Skills Catalog
| Skill | Description |
|---|---|
| commitpush | npx skills add thatjuan/agent-skills --skill commitpushSafe commit-and-push workflow with secrets detection, sensitive file screening, and submodule-aware prompting. Use when committing and pushing changes to git, especially in repos with submodules or when security-conscious commits are needed. |
| creative-director | npx skills add thatjuan/agent-skills --skill creative-directorWorld-class creative director for branding, web design, and UI concepts. Use when the user asks for a new design concept, brand identity, website creative direction, UI experience concept, visual identity, or creative strategy for a business, product, or project. Produces detailed, richly described creative concepts — not code or implementations. |
| team-executor | npx skills add thatjuan/agent-skills --skill team-executorMulti-agent orchestration that transforms braindumps into executed results. Assembles expert planning teams (3-7 agents), produces comprehensive execution plans, then deploys fresh execution teams for autonomous delivery |
| temporal | npx skills add thatjuan/agent-skills --skill temporalExpert Temporal.io workflow orchestration for Python and TypeScript. Use when code imports temporalio/sdk-python or @temporalio/* packages, user asks about durable execution, workflow orchestration, AI agent orchestration with Temporal, or building reliable distributed systems with Temporal |
| heroui | npx skills add thatjuan/agent-skills --skill herouiHeroUI v3 component library expertise for React (web) and React Native (mobile). Use when code imports @heroui/react, @heroui/styles, or heroui-native, user asks to build UI with HeroUI, or references HeroUI components, theming, or migration from NextUI/HeroUI v2 |
| drizzle-orm | npx skills add thatjuan/agent-skills --skill drizzle-ormType-safe SQL ORM for TypeScript with zero runtime overhead. Use when code imports drizzle-orm, drizzle-kit, or drizzle-orm/pg-core, user asks about Drizzle schema design, queries, relations, migrations, or database management with Drizzle ORM |
| logo-studio | npx skills add thatjuan/agent-skills --skill logo-studioProfessional logo design studio that produces 9+ SVG logo concepts through brand discovery, archetype mapping, and iterative refinement, then generates a complete app asset package (iOS, Android, macOS, Windows, favicons, PWA, social) from the final selection and optionally produces a multi-page brand guidelines document (logo, color, typography, layout, UI components, motion, voice, asset management). Use when the user asks for a logo, brand mark, icon, wordmark, app icon, visual identity, or brand guidelines for a business, product, or project. |
| atlassian-cli | npx skills add thatjuan/agent-skills --skill atlassian-cliAtlassian CLI (acli) expertise for interacting with Jira Cloud and Atlassian organization admin from the terminal. Use when scripts invoke acli, user asks about Atlassian CLI, Jira CLI, JQL-driven automation, bulk Jira operations, or managing Jira work items, projects, boards, sprints, filters, fields, dashboards, Atlassian org admin users, or Rovo Dev authentication. |
| cloudbeds-api | npx skills add thatjuan/agent-skills --skill cloudbeds-apiCloudbeds hospitality API expertise for building property-management, booking, payments, accounting, and channel integrations. Use when code calls api.cloudbeds.com, hotels.cloudbeds.com, api.payments.cloudbeds.com, or imports a Cloudbeds SDK; when the user asks about Cloudbeds PMS, reservations, rate plans, webhooks, Pay-By-Link, Payments Vault, Accounting API, Data Insights, Fiscal Documents, or Group Profile APIs; when authenticating with cbat_-prefixed API keys or OAuth 2.0 against Cloudbeds; when subscribing to Cloudbeds webhooks or working with postReservation, getAvailableRoomTypes, postCharge, patchRate, or similar operations. |
| camofox-browser | npx skills add thatjuan/agent-skills --skill camofox-browserDeploy, configure, and use camofox-browser — the Camoufox-engine anti-detection browser server (REST API on port 9377) for AI agents. Use when code hits the /tabs, /sessions/:userId/cookies, or /youtube/transcript endpoints; when scripts install @askjo/camofox-browser, run npm start in the camofox-browser repo, or call make up/make fetch; when agents invoke OpenClaw camofox_* tools; when the user asks about Camoufox fingerprint spoofing, bypassing Cloudflare/Google bot detection, element refs (e1, e2), accessibility snapshots, search macros, Netscape cookie import, per-user session isolation, backconnect proxy rotation with GeoIP, VNC/noVNC login, writing plugins with register(app, ctx), CAMOFOX_*/PROXY_* env vars, or deploying to Docker/Fly.io/Railway. |
| browserbase-sdk | npx skills add thatjuan/agent-skills --skill browserbase-sdkBrowserbase cloud-headless-browser SDK expertise for TypeScript/Node. Use when code imports @browserbasehq/sdk, @browserbasehq/stagehand, playwright-core, or puppeteer-core and connects to Browserbase; when code POSTs to api.browserbase.com/v1/sessions, /v1/contexts, /v1/extensions, or /v1/projects; when sending the x-bb-api-key header or using BROWSERBASE_API_KEY/BROWSERBASE_PROJECT_ID; when the user asks about Browserbase sessions, contexts, proxies, downloads, uploads, recordings, live debugger URL, captcha solving, advanced stealth, verified browsers, fingerprinting, BYOS S3 storage, regions (us-west-2/us-east-1/eu-central-1/ap-southeast-1), keepAlive, the connectUrl CDP WebSocket, chromium.connectOverCDP, puppeteer.connect({browserWSEndpoint}), the browser.contexts()[0] default-context pattern, Stagehand act/extract/observe/agent primitives, the Model Gateway, or deploying serverless via Browserbase Functions. |
| video-storyboard | npx skills add thatjuan/agent-skills --skill video-storyboardWorld-class video storyboard writer for marketing, advertising, brand films, social spots, and product videos. Use when the user asks for a storyboard, video script, ad concept, commercial treatment, video pitch, or shot-by-shot breakdown for any film, ad, social video, explainer, or brand content. Produces an all-text markdown storyboard with richly described visuals (no images, no sketches) — every frame includes shot, action, on-screen text, voiceover, dialogue, sound, and timing. Grounded in the canonical literature on marketing storytelling and ad video production (Donald Miller's StoryBrand, Joseph Campbell / Christopher Vogler's Hero's Journey, Blake Snyder's Save the Cat, Pixar's 22 Rules of Storytelling, Chip & Dan Heath's Made to Stick, Luke Sullivan's Hey Whipple Squeeze This, David Ogilvy's Ogilvy on Advertising, Giuseppe Cristiano's The Storyboard Artist). |
| openrouter-api | npx skills add thatjuan/agent-skills --skill openrouter-apiOpenRouter unified-LLM-API expertise. Use when code POSTs to openrouter.ai/api/v1, imports @openrouter/sdk, openrouter (Python), or @openrouter/agent; when the OpenAI SDK is pointed at https://openrouter.ai/api/v1; when the user asks about routing across hundreds of LLMs (OpenAI, Anthropic, Google, DeepSeek, Meta, xAI, Mistral, etc.) through one endpoint; when working with provider routing, model fallbacks (models array), the Auto Router (openrouter/auto), :nitro/:floor/:online model suffixes, presets (@preset/...), prompt caching with cache_control, structured outputs, tool calling, the openrouter:web_search server tool, reasoning tokens, multimodal (image/PDF/audio/video) inputs, BYOK provider keys, OAuth PKCE, the openrouter: plugins (web, file-parser, response-healing, context-compression), or generation/usage accounting via /api/v1/generation and /api/v1/key. |
| grok-imagine-api | npx skills add thatjuan/agent-skills --skill grok-imagine-apixAI Grok Imagine API expertise for generating, editing, and refining images through xAI REST, xai_sdk, OpenAI-compatible SDKs, and Vercel AI SDK. Use when code calls api.x.ai/v1/images/generations or api.x.ai/v1/images/edits, imports xai_sdk or @ai-sdk/xai, points an OpenAI SDK at https://api.x.ai/v1, or mentions Grok Imagine, grok-imagine-image, grok-imagine-image-quality, aspect_ratio, image editing, image variations, base64 image output, or sample_batch(). |
| implement-issue | npx skills add thatjuan/agent-skills --skill implement-issueEnd-to-end GitHub issue delivery via team-executor. Given an issue number (or URL), opens a feature branch, dispatches a stack-specialized planning team to decide the implementation path (unless the issue dictates it), confirms a TL;DR with the user (or decides autonomously when asked), posts the agreed approach as an issue comment, launches a fresh execution team to build it, and opens a pull request. Use when the user provides only a GitHub issue number, an issue URL, or asks to "implement issue #N", "work on issue N", "ship issue N", or similar. |
| software-engineer | npx skills add thatjuan/agent-skills --skill software-engineerThe architect, developer, and reviewer engineering subject-matter expert and base engineering layer for coding agents. Stage 3 of the implement-issue → team-executor → software-engineer pipeline: team-executor assigns it to any agent that writes, updates, or reviews code (it can also be invoked explicitly), holding the work to a strict engineering bar across its Three Lenses and Eight Standards. Applies equally to new code and changes to existing code. Carries standards for structural simplicity, clean architecture, typed boundaries, decomposition, reuse, per-domain practice (backend, frontend, data, devops, security, testing), and a self-review gate run as definition-of-done. Stack-specific skills (heroui, drizzle-orm, temporal) overlay on top of this one. |
| openwa | npx skills add thatjuan/agent-skills --skill openwaOpenWA WhatsApp API Gateway expertise — deployment, sessions, REST API, webhooks, real-time events, SDKs, plugin architecture. Use when working in an OpenWA repo or with a self-hosted gateway based on it; when code hits port 2785, builds the openwa-api Docker service, or fronts the dashboard on 2886; when scripts send X-API-Key: owa_k1_… headers; when configuring whatsapp-web.js sessions via POST /api/sessions/:id/start, sending messages via POST /api/sessions/:sessionId/messages/send-text, or subscribing to message.received/message.sent/message.ack/session.status webhooks with X-OpenWA-Signature HMAC; when working with the /events Socket.IO namespace, the @openwa/sdk JS client, the openwa Python package, plugin hooks (message:sending, message:sent), or n8n integration. |
| unifi-operator | npx skills add thatjuan/agent-skills --skill unifi-operatorOperate UniFi Network and UniFi Protect through their local APIs on a UDM, UDM-Pro, Cloud Key, or self-hosted console. Use when managing UniFi gateways, switches, access points, clients, firewall, VLANs/WLANs, port-forwards, or hotspot vouchers; when controlling Protect cameras, recordings, snapshots, smart-detection events, lights, sensors, chimes, or alarms; when building curl calls to /proxy/network or /proxy/protect; or when the user mentions UniFi, Ubiquiti, UDM, Cloud Key, UniFi OS, controller API keys, or X-API-KEY. Covers both the official API-key integration APIs and the reverse-engineered private controller/Protect APIs plus the realtime WebSocket. |
Click a skill above for full details, example prompts, and bundled resources.
Getting Started
Prerequisites
- Node.js >= 18
- An AI agent that supports skills (e.g., Claude Code)
Install a specific skill
npx skills add thatjuan/agent-skills --skill team-executor
Install all skills
npx skills add thatjuan/agent-skills --all
Once installed, skills are available to your AI agent automatically. Invoke them by describing a task that matches the skill's trigger — for example, pasting a braindump of project ideas will activate the team-executor skill.
Verify installation
After installation, you should see the skill files in your project's skills directory and a skills-lock.json tracking installed skills:
{
"version": 1,
"skills": {
"team-executor": {
"source": "github/thatjuan/agent-skills",
"sourceType": "github"
}
}
}
Skill Anatomy
Each skill follows a consistent structure:
skill-name/
SKILL.md # Skill definition (required) — YAML frontmatter + instructions
*.md # Bundled reference docs (optional)
*.sh # Helper scripts (optional)
The SKILL.md file is the entry point. Its YAML frontmatter defines the skill's name and description (used for trigger matching), followed by the full instructions the agent will follow.
[!NOTE] Reference files like
agent-templates.mdandorchestration-workflow.mdare loaded by the agent at runtime — they keep the mainSKILL.mdfocused while providing depth on demand.
Creating Skills
Want to add a new skill to this collection? Each skill should:
- Solve a specific, repeatable problem — skills work best when they encode a well-defined workflow
- Be self-contained — include all instructions, templates, and scripts the agent needs
- Use rich frontmatter — write a descriptive
descriptionfield with trigger phrases so agents know when to activate the skill - Include bundled resources — break complex workflows into reference docs rather than stuffing everything into
SKILL.md - Be production-oriented — skills should produce real, working output — not drafts or placeholders
---
name: my-skill
description: Short description of what this skill does and when to use it.
---
# My Skill
Instructions the agent follows...