Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Evaluate every dependency a branch pulls in — client or server, any language — against the WARM check (Worth it, Alive, Right-sized, Maintained securely). Diffs the branch against a base, finds newly added or upgraded direct dependencies across all manifests, and scores each one. Use when the user asks to "WARM check" a branch, vet new dependencies, or review what a PR adds to the dependency tree.
Test Android apps on a rooted device. Decompile APKs, intercept traffic, parse UI, test for IDORs, bypass SSL pinning, hook methods with Frida, inspect exported components, read local storage, and find sensitive data. Use when asked to "test this app", "find bugs", "pentest", "reverse engineer", "decompile", "intercept requests", "check for IDORs", "bypass cert pinning", "hook this method", or "check deeplinks".
Handle structured co-authoring of professional documentation. Use for proposals, technical specs, and RFCs. Use proactively when a collaborative drafting process (Gathering -> Refinement -> Testing) is needed. Examples: - user: "Draft a technical RFC for the new API" -> follow Stage 1 context gathering - user: "Refine the introduction of this proposal" -> use iterative surgical edits - user: "Test if this document is clear for readers" -> run reader testing workflow
Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈ 27× cheaper than ElevenLabs Music). Four endpoints: ACE Step text-to-audio (the default), ACE Step 1.5 text-to-audio (50+ language lyrics, refined structured-lyric handling), ACE Step audio-inpaint (regenerate a time range inside an existing track), ACE Step audio-outpaint (extend an existing track before or after). Triggers on "ace step", "ace-step", "acestep", "ACE music", "open music model", "cheap AI music", "inpaint audio", "audio inpaint", "extend music", "audio outpaint", "lengthen track", "music with tags", or any explicit ask to generate or edit music with ACE Step.
Export this agent's data into a migration bundle for import elsewhere. Use when moving an agent off Starchild or backing up state (e.g. export my memory and tasks, create a migration code, hand off to a new agent). Building a bundle works anywhere. Uploading it to the Starchild migration relay is only available from external agent platforms — a bundle built inside Starchild can be kept as a local backup but not handed off through the relay.
Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image
Walks the user through Charlie Hills's AI Second Brain + Karpathy Wiki setup from the MarTech AI newsletter. Use whenever the user mentions building an AI second brain, the Karpathy wiki, organising their ChatGPT/Claude exports in Obsidian, setting up a living wiki with Claude Code, connecting iMessage Channels, or installing the /today, /ideas, /create slash commands. Trigger on phrases like "set up my second brain", "build the Karpathy wiki", "follow Charlie's newsletter setup", "organise my AI conversations", "Obsidian + Claude Code setup", "I exported my ChatGPT data what now", or any reference to MarTech AI's Karpathy Wiki issue. Use even if the user only mentions one of the three steps (AI Brain, Karpathy Wiki, or Channels + slash commands).
Set up agent context for a project. Analyzes tech stack, installs relevant skills from skills.sh, generates custom skills, and configures MCP servers. Use when starting new project, setting up AI context, or asking "set up project", "configure AI", "what skills do I need".
Generate and maintain project documentation. Creates a lean README as a landing page with detailed docs pages split by topic in the configured docs directory. Use when user says "create docs", "write documentation", "update docs", "generate readme", or "document project".
ALAPI integration assistant. Helps developers search ALAPI endpoints, read ALAPI docs, extract parameters, generate ALAPI integration code, and call ALAPI endpoints after the user explicitly provides a token and confirms. Triggers when users mention "ALAPI", "alapi.cn", an ALAPI docs URL, an ALAPI token, an ALAPI endpoint example, or want to integrate ALAPI platform endpoints.
Alibaba Cloud PolarDB-X Distributed Database AI Assistant. Use for PolarDB-X cluster management, topology inspection, performance diagnostics, SQL optimization, data distribution analysis, elastic scaling diagnostics, connection/session analysis, security audit, backup/restore, parameter tuning, and other O&M operations. Triggers: "PolarDB-X", "distributed database", "pxc-", "DN/CN nodes", "data sharding", "PolarDB-X diagnostics", "PolarDB-X performance", "PolarDB-X slow SQL", "YaoChi Agent", "PolarDB-X topology", "PolarDB-X backup", "PolarDB-X security audit", "PolarDB-X scaling"
Create "[Competitor] alternative" and comparison pages for developer tools. Build honest, high-converting comparison content that ranks for competitive search terms. Trigger phrases: "alternatives page", "comparison page", "vs page", "[competitor] alternative", "competitor comparison", "competitive content", "comparison table", "migration guide", "switch from [competitor]", "compare to [competitor]", "alternative to"
Builds mini-program UIs with Ant Design Mini components for Alipay and WeChat mini-programs. Covers Button, Form, List, Modal, Tabs, NavBar, and 60+ components with theme customization and CSS variable theming. Use when the user needs to create mini-program interfaces with Ant Design Mini, configure themes, or implement mini-program-specific UI patterns.
Use when testing REST, GraphQL, gRPC, or WebSocket APIs against the OWASP API Security Top 10 — object- and function-level authorization (BOLA/BFLA), excessive data exposure, mass assignment, unrestricted resource consumption, and GraphQL-specific abuse. For apps you own or are authorized to test.
Generate API test suites from route definitions across frameworks: auth, input validation, contract, k6 load testing, mocking, and OpenAPI-driven generation. Use when adding new APIs, auditing test coverage, or building regression suites.
Trustworthy multi-tradition astrology. Casts mathematically real charts (Western tropical, Vedic/Jyotish sidereal, Chinese BaZi) from birth data via a deterministic ephemeris engine — never guessed positions — then interprets them with grounded classical rulesets and counsels like a real astrologer. Use for horoscopes, natal/birth-chart readings, kundli, zodiac signs, nakshatras, compatibility/synastry, daily & yearly transits, vimshottari dasha, four pillars of destiny, solar/lunar returns, navamsa/D9, panchang, moon phases, numerology, aspect patterns (Grand Trine, Yod, T-Square), Part of Fortune, Vertex, and "what do the stars say" questions about love, career, money, timing, health, or life purpose.
Produz aulas guiadas em HTML sobre qualquer assunto — telas curtas com pouco texto, um botão Continuar, mocks realistas da ferramenta ou situação, diagramas animados e prática com feedback — e as revisa quadro a quadro via Playwright. Use quando o usuário quiser aprender nesse formato ou transformar material em uma aula interativa. Pergunta apenas idioma, assunto e profundidade ou quantidade de telas; executa pesquisa, roteiro, design, motion, captura, correção e entrega com os recursos incluídos.
Generate, validate, and explain `auth.md` files — the open protocol for AI agent registration. Use when making apps agent-ready, generating Protected Resource Metadata (RFC 9728), validating auth.md files, or implementing agent registration endpoints. Triggers on "auth.md", "agent registration", "agent auth", "make my app agent-ready", "ID-JAG", "identity_assertion", "service_auth", "protected resource metadata", "agentic registration".
Use when authoring or amending developer-tool documentation — the adoption + integration narrative for an SDK, library, CLI, framework, or API platform: the guide a developer reads to install, integrate, and operate the tool. Guides the METHOD, not the outline: developer GOALS not endpoints; a signposted start-here + a fast verifiable first success; concepts before recipes; goal-named runnable recipes; an end-to-end tutorial; grounded best-practices; a troubleshooting path; archetype-aware emphasis (API/SDK/CLI/framework); POINTERS into — never a copy of — the api-reference; and amending a guide as a versioned delta that sweeps the tool's changes for stale samples. Full Diataxis correctly typed, every sample runnable + accurate to the tool, nothing fabricated. Composes with a template tool + deep-research. Consumes the handed-in feature-spec + api-reference + PRD — never a blank page. Not the api-reference catalog, the end-user user-guide, engineering docs, or reviewing one.
Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".
Best practices for Bloc state management in Flutter/Dart, covering Cubit versus Bloc, event and state naming, sealed classes with Equatable, the Page/View split with BlocProvider, BlocBuilder, BlocListener, and BlocSelector. Use when writing, modifying, or reviewing code that uses package:bloc, package:flutter_bloc, or package:bloc_test. Also use for any test of a class that extends Bloc or Cubit, including "write the unit tests for this bloc", "test my cubit", "add tests for LoginBloc", mocking a repository a bloc depends on, and asserting the states an event emits. Bloc and Cubit tests must use blocTest() from package:bloc_test with package:mocktail, so prefer this over the testing skill whenever the class under test is a Bloc or Cubit. Also use when a request pushes against these rules, such as injecting one bloc into another to read its state, calling a repository from a widget or build method, or keeping a Cubit for a feature that needs an event transformer such as debounce.
Shared building blocks for Box-based legal workflows — Box collaboration role definitions, Box AI usage boundaries (what AI must not decide), and reusable human-in-the-loop confirmation phrasings. Referenced by box-legal-workflows-ma, box-legal-workflows-intake, and box-legal-workflows-contract skills.
Generates a rich, visual HTML one-pager that lets a busy reviewer understand a body of changes and either approve a proposed PR stack or merge a finished one — without reading the diff themselves. Auto-detects whether the run is DRAFT (working-tree changes plus a proposed stack, pre-approval) or FINAL (a real PR stack with review complete, pre-merge). Leads with a TL;DR, surfaces the PR stack near the top, flags high-stakes changes (endpoints, auth, schema), then walks the reviewer through the important code as a numbered Code Tour with inline diff snippets. Use whenever someone wants to eyeball a change before approving or merging — "review the changes", "show me what changed", "summarize the diff / the branch / the stack", "what am I about to approve", "walk me through what shipped", "explain the final code", or any shipping-workflow approval/merge gate — even if they don't say the words "brief" or "HTML".
Score a page for how well AI answer engines can CITE it — Answer Engine Optimization, not classic rankings — by pulling structured data, meta, headings, and answer-shaped content via the `browse` CLI (schema/meta/headings/text) into a weighted 0-100 audit, plus a SERP mode that reads Google AI Overviews, Perplexity, and ChatGPT Search snapshots to see who actually gets cited. Never fabricates a score: an un-evaluable dimension is marked N/A, and "appears in AI Overviews" is asserted only after a real SERP check. Use to make a page answer-ready or to check its AI-answer visibility.
Run a full on-page technical SEO audit from a LIVE render — real rendered signals, not source guesses — extracting meta tags, heading hierarchy, structured data, navigation timing, link structure, and multi-viewport mobile rendering via the `browse` CLI (meta/headings/schema/perf/ links/responsive plus targeted JS checks), then rating each area PASS/WARNING/FAIL with prioritized fixes. The agent interprets the raw signals browse extracts; no scores are invented. Use to audit a page's technical/on-page SEO health.
Design the right business model for monetizing skills and expertise. Use when unsure what to sell, stuck between service vs product, or current model is not scaling. Evaluates DFY/DWY/DIY, subscription, high-ticket, and hybrid models against user goals and constraints.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
