Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
[漫剧老李AIGC Full-Process Skill · V7.5.0-SLIM Compact Edition] An industrialized screenwriting and audiovisual directing system for hit short dramas and animated dramas on Douyin/Hongguo (1 controller + 10 subskills · four layers of depth). Covers the full pipeline from script development → storyboards → asset prompts → fight scenes → feeding scripts → output quality checks, producing video prompt sets ready to feed directly into Seedance 2.5 / 2.0 (model version must be locked). Five required locks before starting (① source material ② model version ③ aspect ratio ④ delivery format ⑤ shot transitions) plus a visual style lock: if any is unspecified, stop and ask the user, presenting options for them to select. Never skip by default or make assumptions on the user's behalf—these are hard gates, not suggestions. Also includes three fixed action-intensity levels. Use for writing short-drama scripts, adapting novels, episode outlines, storyboard scripts, 3×3 scene images and character portrait prompts, fight-scene storyboards, dialect dubbing annotations, feeding-script generation, and output self-checks. The user can simply state the request; the controller routes it to the appropriate subskill automatically, so they need not understand the division of work (but the locks must be asked).
Organizes and rewrites prose and notes into outline-style bullet points built around claims and supporting evidence. Use for requests such as "write an outline" or "organize the key points into bullets". Do not use for listing items or task management. For slide creation, do not launch it on its own; it handles only the outline structure as a dependency of the `shunk031-writing-technical-slides` skill.
Rewrites technical explanations and paper-summary slide text into a structure where the hierarchy of sections and slide items is immediately clear. Do not use for general telegraphic style, retrospectives, slide visual design, or file creation
Reorganizes or rewrites articles and notes as concise telegraphic-style outline bullets, omitting words clear from context and conveying one idea per line. Use for requests like “write a report,” “make it an HTML report,” “in telegraphic style,” or “shorten the bullet points.” Do not use when the request is only to proofread or polish a report that remains in paragraph form. For technical slides, do not trigger independently; it only handles the writing style as a dependency of the `shunk031-writing-technical-slides` skill. Do not use to create slide files
Apply Edward de Bono's Six Thinking Hats methodology to software testing for comprehensive quality analysis. Use when designing test strategies, conducting test retrospectives, analyzing test failures, evaluating testing approaches, or facilitating testing discussions. Each hat provides a distinct testing perspective: facts (White), risks (Black), benefits (Yellow), creativity (Green), emotions (Red), and process (Blue).
Create beautiful web presentations from a topic, rough notes, or an outline, and edit decks afterward — adding, removing, or revising slides. Generates a custom theme and a short two-slide preview, then builds the full deck only once the user confirms the direction; edits to an existing deck skip that flow and apply in place. Use when the user wants to make slides, a presentation, a talk deck, a pitch deck, or to add/remove/change a slide in one that already exists
Use when you need to execute R3 (prototype generation) in the sdlc-dev product requirements Spec workflow, producing requirements/prototype.md from requirements/prd.md (task flow + page structure + ASCII wireframes + AC mapping + walkthrough script), and avoid continuing to generate when context or the PRD is missing, replacing the validation checklist with Open Questions, or using non-ASCII formats that make the prototype untraceable and unreviewable.
Use when the user is asking how Spree's domain models relate — Orders, LineItems, Variants, Products, Stores, Channels, Markets, Payments, Shipments, Customers, Adjustments. Architecture and relationships only. Common phrasings include "how does X connect to Y", "what's the relationship between", "where does Spree store X", "how do I query orders across stores", "how do channels work", "what's the difference between Cart and Order", "Store vs Channel vs Market". For adding new models / new API resources, use the `spree-resource` skill. For field-level detail, see `docs/developer/core-concepts/` in the installed `@spree/docs` package.
Open an acceptance-testing session — the user is about to try finished work by hand. Points them at the feature's ACCEPTANCE.md, or writes one from what actually changed when there is none, then takes their notes, screenshots and corrections one at a time, recording each verdict beside its check and fixing or carrying what it finds. Anything that looks like a pattern rather than an incident — a missed requirement, a recurring bug, a design error — is written as a candidate to docs/acceptances/ATTENTION.<feature>.md for end-acceptance to promote, with the user, into docs/acceptances/ATTENTION.md. Runs no test suite during the session, because it is too slow while a person waits; end-acceptance runs it once. Use when the user says they are starting acceptance, about to test or try the feature, or invokes /start-acceptance <feature>.
Open a pull-request review session — you are the reviewer, not the author. Asks for the spec the change was written from, reads the project's principles and best practices, then reviews the diff for unnecessary complexity, smelly code and drift from the spec, reporting findings first and recording what the user decides on the PR itself. Hands over to start-acceptance once the findings are settled. Use when the user says they are starting a PR review, asks to review a pull request or a branch someone else wrote, or invokes /start-pr-review <pr or branch>.
Set up Tailwind v4 with shadcn/ui using @theme inline pattern and CSS variable architecture. Four-step mandatory pattern: define CSS variables at root, map to Tailwind utilities, apply base styles, get automatic dark mode. Use when: initializing React projects with Tailwind v4, setting up shadcn/ui dark mode, or fixing colors not working, theme not applying, CSS variables broken, tw-animate-css errors, or migrating from v3.
Decide which tests are worth having. Use whenever writing, changing, reviewing, or pruning tests: a gate for every new test, and an audit workflow for tests that re-assert source, mirror the code under test, test mocks, duplicate stronger coverage, or keep test-only production code alive. Triggers: adding a regression test, 'clean up the tests', 'these tests are flaky/brittle', mock-heavy suites, coverage-driven tests.
Generate a Transilience-branded PDF report (pentest, vuln assessment, compliance, threat intel) from a single findings JSON using the bundled ReportLab generator. Use whenever an engagement needs its final report/deliverable PDF in Transilience house style.
UTM parameter strategy, campaign tracking, and marketing attribution modeling. Build consistent UTM taxonomies, configure attribution models, measure cross-channel performance, and connect marketing spend to revenue. Use when the user asks about UTM parameters, campaign tracking, attribution models, marketing measurement, or cross-channel analytics.
Design or critique a checkout, cart, payment, or booking flow — the path from "ready to buy" to "order confirmed." Applies the conversion-protecting core (guest checkout, transparent cost summary, inline validation, processing feedback, confirmation) and gates context-dependent levers (name fields, payment-method count, single- vs. multi-step, booking date pickers, promo-code prominence) with trade-offs. Trigger when designing or reviewing a checkout page, shopping cart, payment form, card-entry screen, promo/discount code, booking/reservation flow, or when checkout/cart abandonment needs improving.
Design or critique a user-onboarding flow — the first-run experience that gets users to value fast. Gates context-dependent choices (onboarding method, progressive profiling, product tours) and applies the always-true core. Trigger when designing welcome screens, first-run experiences, product tours, activation flows, or when onboarding drop-off needs improving.
Use when the user explicitly asks for vibe brainstorming, creative implementation ideas, implicit expected behavior, or convention checks, and when an implementation task is creative or convention-dependent. Do not use for obvious mechanical edits.
Video creation skill. Composites video from images + audio, supporting TTS voiceover, fade-in/fade-out transitions, subtitles, end credits, and BGM. Triggers when the user mentions "generate a video", "make a video", "tutorial video", "turn images and text into a video", "make a video for a video channel", "voiceover video", "image-and-text video", "classical poem video", or "story video". Includes the full image generation → voiceover → compositing pipeline, so image-service does not need to be called separately.
Plan and integrate ShengShu Vidu Open Platform video generation with current model/mode selection, reference consistency, pricing, exact approval, async task handling, and safe artifact custody. Use for Vidu API text-to-video, image-to-video, start/end-frame, multi-subject reference, media-reference, or Q2 multi-frame work; do not conflate the API with vidu.com consumer plans or Vidu-S1 streaming digital humans.
10 proven viral video hook templates with FFmpeg implementations for maximum first-3-second retention. PROACTIVELY activate for: (1) Video hook creation, (2) Opening sequence optimization, (3) Attention-grabbing techniques, (4) Pattern interrupt effects, (5) Curiosity gap implementation, (6) Text overlay hooks, (7) Visual hook effects, (8) Audio hook strategies, (9) Retention optimization, (10) Scroll-stopping content. Provides: Research-backed hook formulas, FFmpeg filter implementations, psychological triggers, platform-specific hooks, A/B testing workflows, and real-world examples with measurable impact.
Specify any visual piece —a product interface, a presentation, an infographic— screen by screen or slide by slide: purpose, structure, hierarchy, the content of every block and the visual criteria applied, written as a dated document of the loaded product node. It closes by checking whether the session has a tool able to build it and only then offers to; with no tool it closes with the document. Manually triggered, invocable on its own.
Intelligently create and publish WeChat Official Account articles. Supports AI article generation, link publishing, Markdown conversion, image cleanup, style processing, and one-click publishing. Use when the user mentions "创作公众号文章", "发布文章链接", "生成微信文章", "推送到微信公众号", "发布到微信公众号".
Write the release descriptor and notes for the next release on a channel (stable, beta, nightly, or whatever the project names), following the project's own release-writing instructions. Use when the user asks for release notes, a changelog entry, a release descriptor, or “the next nightly / beta / stable.” Gathers what is published now and what this tree holds, lets the project's instructions choose the version and format, writes the file, and never publishes.
Optimizes X/Twitter content for algorithm engagement signals using xai-org/x-algorithm's Grok transformer predictions. Activates for tweet optimization, thread strategy, X growth, algorithm-aligned content, improving X/Twitter engagement, or maximizing reach on X.
Build Zalo Mini Apps - lightweight web apps running inside Zalo super-app. This skill provides ZaUI components (Button, Input, Modal, Tabs, Avatar, etc.), JavaScript APIs (authorize, getUserInfo, getPhoneNumber, getLocation, Storage, Camera), Checkout SDK for payments, design guidelines, and development tools. Use when building Mini Apps, using ZaUI components, calling Zalo APIs, integrating payments, converting web apps to Mini Apps, or following Zalo design standards.
Zod schema validation best practices for type safety, parsing, and error handling. This skill should be used when defining z.object schemas, using z.string validations, safeParse, or z.infer. This skill does NOT cover React Hook Form integration patterns (use react-hook-form skill) or OpenAPI client generation (use orval skill).
Step-by-step guide for executing token swaps using the 0x API (Swap API v2 and Gasless API v2). Use this skill when a user wants to: swap tokens on any EVM chain (e.g. "swap 0.5 ETH for USDC on Arbitrum", "sell 1000 ARB and get a quote", "how much WBTC for 5000 USDC on Base"); do a gasless swap without holding ETH for gas; integrate 0x into a dApp in TypeScript or Python (permit2 flow, allowanceholder flow); use 0x with a Gnosis Safe or multisig wallet; migrate from 0x Swap v1 to v2; debug 0x API errors like INSUFFICIENT_ASSET_LIQUIDITY or allowance issues; or understand when to use AllowanceHolder vs Permit2. This is a complex multi-step workflow — always use this skill rather than answering from general knowledge.
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
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.
