Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Format a finalized long-form article as mobile-friendly WeChat Official Account rich text and generate a preview; after Ray explicitly approves, write or update the WeChat draft box and read it back for verification. Use for “format for the public account”, “push to the WeChat draft box”, or “update the WeChat draft”. If the request is ambiguous, only create a preview first; do not publish or send to all followers.
Write a completed long-form article and its 5:2 cover to the logged-in X Articles dashboard as a draft, check the preview, and write the draft URL back to the knowledge base. Use for “put it in the X dashboard”, “save as an X Article draft”, or “push it to X”. Draft only: do not click Publish or create another draft on the same topic.
Cheminformatics toolkit for molecular analysis and virtual screening: SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints (Morgan/ECFP, MACCS), Tanimoto similarity, SMARTS substructure filtering, Lipinski drug-likeness, reaction enumeration, 2D/3D coordinates. For simpler API use datamol; use RDKit for fine-grained sanitization, custom fingerprints, or SMARTS/reaction control.
Game reverse engineering: Unity/Unreal, Cheat Engine, Lua script engines, graphics shaders. Triggers: game reverse engineering, Unity, Unreal, Cheat Engine, memory modification, anti-cheat, Lua, LuaJIT, .luac, .jsc, script engine, Shader, shader, SPIR-V, DXIL, DXBC, GLSL.
Move items only, reword nothing; realign a listing whose order has gone arbitrary (a list, table, catalog, sections, an enum) into a logical sequence under one stated principle. Nothing is added or removed. Use when the user names a listing, or a scope holding one, whose order no longer helps a reader follow the set, or when a pipeline the user invoked passes that scope on. Acts only inside that scope.
Fix code in a named change or file list so it matches the conventions its own repository already keeps: run the project's configured formatter and linter in fix mode through the project's own toolchain, then fix by hand what no tool decides (naming, import order, file layout, error style) toward the dominant pattern in neighbouring files, behavior preserved, and ask with counts where the repository keeps two competing conventions. Use for 'make this match the codebase', formatter or linter setup, naming consistency, or a style pass on a change under review. Acts only inside the change or files the user names.
Read one stated intent, pick and order the installed skills that serve it, show that order, then run the steps the session may run and stop where a person must act. Use when someone states a goal but does not know which skills serve it or in what order, asks which skills to use, or wants a job that needs several skills run end to end. Typing /paperthin lands here.
Provides comprehensive guidance for React development including components, JSX, props, state, hooks, context, performance optimization, and best practices. Use when the user asks about React, needs to create React components, implement hooks, manage component state, or build React applications.
Build React 19 applications with TypeScript. Covers Actions, Activity, use() hook, React Compiler, ref-as-prop, useEffectEvent, and strict TypeScript patterns. Use when creating components, managing state, typing props, handling events, using hooks, or working with React 19 features. Triggers on react, typescript, tsx, component types, hook types, react 19, react compiler, actions, use hook, useEffectEvent, activity, import defer.
Use when a wallet wants to create a launch on Realbond (1% tax token; open to any wallet), when an Agent ID holder wants to bind its X account from a website-signed binding.json, buy (needs Agent ID + X binding) or sell a launch on its bonding curve, process tax or claim tax-token dividends (paid in the token), or check its binding or position on BSC. Every transaction goes through the Binance Agentic Wallet (`baw contract-call`) with a human confirmation before execution
Deep recursive research with a self-regulating loop up to PhD level. Applicable to any domain (science, technology, business, art, humanities). Uses WDM + Munger inversion for autonomous decisions, trusted-source tiering, and disk checkpointing to survive context limits.
A skill for judging whether refactoring (including redesign of structure, boundaries, and contracts) is needed and how to proceed, in the direction of improving changeability. Use when told "refactor this", "tidy this up", or "clean this up" after local development is complete, when code is hard to understand or maintain, or when Code Smells need to be addressed. For detailed decisions on how to draw boundaries and place responsibilities, use module-boundary-design.
Create polished, code-driven Remotion motion explainers from scripts, narration, subtitles, product specifications, reference videos, UI recordings, diagrams, or abstract concepts. Use for product launches, AI demonstrations, UI interactions, algorithms, scientific principles, electrical systems, data flows, architecture, charts, equations, and concepts best expressed with React, SVG, Canvas, WebGL, or Three.js. Prioritize continuous spatial logic, visible cause and effect, precise interaction states, editable parameters, deterministic rendering, and evidence-backed visual QA.
Guide and operate resume-canvas (a local HTML visual resume fine-tuning editor), validate its editing protocol, fine-tune text and layout, and complete the post-save fact-checking loop. Use when the user wants to preview a visual resume, make small text edits, adjust layout (font size, spacing, colors, margins), launch the local editor, or troubleshoot the editing protocol.
This skill MUST be used for product-review salience scoring (0–7), review × attribute Excel matrices, or PCA and K-means analysis of those review scores (逐則評論評分、提及程度、顯著度矩陣、評論×屬性 Excel、評論 PCA、評論分群). It MUST support requests for individual stages and MUST NOT be used for unrelated PCA or clustering tasks.
Use when reviewing/judging a finished data-model document (the persistence/ domain model — entities, keys, relationships, indexes, normalization, lifecycle) to decide if an engineer can build the schema + query it correctly — an acceptance gate, not authoring. Judges it against a single-sourced 9-condition integrity + queryability bar: entities typed + keyed (stored shape, not the api-spec DTO); relationships carry cardinality + a referential rule (on-delete / embed-vs-reference); every index traces to an access pattern; normalization + paradigm choice + tradeoffs; lifecycle + migration; diagram ⇄ tables in sync; privacy/scale; one-directional vs the api-spec + consistent with the shipped schema; amend delta-scoped. Paradigm-aware (relational/document/graph/wide-column/key-value — never a relational reflex). Emits exactly `VERDICT: approve|revise` — approves a model meeting the bar, revises on a named gap. Not for authoring, the api-spec/feature-spec, or generic design docs (use design-review).
Pipeline skill for CMS-HCC risk adjustment calculation and coding gap identification. Use when the user asks to apply the ICD-10-to-HCC crosswalk, calculate RAF scores, resolve disease hierarchies programmatically, identify coding gaps from Rx or lab proxies, project member-level risk scores, build a risk adjustment data pipeline, compute HCC coefficients, run hierarchy resolution code, or generate member risk score reports. Triggers include "calculate RAF score", "ICD-10 to HCC crosswalk", "hierarchy resolution code", "coding gap detection", "Rx proxy gap", "lab proxy gap", "risk score projection", "HCC pipeline", "member risk report", "risk adjustment Python", "risk adjustment SQL", "RAF calculation code", "CMS-HCC pipeline".
Reasoning skill for CMS-HCC risk adjustment strategy and methodology. Use when the user asks about CMS-HCC model versions V24 or V28, blended transition methodology, ICD-10-to-HCC mapping logic, disease interaction hierarchies, RAF score methodology, risk adjustment factor calculation, coding gap identification, audit-defensible documentation, HCC recapture strategy, prospective vs retrospective risk adjustment, or Medicare Advantage risk scoring. Triggers include "CMS-HCC", "V24", "V28", "blended transition", "HCC mapping", "disease hierarchy", "RAF score", "risk adjustment", "coding gap", "HCC recapture", "chart review", "audit defensible", "risk score methodology", "Medicare Advantage risk", "capitation revenue", "hierarchical condition category".
Reasoning skill for clinical risk stratification index selection and interpretation. Use when the user asks about LACE scores, Charlson Comorbidity Index, Elixhauser Index, readmission risk scoring, comorbidity weighting, SDOH Z-codes, Area Deprivation Index, or population health stratification methods.
Bulk RNA-seq analysis pipeline covering alignment (STAR), quantification (Salmon, featureCounts), and differential expression (DESeq2). Triggers on RNA-seq, STAR, Salmon, DESeq2, differential expression, gene expression, tximport, featureCounts, transcriptomics, "bulk RNA-seq", "STAR alignment", "Salmon quantification", "gene counts", "DESeq2 results", "shrinkage estimator", "volcano plot RNA-seq".
Roblox Luau development — implement, review, and refactor Luau gameplay scripts; diagnose Roblox gameplay, replication, performance, DataStore, and runtime issues; and understand or sync Rojo-managed Roblox codebases. Use when working on Roblox, Luau, Roblox Studio code, or Rojo projects, or when debugging Roblox runtime issues.
Development guidance for writing idiomatic Rust. Use when: (1) writing new Rust functions or modules, (2) choosing between borrowing, cloning, or ownership patterns, (3) implementing error handling with Result types, (4) optimizing Rust code for performance, (5) configuring clippy and linting for a project, (6) deciding between static and dynamic dispatch, (7) writing documentation or doc tests.
Sa-Token integration extension skill. Covers JWT integration (comparison table of Simple/Mixin/Stateless modes), Redis persistence (JDK serialization/JSON serialization), Alone-Redis standalone Redis (isolating auth cache from business cache), AOP annotation-based authorization (using annotations in the Service layer), SpEL expression annotations (@SaCheckEL), Quick-Login quick login (zero-code login page), JSON serialization extensions (Jackson/Fastjson/Fastjson2/Snack3), template engine integration (Thymeleaf/Freemarker tag dialects), and RPC integration (Dubbo/Dubbo3/gRPC context propagation). Use when users need to integrate JWT for stateless authentication, configure Redis distributed sessions, isolate caches, use annotation-based authorization in the Service layer, or quickly build a login page. For basic login authentication, use the sa-token skill first.
Sa-Token microservice authentication skill. Covers the Same-Token mechanism for isolating internal services from the public network, unified authentication at the SpringCloud Gateway (Reactor reactive), authentication for internal RPC calls via Feign/Dubbo/gRPC, distributed Session schemes (Redis Session center / stateless JWT), Reactor/WebFlux framework integration, and SpringBoot3/4 dependency adaptation. Use when the user needs service-to-service authentication in a microservice architecture, gateway Token forwarding and validation, isolation of internal services from the public network, or distributed session sharing. For basic login authentication, use the sa-token skill first.
Sa-Token OAuth2.0 server-side skill. Covers the four grant types: Authorization Code, Implicit, Password, and Client Credentials. Includes complete OAuth2-Server setup, the SaOAuth2DataLoader data loader, custom and tiered Scope permissions, the OIDC protocol, OpenId/UnionId, custom grant_type, custom login authorization pages, annotation-based Access-Token validation, interoperability with login sessions, Scope level control, and custom API routes. Use when the user needs to build an OAuth2.0 authentication server, develop an open platform, or implement third-party application authorization. For basic login authentication, use the sa-token skill first.
Writes and structure a Qwilr proposal page that closes deals. Use when your proposals look generic and aren't closing, you don't know what sections to include, the pricing table confuses buyers, your proposal doesn't stand out from competitors, or you're staring at a blank Qwilr page and need a structure that sells. Do NOT use for a multi-stakeholder deal room (use /sales-deal-room), reusable team templates (use /sales-proposal-template), or interpreting engagement analytics (use /sales-proposal-analytics).
Build a Salla Communication App that delivers SMS, WhatsApp, or email on the merchant's behalf. Use when building channel apps, OTP/notification delivery, or the communication.*.send events. Salla deltas: no sub_category_id, zero default webhooks, channels MUST be declared via supported-features before publish (else 403), and each send event is an App Function trigger — prefer App Functions. App creation → salla-app-builder; credentials → salla-app-settings; handler code → salla-app-functions; token/OAuth → salla-app-auth.
Create, style, export, and validate publication-quality scientific and technical figures. xy is the preferred default (matplotlib.pyplot-compatible for easy migration); matplotlib/seaborn/plotly also supported. Use when the user asks for a "publication figure", "paper figure", "journal-ready plot", "scientific visualization", "SVG/PDF/TIFF export", "colorblind-safe palette", "multi-panel layout", "error bars / significance markers", or works with figure scripts that import matplotlib, seaborn, plotly, or xy.
Expert at securing web applications against OWASP Top 10 vulnerabilities. Covers authentication, authorization, input validation, XSS prevention, CSRF protection, secure headers, and security testing. Treats security as a first-class requirement, not an afterthought. Use when "security, OWASP, XSS, CSRF, SQL injection, authentication security, authorization, input validation, secure headers, vulnerability, penetration testing, security, owasp, authentication, authorization, xss, csrf, injection, headers" mentioned.
Generates sentence, text, and image embeddings locally with the Python sentence-transformers (SBERT) library, using pre-trained Hugging Face models such as all-MiniLM-L6-v2, all-mpnet-base-v2, and multilingual variants. Covers encoding, cosine similarity, semantic search, batch encoding, fine-tuning, and LangChain/LlamaIndex integration. Use when building embeddings for RAG, running semantic search or similarity scoring, clustering or classifying text, embedding multilingual text without an API, or fine-tuning an embedding model on domain data. For API-based or managed embeddings, use OpenAI or Cohere Embed instead.
Image SEO audit for a URL or domain. Pulls raw image inventory via Firecrawl, then audits alt-text quality, modern-format coverage (WebP / AVIF), responsive sizing (`srcset` / `sizes`), lazy-loading and LCP signals (`loading`, `fetchpriority`, `decoding`), CLS-safe dimensions, descriptive file names, and `ImageObject` JSON-LD. Optional PageSpeed Insights cross-reference for real byte-saving estimates. Produces a prioritised remediation list plus paste-ready picture-element markup and `ImageObject` schema. Distinct from `seo-technical-audit` (which surfaces audit-flagged image issues at the site level) and from `seo-schema` (which generates page-level JSON-LD but not image-specific markup). Use when the user asks for "image SEO", "image audit", "alt-text audit", "WebP coverage", "AVIF", "responsive images", "lazy loading", "CLS images", "image schema", "ImageObject", "image rich results", "licensable images", or "optimise images".
Master SEO orchestrator with 24 specialized sub-skills across 9 categories. Comprehensive SEO analysis for any website or business type. Performs full site audits, single-page deep analysis, technical SEO checks (crawlability, indexability, Core Web Vitals with INP), schema markup, content quality (E-E-A-T framework), image optimization, sitemap analysis, site architecture planning, AI search optimization (GEO for ChatGPT, Perplexity, AI Overviews), backlink analysis, keyword research, SERP tracking, and AI visibility monitoring. Industry detection for SaaS, e-commerce, local business, publishers, agencies. Triggers on: "SEO", "audit", "schema", "Core Web Vitals", "sitemap", "E-E-A-T", "AI Overviews", "GEO", "technical SEO", "content quality", "page speed", "structured data", "site architecture", "metadata", "AI SEO", "backlinks", "link building", "keywords", "keyword research", "SERP", "AI visibility", "local SEO", "GBP", "Google Business Profile", "Google Maps", "local pack", "NAP", "local citations", "Ask Maps".
Pull a domain's XML sitemap (and sitemap-of-sitemaps), then compare against the most recent SE Ranking website audit. Surfaces (a) sitemap entries the crawler couldn't find (orphans from the sitemap), (b) audit pages missing from the sitemap (probably an oversight), (c) sitemap entries that are now 404, (d) lastmod inconsistencies. Use when the user asks for "sitemap analysis", "check my sitemap", "sitemap vs audit", "missing pages", "orphan pages", or "sitemap health".
Use this skill to choose between host (Robolectric/JVM) and device (instrumentation) tests for Jetpack Compose, and to configure each correctly. Covers the `androidHostTest` (a.k.a. `src/test/`) vs `androidDeviceTest` (a.k.a. `src/androidTest/`) source set split, what each flavor can and cannot drive (RenderThread, screenshots, accessibility), the `@RunWith(AndroidJUnit4::class) @Config(minSdk = 23)` setup for Robolectric, and why `Thread.sleep` is forbidden everywhere except screenshot tests waiting on the RenderThread. Use when the user reports "tests pass locally but fail on CI", asks "Robolectric vs instrumentation", mentions screenshot tests, ripple animations, accessibility checks throwing on Robolectric, or "should this test live in test/ or androidTest/".
Settle a session by saving its work, recording what remains, and freeing proven-merged, unoccupied worktrees while leaving the caller and terminal layout open. Use when the user says "settle" or "end the session" about this session, or when another skill says to settle. When the user says to settle an effort, use /settle-effort instead.
Guide the user through integrating Hyperspell into their project. Installs the SDK, configures the API key, detects the project type, sets up memory ingestion (OAuth or direct), and integrates memory search. Use when a user wants to add Hyperspell to their codebase, set up memory search, or connect user accounts via OAuth.
Keep an eye on this PR. Review and resolve pull request comments and fix build failures autonomously. Use when asked to review PR feedback, address reviewer comments, fix CI failures, resolve PR threads, or handle PR maintenance tasks like "review PR comments", "fix the build", "address PR feedback", "clean up PR", or "resolve comments". Handles comment triage (resolve false positives, fix trivial issues, flag complex ones), build/lint/type errors, and e2e snapshot updates.
Turn talking-head footage into a finished reel, YouTube Short, or short advertisement with curiosity-led openings, earned payoffs, story-driven cuts, transcript-synced motion graphics, moving B-roll, captions, subtle music, and synchronized sound effects. Use for short-form editing; use edit-video for long-form videos and cut-silences for pause removal alone.
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.