Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Detect project linting and validation tools, build an execution pipeline, run all tools to zero errors, and fix issues using an atomic fix protocol. Auto-detects Makefile targets, package.json scripts, Go tools, Python tools, and other common linters. Use when fixing linting errors, running validation pipelines, or ensuring code quality before committing.
Symfony UX LiveComponent for reactive server-rendered UI -- components that re-render via AJAX on user interaction, zero JavaScript required. Use when building live search, real-time filtering, dynamic forms, inline validation, dependent selects, auto-save, polling, deferred/lazy rendering, or any UI that updates itself based on user input. Code triggers: AsLiveComponent, LiveProp, LiveAction, data-model, data-loading, data-live-action-url, ComponentWithFormTrait, LiveListener, emit, defer, lazy, polling. Also trigger when the user asks "how to build a search that filters as I type", "how to validate a form in real-time", "how to make a reactive component in PHP", "how to build dependent selects", "how to defer component rendering", "how to communicate between components via emit", "how to bind a form to a LiveComponent". Do NOT trigger for static reusable UI without reactivity (use twig-component), pure client-side JS behavior (use stimulus), or page-level navigation (use turbo).
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Use when the user says 'migrate beaver builder to bricks', 'convert bb to bricks', or 'replace beaver builder with bricks'. Reads the Beaver Builder flat node map, maps each module to its Bricks element, and creates draft duplicates for review.
Use when the user says 'migrate divi to breakdance', 'convert divi to breakdance', or 'rebuild divi pages in breakdance'. Parses Divi shortcodes, maps modules to Breakdance elements, and creates draft duplicates for review.
Use when the user says 'migrate wpbakery to bricks', 'convert visual composer to bricks', or wants to modernize a WPBakery site onto Bricks. Parses WPBakery shortcodes, maps elements to their Bricks equivalents, and creates draft duplicates for review.
Motoko actor state migration and schema evolution using the mops-managed migration chain (a migrations/ directory of timestamped files). Use when upgrading canisters, changing actor field types, renaming or adding stable fields, deciding implicit vs explicit migration, or writing migration files — including one-shot changes. For unexplained compatibility diagnostics, frozen migration files, a non-empty first OldActor, projects converted from legacy persistence, or requests to remove the chain or revert to inline (with migration = ...), use troubleshooting-motoko-migrations.
Build and query managed search indexes (Stores) using the Mixedbread Python and TypeScript SDKs. Use when creating knowledge bases, uploading documents, performing semantic or vector search, asking questions over documents, using agentic multi-step retrieval, combining store search with web results, filtering by metadata, reranking, or discovering metadata facets.
Automatically generates HarmonyOS code scaffolding from design documents, including IDL interface definitions, directory structure, header files, source file templates, build configurations, and more. Before generating, it analyzes existing OpenHarmony code to learn the current code style and architecture conventions. Use when the user requests: (1) generate code scaffolding, (2) create IDL interfaces, (3) generate BUILD.gn configurations, (4) create service code, (5) initialize project structure, (6) reference existing code style. Keywords: code generation, IDL, BUILD.gn, bundle.json, SA profile, OpenHarmony code style, 代码生成, 接口定义, 构建配置, OH代码风格
Eight-stage PDCA problem-solving workflow that persists analysis, proposal, design review, plan, execution, and verification into OpenSpec artifacts (openspec/changes/<name>/, archived into openspec/specs/) instead of leaving them only in chat context. Use for feature work, bug fixes, refactors, and complex engineering tasks that need long-term behavioral-contract traceability, team review, or auditability. Do NOT use for a quick one-off edit with no traceability need — use solve-workflow instead. Triggers：「opsx解决」「OpenSpec解决」「规范化解决」「创建OpenSpec变更」「创建opsx变更」「用OpenSpec分析」「用OpenSpec修复」「opsx自动解决」「OpenSpec自动解决」「opsx-solve」「opsx-solve-workflow」；「ai-proxy 模式」「AI 代理模式」「切换 ai-proxy」 / opsx solve, OpenSpec solve workflow, create an OpenSpec change, ai-proxy mode, switch to ai-proxy.
Structured planning workflow for any coding task. Use at the start of every new feature, bug fix, refactor, or implementation request. Analyzes the project, asks up to 5 clarifying questions, creates a TODO.md, gets user approval, then executes task by task. Never writes code before a plan is approved.
Prepares a reproducibility artifact (code/data) for submission and badging. Use when a researcher says "artifact evaluation", "artifact appendix", "reproducibility", "badge", "Artifacts Available/Evaluated/Functional/Reusable", "Results Reproduced/Replicated", "ACM badging", "USENIX/OSDI/SOSP AE", "SIGMOD ARI", "NeurIPS code/checklist", "ACL repro checklist", "Zenodo DOI", "Software Heritage", "anonymize my code/repo", or "package my code". Builds the artifact README + appendix, the dependency/run instructions, an anonymized repo for double-blind, and archival-DOI (Zenodo version vs concept) / Software Heritage SWHID guidance; resolves the ACM badge taxonomy and the Reproduced/Replicated era swap; and lints the artifact directory against the ML Code Completeness checklist with bundled stdlib-only scripts. Outputs an artifact-readiness checklist + packaging plan. Re-verifies the venue current artifact rules live. Advisory only; never submits.
Programmatic Power BI development with PBIR, PBIP, TMDL, TOM, and fabric-cicd. PROACTIVELY activate for: (1) creating Power BI reports programmatically (PBIR enhanced report format), (2) PBIR vs PBIR-Legacy selection (2026 default), (3) PBIP developer mode and Power BI project files, (4) Tabular Object Model (TOM) / .NET SDK scripting, (5) Tabular Editor scripting (C# scripts, advanced scripting), (6) pbi-tools workflows, (7) fabric-cicd Python deployments (FabricWorkspace, publish_all_items), (8) Fabric CLI (fab deploy), (9) Semantic Link / sempy / semantic-link-labs, (10) generating PBIX programmatically, (11) parameter.yml for environment-specific deployments, (12) ALM Toolkit. Provides: PBIR/PBIP project templates, fabric-cicd deploy.py, Tabular Editor scripting recipes, parameter.yml patterns, and end-to-end programmatic workflows.
Ensures HeyEddi projects have the right engineering stack: Vue (Vite/Vitest), FastAPI backend, or Firebase tooling. Audits gaps, scaffolds as needed, installs deps, runs tests, documents local dev servers. Use when the repo is thin or before design/feature work on any HeyEddi app.
Write and run Python (PyGhidra) code inside the Ghidra session that ReVa's MCP server is already attached to, using the five ReVa scripting tools — `run-script`, `list-scripts`, `read-script`, `write-script`, `edit-script`. Use this whenever the user asks to execute Python against the current program, reach for the Ghidra Flat API directly, write a custom analysis pass, automate something the other ReVa tools don't expose, or persist a `.py` script in Ghidra's scripts directory. Also use when an existing ReVa MCP tool can't do what's needed and the right answer is "drop into PyGhidra for one call." Do NOT use this skill for plain ReVa tool calls that already have a dedicated MCP tool (use that tool instead); do NOT use it to build standalone Python programs that run pyghidra in their own process (the run-script tool runs *inside* the ReVa-hosted Ghidra).
Use when planning or auditing a Quest or Horizon OS product from platform choice to operation, as a stage, evidence and owner map. NOT for one engine bug, profiling (quest-perf), upload (quest-store) or delivery (task-pipeline). Opt out: no xr, без xr. Triggers - "Quest roadmap" / "план для Quest".
React and Next.js performance optimization from Vercel Engineering. Use when building React components, optimizing performance, eliminating waterfalls, reducing bundle size, reviewing code for performance issues, or implementing server/client-side optimizations.
Comprehensive React and Next.js performance optimization guide. Covers waterfall elimination, bundle size reduction, server-side optimization, re-render prevention, and rendering performance. Use when building, reviewing, or optimizing React/Next.js applications for speed.
Structure, tone, and content conventions for writing effective project README files, covering hooks, quick starts, feature presentation, badges, and common documentation sections. Use when writing a new README, rewriting an existing one, or reviewing README quality for a repository, library, or CLI tool.
Clean research code for public release while preserving reported results. Uses release_audit.py to separate safe mechanical cleanup from ask-first behavior risks and identity leaks. Use for release-ready repos, dead experiment branches, config extraction, documented entrypoints, and double-blind code cleanup.
Enable automatic disposal of Riverpod providers when they have no listeners; keepAlive, onDispose, invalidate, ref.keepAlive. Use when preventing memory leaks, caching only while used, or cleaning up resources when a provider is no longer needed. Use this skill when the user asks about auto-dispose, keepAlive, or when to dispose Riverpod state.
Salla OAuth 2.0 and merchant token management — the Salla delta on standard OAuth: Easy Mode (tokens via the app.store.authorize webhook, no callback — published apps) vs Custom Mode (authorization-code, dev/testing only), the offline_access scope, single-use refresh tokens needing a per-merchant refresh lock, and the User Info endpoint. Use before writing any Salla token-handling code. Lifecycle events → salla-app-lifecycle; webhook verification → salla-webhooks; API usage → salla-api-core.
Use when authoring or modifying a Datex Studio selector (configurationTypeId=7, *-selector.json suffix) on a branch — datasource-backed dropdown / autocomplete control. Owns the hard component-variant rule (backing must be a -datasource.json, never a -footprintDatasource.json), the sort-by-display-label rule, and the three-piece full-text-search contract (getList filter + getByKeys keyset + full-text param). Triggers: "create a dropdown", "create an xxx_dd selector", "autocomplete for entity X", "enum dropdown", "dropdown is empty", "full-text search doesn't filter the dropdown", "selector backing-datasource is wrong variant".
Technical SEO audit across 9 categories: crawlability, indexability, security, URL structure, mobile, Core Web Vitals, structured data, JavaScript rendering, and IndexNow protocol. Use when user says "technical SEO", "crawl issues", "robots.txt", "Core Web Vitals", "site speed", or "security headers".
Applies the user's engineering standards during substantial technical work: preserve scope, use current evidence, delegate independent parts, and complete authorized outcomes. Use during substantial implementation, debugging, refactoring, or multi-part delivery work.
Expert-level SolidJS and SolidStart development skill with 20+ years senior/lead engineer mindset. Comprehensive guidance for building production-ready, scalable web applications with fine-grained reactivity. Use when Claude needs to: (1) Create new SolidJS/SolidStart projects, (2) Implement TanStack Query/Router/Table/Form integration, (3) Build reactive components with signals/stores/resources, (4) Handle SSR/SSG/streaming with SolidStart, (5) Implement authentication and API routes, (6) Optimize bundle size and performance, (7) Debug reactivity issues and memory leaks, (8) Structure large-scale applications, (9) Implement type-safe patterns with TypeScript, (10) Handle error boundaries and suspense, (11) Build accessible UI components, (12) Deploy to Vercel/Netlify/Cloudflare. Triggers: "solid", "solidjs", "solidstart", "createSignal", "createStore", "createResource", "tanstack solid", "vinxi", "fine-grained reactivity".
Use when authoring or modifying a Datex Studio storage component (configurationTypeId=17, *-storage.json suffix) on a branch — cloud-persisted Mongo storage accessed via $db at function-tier. Owns the storage-vs-Footprint entity decision, column descriptor shape, the `required: true` read-then-patch trap (additive-only-after-shipping), additive evolution rules, and impact analysis before schema changes. Triggers: "create a storage", "add a column to xxx_storage", "options/config table", "rule table", "daily snapshot capture", "$db.update validation error after adding a required column", deciding between storage and Footprint entity.
Design, audit, and evolve physical source and package structures that expose real architectural boundaries while keeping related behavior together. Use when creating or reviewing repository trees, deciding where files or packages belong, reducing flat folders, organizing by feature, route, screen, use case, bounded context, workflow or endpoint, structuring frontend state/data/UI ownership and design systems, making hexagonal inside/outside boundaries visible, locating ports, adapters and composition roots, structuring BFF routes, planning folder migrations, or enforcing package and import direction. For one module's logical responsibility, deepening, splitting, or caller contract use codebase-design; for repository-wide architecture investment discovery use improve-codebase-architecture. A physical flattening alone is not a reduce-system-complexity result.
Automated retrospectives — captures learnings at EPIC completion and on manual invocation. EPIC-scoped retros embed a Retrospective section in the EPIC artifact. Cross-epic and time-based retros produce standalone retro docs. Triggers on: 'retro', 'retrospective', 'post-mortem', 'lessons learned', 'debrief', 'what worked', 'what didn't work', 'what did we learn', 'reflect', or automatically after EPIC terminal transitions.
Use this skill for JavaScript apps needing Excel-like UI using the Syncfusion Spreadsheet Component. Trigger for creating, viewing, editing Excel (.xlsx, .xls, .xlsb) and CSV files; embedding spreadsheet editors; data binding from APIs/JSON; using formulas, charts, validation, filtering, or conditional formatting. Also trigger when users reference spreadsheet files ("open xlsx", "load Excel file", "add Syncfusion spreadsheet", "bind data to spreadsheet"). Do NOT trigger for standalone file processing without UI components.
Comprehensive guide for implementing Syncfusion Essential Studio Windows Forms (WinForms) controls in desktop applications. Use this skill when working with Syncfusion WinForms components or Essential Studio WinForms. Covers WinForms installation, localization, high DPI support, and .NET Core compatibility. Helps with adding controls, registering license keys, and troubleshooting WinForms component issues.
Implements work already planned—a plan.md from tlc-plan or a small ticket—by freezing it into checks with proofs, building, and proving every check with a script and an independent Verifier before declaring done. Use when the user says “implement this plan”, “build this ticket”, “implement this spec”, “write the checks”, “verify work”, or “tlc-implement”. Do NOT use when nobody has decided what to build, or to plan a feature that needs one (that is tlc-plan).
Turns a request, ticket, PRD, design or thread into one plan a human approves and a builder can act on without the conversation: asks every gray area until no product decision is left to the builder, then writes the problem, EARS criteria with concrete values, the path and the data it touches (drawn in mermaid), the interface, and only the decisions that are hard to reverse. Captures that come with the request bind. Use when the user says “plan this”, “plan feature”, “specify feature”, “write the plan”, “cut this PRD into tasks”, or “tlc-plan”. Do NOT use to implement (that is tlc-implement), for a standalone design document, or when nobody has decided what to build.
Dense vector embeddings, semantic search, RAG pipelines, and reranking via Together AI. Generate embeddings with open-source models and rerank results behind dedicated endpoints. Reach for it whenever the user needs vector representations or retrieval quality improvements rather than direct text generation.
Translate a multilingual site with AI. Covers Rosey locale JSON files (untranslated + stale entries) and per-locale content directories (MDX/MD with frontmatter: split-by-directory collections, or a Hugo site's content_fr/). Use when the user wants to translate locale files, fill in missing translations, update stale translations, bulk-translate a locale, or translate per-locale content directories (blog_fr/, content_fr/).
Use when authoring or modifying Datex Studio type definitions (configurationTypeId=22, *-customType.json suffix) on a branch — both interfaces (i_<name>) and enums (e_<name>) live in this single component type. Owns the interface vs enum decision, custom-type self-reference prohibition, UI-component enum FQN constraint (vars/inParams/outParams cannot use FQN to reference custom enums — declare as primitive instead), and the "tightening a previously-loose type ripples to consumers" impact rule. Triggers: "create an interface", "create an enum", "define a shared type", "add a property to i_xxx", "add a value to e_xxx", authoring types for flow inParams/outParams/objectTypeDef.
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.