Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
The software cost assessment dashboard is for management, technical, software, and general use when users want to estimate software project development costs; it helps generate an external web app entry point and a software cost assessment process within `https://soft.ai-skills.ai` based on input materials.
The architect, developer, and reviewer engineering subject-matter expert and base engineering layer for coding agents. Assigned by team-executor to any agent that writes, updates, or reviews code (the architect/developer/reviewer hand-off), or invoked explicitly, to hold the work to a strict engineering bar across the Three Lenses and Eight Standards. Applies equally to new code and to changes to existing code. Carries the 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 such as heroui, drizzle-orm, and temporal overlay on top of this one.
Use when running or explaining SpacetimeDB CLI commands and standalone configuration. Covers `spacetime init`, `build`, `publish`, `generate`, `call`, `sql`, `logs`, `describe`, `dev`, `server`, `start`, login/logout, and `config.toml`. Triggers on: spacetime CLI, spacetime publish, spacetime generate, spacetime sql, spacetime logs, spacetime server.
Reverse-engineer a functional specification (spec) from existing source code. Use when you need to write requirements documentation for legacy code, freeze existing behavior before a refactor or migration, or take over an undocumented codebase. The resulting spec structure follows GitHub Spec Kit conventions.
Develop features in an existing project within the current session with ponytail taste. Use when explicitly requested, or automatically for ordinary feature, plugin, extension, and cross-module work that needs project understanding and clarification before implementation. Survey the real flow, grill only unresolved decisions, then implement and verify here without plan or handoff documents. Prefer quick-do for clear, bounded changes; prefer plan-brief when long-horizon work needs planning and separate-session execution.
Create and edit visual diagrams with Syncfusion JavaScript Diagram (flowcharts, BPMN, swimlanes, UML, org charts, network topologies). Trigger for diagram rendering, node/connector modeling, layouts, data binding, palettes, interactive tools, exporting, and workflow visualization tasks.
Implements Syncfusion Javascript TreeGrid for hierarchical data with sorting, filtering, editing, exporting, paging, virtual scrolling, and advanced features. Supports configuration, CRUD, aggregates, templates, state persistence, and performance optimization in Javascript applications.
Implement hierarchical tree structures with Syncfusion JavaScript TreeView component for selection, editing, and drag-drop functionality. Use this skill when building tree navigation interfaces, displaying hierarchical data, implementing node selection and checkboxes, performing node manipulation (add/remove/update), and customizing tree templates. Covers data binding with local and remote data sources, DataManager integration, node events, API methods, and properties.
Build interactive diagrams using Syncfusion Vue Diagram, including flowcharts, BPMN workflows, UML diagrams, Entity Relationship (ER) diagrams, swimlanes, and organizational charts. Trigger when working with Vue diagram components such as nodes, connectors, shapes, ports, labels, layouts, symbol palettes, serialization/deserialization with unsaved changes detection, Mermaid syntax support, data binding, interactive editing, and exporting diagrams for visualization and process flows.
Implement the Syncfusion Vue Speech-to-Text component. Instructions for integrating voice input, real-time transcription, language configuration, programmatic control, event handling, UI customization, browser compatibility, and security considerations for microphone-enabled applications.
Implements Syncfusion Vue TreeGrid for hierarchical data with sorting, filtering, editing, exporting, paging, virtual scrolling, and advanced features. Supports configuration, CRUD, aggregates, templates, state persistence, and performance optimization in Vue applications.
Core Web Vitals discipline for agent-built pages: LCP, CLS, INP budgets, font loading that doesn't shift layout, images that don't bloat, CSS/JS that doesn't block. A designed page that loads like a template is half a page. Use when generating or auditing any web page or component. Stack on the design-taste core skill.
A skill that runs a test-driven development (TDD) workflow. When to use: (1) starting a new feature, (2) fixing a bug, (3) before refactoring, (4) when asked to "write the tests first", (5) when the implementation needs to emphasize quality. Example triggers: "implement with TDD", "test-driven", "write the tests first", "RED-GREEN-REFACTOR", "write tests for UserService".
Canon TDD for humans and AI agents. Use for production code changes by writing tests first, proving RED, implementing minimal GREEN, and refactoring safely. 2026 edition adds TDP, flakiness gate, ralph-loop integration, memory-search in Step 0, PBT as Step 5.5, mutation testing gate in Step 4, and CJS LSP warning.
Use this skill as the main entry point whenever the user wants to build, plan, or evolve an interactive teaching website / course microsite / workshop landing page — from a blank slate, from existing course materials, or any state in between. Triggers on broad phrases like "做課程網站", "做教學網頁", "做工作坊網站", "把講義變網頁", "course microsite", "workshop site", "interactive lesson page", "multi-day curriculum website", "做一套課程". This skill is the router for the whole teaching-site pipeline (outline → content → SPA → interactions → visuals → corporate / ebook) and dispatches to the 10 specialised sub-skills as needed. Prefer this when the user's request is broad or unclear about which stage they're at — sub-skills (e.g. `course-ebook-publishing`) are still triggerable directly for stage-specific requests.
Default FMC tech stack for geo-heavy React SPAs: Bun/Vite, React 19, TanStack, maps, styling, TypeScript editor/CLI alignment, tsconfig templates, browserslist client targets, Claude Code MCP (Postgres, agent-browser), and when to pick sibling skills. Use when scaffolding a new app, evaluating libraries, setting up Bun install/global store or Knip, changing supported browsers or compat lint, setting up Claude Code MCP, or making stack/architecture decisions on existing apps.
Verify technical nonfiction manuscripts for runnable accuracy, including commands, configuration, code snippets, links, version drift, screenshots, prerequisites, security warnings, expected outputs, and reproducibility. Use when auditing self-hosting, DevOps, programming, infrastructure, data, security, or software tutorial drafts before beta reading, publication, or release.
tmux and tmuxp session configuration, management, and troubleshooting. Use when creating, editing, debugging, or optimizing tmuxp YAML configs, designing tmux workspace layouts, fixing tmux session errors, managing multi-environment terminal setups, or working with tmux panes, windows, and sessions. Also use when the user mentions tmuxp, .tmuxp, tmux layouts, session_name, or terminal workspace organization.
Write AST-based code search and rewrite rules using ast-grep YAML. Create linting rules, code modernizations, and API migrations with auto-fix. Use when the user mentions ast-grep, tree-sitter patterns, code search rules, lint rules with YAML, AST matching, or code refactoring patterns.
Plan and execute language-to-language server or application migrations with behavior parity. Use when porting modules, services, APIs, or runtimes between programming languages; generating source-runtime oracles and fixtures; generating migrated parity tests; detecting runtime, standard-library, serialization, numeric, encoding, time, regex, or protocol differences; building temporary compatibility layers; accumulating migration knowledge; benchmarking; shadow testing; canarying; or planning cutover and rollback.
Corrects the wrong defaults a model has for tRPC v11 (verified against 11.18.0). Use when code imports initTRPC, createTRPCContext, createTRPCOptionsProxy, createTRPCReact, httpBatchLink, httpSubscriptionLink, fetchRequestHandler, or TRPCError, or when building routers, procedures, middleware, links, or RSC prefetching. Covers the v10 to v11 drift that makes stale code fail — the React client that flipped to @trpc/tanstack-react-query, transformers moving into links, renamed type exports, observable subscriptions replaced by async generators over SSE — plus the defaults that are unsafe rather than merely stale — uncapped batching, CDN cache headers that serve one user's data to another, stack traces shipped from edge runtimes, and middleware that runs before input validation. NOT for TanStack Query semantics generally (use tanstack-query), Zod schema authoring (use zod), or Next.js App Router routing (use nextjs).
This skill should be used when the user asks to test, debug, snapshot, validate, reproduce, or automate terminal UIs, curses apps, raw ANSI output, PTY-driven interactions, virtual terminal emulators, ConPTY behavior, resize tests, keyboard/mouse/paste tests, or flaky terminal snapshots. PROACTIVELY activate for: TUI testing, snapshot tests, golden files, pty integration tests, pseudo-terminal automation, ConPTY, Pexpect, node-pty, vt emulators, Textual Pilot, Ratatui snapshots, Bubble Tea tests, terminal debug logs, and CI failures. Provides: layered test strategy, deterministic snapshot rules, PTY/ConPTY patterns, debugging playbooks, and flake prevention.
Controls the Unity Editor and projects from the command line, driving a running Editor to edit scenes and assets or run C#. Use when asked to install or manage Editors, licenses, or projects, set up version control, build, test, configure the Unity MCP server, or run any unity command.
OpenAPI documentation skill for Rust APIs using utoipa with Axum framework. Use when building REST APIs with automatic OpenAPI spec generation and Scalar UI. Covers: (1) ToSchema derive for request/response types, (2) #[utoipa::path] for endpoint documentation, (3) OpenApi derive for combining specs, (4) Security schemes (JWT, API keys), (5) IntoParams for query/path params, (6) Scalar UI integration, (7) Response and error handling patterns. Triggers: utoipa, openapi, scalar, axum api, ToSchema, IntoParams, rust api docs.
Vapor UI design system component and icon guide, UI mockup generator, and Figma design converter. Provides component catalog, icon lookup, usage patterns, props documentation, and converts Figma designs to production-ready vapor-ui code. Use when user asks "vapor-ui components", "vapor-ui icons", "아이콘 찾기", "vapor-ui 사용법", "vapor-ui를 사용해서 시안 구현", "convert figma", "figma to code", "implement design from figma", provides a Figma URL, or mentions specific components like "Button", "Input", "Modal".
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture.
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
Upgrade the very_good_analysis lint package to a new version in any Dart or Flutter package, handling the pubspec.yaml version bump, the lint fixes the new rules force, and the PR. Trigger on phrases like "bump very_good_analysis to 10.0.0", "upgrade very_good_analysis", "update our lint package", "we're due for a lint upgrade", "take very_good_analysis to the latest", or a `dart pub get` conflict reported after a very_good_analysis bump. Use it even when the user only describes the package instead of pointing at it, because the decisions it governs are scope calls that do not need the files on disk: which constraint to write, which warnings to fix, and what stays out of the PR. The trigger is a very_good_analysis version change. A conflict surfaced by a Dart or Flutter SDK bump belongs to dart-flutter-sdk- upgrade instead, even when very_good_analysis is the package blocking resolution.
Develop, maintain, refactor, and review the vue3-element-admin frontend, including Vue pages, API modules, stores, routes, menus, permissions, caching, i18n, and project components. Use only in the vue3-element-admin repository or when the user explicitly asks to follow its conventions; do not apply these project-specific patterns to unrelated Vue applications.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components—not for simple single-file HTML/JSX artifacts.
Curated Swift package ecosystem for WendyOS and Linux. Use when developers mention: (1) Swift packages for Linux or ARM64/AMD64, (2) choosing a Swift library, (3) Swift Package Index, (4) swiftpackageindex.com, (5) what Swift library to use, (6) Swift on WendyOS dependencies, (7) edge computing Swift libraries.
Control WinDbg via HTTP REST API for three scenarios - dump analysis (process crash dumps, kernel crash dumps / BSOD), live kernel debugging (KDNET, local kernel, VM kernel), and user-mode process debugging (attach to process, application crash). Use when the user mentions WinDbg, crash dump, .dmp file, BSOD, bugcheck, kernel debug, process debug, !analyze, breakpoints, or says the windbgskill plugin is running on a port number.
Port a WordPress theme's design and template behavior to an EmDash-powered Astro site. Use for theme migrations, design matching, PHP-template conversion, and CMS wiring. Do not use for WordPress plugin behavior that does not affect the site theme.
WordPress REST API review and development guidance. Use when reviewing custom REST routes, permission_callback logic, schema design, WP_REST_Request handling, response structure, versioning, controller classes, nonce or auth usage, or when user mentions "REST API review", "register_rest_route", "permission_callback", "WP_REST_Request", "REST endpoint", "custom API", "API schema", "REST controller", "headless WordPress", or "API auth". Detects route registration issues, authorization mistakes, schema drift, input validation gaps, and response design problems in WordPress REST API code.
Send images, audio, video, or documents into an AG2 `Agent` alongside text. Pass `ImageInput`, `AudioInput`, `VideoInput`, or `DocumentInput` as positional args to `agent.ask(...)`. Use when the user wants the agent to process non-text input — describe a photo, transcribe audio, summarise a PDF, analyse a video. Covers per-provider support matrix, the four ways to source data (URL / path / bytes / file_id), Gemini-specific YouTube + media-resolution + clipping, OpenAI image-detail, Anthropic prompt-caching on attachments, and `FilesAPI` for upload lifecycle.
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.