Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use when working with sunpeak, or when the user asks to "build an MCP App", "build a ChatGPT App", "add a UI to an MCP tool", "create an interactive resource for Claude Connector or ChatGPT", "build a React UI for an MCP server", or needs guidance on MCP App resources, tool-to-UI data flow, simulation files, host context, platform-specific ChatGPT/Claude features, or production builds. For testing (e2e, visual regression, live tests, evals), see the test-mcp-server skill.
Create symbolic links (symlinks) on Windows, macOS, and Linux. Automatically selects the correct command for the current operating system to create a symlink to a directory or file. Use this skill when users need to create a symlink or share files/directories across different locations.
Turn a CodeSpring feature's notes + PRDs into a numbered, prioritized Kanban task list linked to that feature. Reads the feature, its sub-features, its PRDs, and any features that link to it, then writes ordered tasks that are safe to build in parallel — each with what/why/what-it-touches/what-not-to-touch/dependencies. Use when the user has a feature planned and wants a build plan. Triggers, "create tasks", "make a task list", "break this feature into tasks", "generate a build plan", "turn my PRD into tasks", "what do I build first".
The CodeSpring entry point. Connects the agent to the user's CodeSpring account, reports where the project actually is (map? notes? PRDs? tasks?), and names the single next step — audit an app that isn't doing its job, import one that is, plan a new one from scratch, or carry on from wherever the project already got to. Routes on two questions: is there code, and does it do the job (five specific checks, not "do you trust it"). Safe to run at any point, not just the beginning. Use when the user is unsure where to begin or what to do next, or right after installing the CodeSpring skills. Triggers, "get started with CodeSpring", "set up CodeSpring", "connect CodeSpring", "I just installed the CodeSpring skills", "what can I do with CodeSpring", "where do I start", "what should I do next".
Re-sync CodeSpring with the real code after building. Independently checks whether the features, notes, and PRDs in CodeSpring still match what the code actually does now (features drift from their plan once built), then updates CodeSpring to match. Read-only on the codebase — it only reads code/git and writes to CodeSpring. Use after a feature is finished, or periodically, to keep the map from going stale. Triggers, "resync my codebase", "is CodeSpring up to date", "check for stale PRDs", "update CodeSpring from the code", "my plan drifted from the code".
Edit dagger.gen.go output, Go templates (object.go.tmpl, defs.go.tmpl), invoke() dispatch, SDK interfaces (CodeGenerator, ClientGenerator), `dagger develop`, `dagger client install`. Keywords: codegen, SDK, bindings, templates, internal/dagger, dag.*, ModuleMainSrc
Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents. Stores entities (modules, functions), their dependencies (imports), public API (shared/exports), and reasons for every connection. Use when: (1) project has a .dsp/ directory, (2) user asks to set up DSP or bootstrap project structure, (3) creating/modifying/deleting code files in a DSP-tracked project, (4) navigating project structure, understanding dependencies, or finding modules, (5) user mentions DSP, dsp-cli, .dsp, or structure mapping.
Load PROACTIVELY when task involves database design, schemas, or data access. Use when user says "set up the database", "create a schema", "add a migration", "write a query", or "set up Prisma". Covers schema design and normalization, ORM setup (Prisma, Drizzle), migration workflows, connection pooling, query optimization, indexing strategies, seeding, and transaction patterns for PostgreSQL, MySQL, SQLite, and MongoDB.
DDD4J MyBatis-Plus persistence layer conventions skill. Covers the ActiveRecord pattern (Entity must extend BaseEntity→Model<T>), @TableLogic logical deletion, automatic audit field population (createBy/createTime/updateBy/updateTime), the @Param("model") XML parameter convention, PaginationEntity pagination wrapper (15 rows/page/Oracle-style offset), the type handler system (BooleanEnum/dual JSON/ListSetArray splitting), and BaseMapper built-in methods such as getPagedList/setStatus/getCountBy*. Use this skill when users define Entity/Repository, write Mapper XML, use paginated queries, or configure type handlers in a DDD4J project. Use together with the ddd4j-core skill.
Use when debugging any non-trivial bug — wrong output, crash, flaky test, performance regression, or "it works locally but not in CI." Forces a scientific-method loop (Observe → Hypothesize → Experiment → Conclude) so the agent stops guessing and starts reasoning. Prevents the #1 AI debugging failure mode — bulldozing through a wrong idea instead of falsifying it.
Complete 9-phase development pipeline guide — from schema to deployment. Pipeline phases (1-schema → 9-deployment) are orthogonal to PDCA's 9-phase per-feature cycle and Sprint's 8-phase container; each pipeline phase may host PDCA cycles for individual features, and multi-feature pipeline initiatives can be wrapped in /sprint (v2.1.13). Triggers: development pipeline, where to start, phase
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sections, tables of contents, and cross-references. Use when the user asks for a docs canvas, documentation overview, architecture walkthrough, API reference page, or wants to render structured documentation as an interactive canvas.
Browse and install components from the Elements registry (tryelements.dev). Use when user asks about available components, wants to explore providers, says "elements", "component library", "what components", "install from registry", "tryelements", or needs to find the right component category.
This skill MUST be used for architecture decisions, module boundaries, turning plans or specs into tickets, or explicit UI/design reviews. SHOULD be used when implementation requires unresolved architectural choices or the user is unsure how to divide the work. MUST NOT expand an already specified implementation into a new planning exercise. Triggers on: 技術方案, 架構設計, 怎麼切模組, 拆任務, 切票, 排開發順序, 技術規劃, design review, UI review, AI slop scan.
Generate the `СведенияОВнешнейОбработке` function in the object module of a processing — the description for connecting via the БСП «Additional reports and processings» subsystem. Use when you need to make a processing compatible with БСП and connectable via «Additional reports and processings»
Comprehensive ESLint agent for JavaScript/TypeScript code quality. Use when setting up ESLint, configuring linting rules, analyzing code for issues, fixing violations, or integrating ESLint into development workflows. Triggers on requests involving code quality, linting, static analysis, or ESLint configuration for JavaScript, TypeScript, React, or Node.js projects.
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines
AI-simulated event storming workshop with multi-persona support. Use when discovering domain events, commands, actors, and bounded contexts. Supports three modes - full-simulation (5 persona agents debate), quick (single-pass analysis), and guided (interactive with user). Orchestrates persona agents and synthesizes results.
Generate technical documentation for Vue components under core/ui2-components and sync it to the Feishu knowledge base and local markdown files. Supports creating and updating component docs, including API information such as Props, Slots, Events, and Methods. Feishu uses the lark-table format, while local files use standard markdown. Triggered when the user mentions "component docs", "ui2 docs", "sync Feishu", or a specific component name.
Feishu campaign plan requirement analysis — extract gameplay descriptions and numeric calculations from Feishu documents, summarize them grouped at section granularity, and output a structured requirement document for code generation. Triggered when the user mentions "analyze requirements", "requirement document", "Feishu plan", or "analyze plan".
Post-verification feature-branch closeout menu: after verify (and archive when applicable), and after optional delivery-discipline when code delivery is needed, present PR / merge / keep / continue options; optional worktree cleanup; selecting merge MUST load merge-discipline Parts A→B→C→R→D; keep/continue MUST NOT trigger merge gates. Open/update PR delegates to delivery-discipline. Triggers — 「分支收尾」「feature 收尾菜单」「合入或保留分支」「branch closeout」 / feature branch closeout, post-verify branch menu. Do NOT use as a name alias for finishing-a-development-branch.
Download, install, and launch Fiddler Everywhere from scratch, then configure MCP for AI agent tools. Use this skill when the user does not have Fiddler installed, says "download Fiddler", "install Fiddler Everywhere", "get started with Fiddler", "first time Fiddler setup", "set up Fiddler from scratch", or needs a complete onboarding from zero to a working Fiddler MCP connection.
Audit and fix HTML metadata including page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD structured data, and robots directives. Use when adding SEO metadata, fixing social share previews, reviewing Open Graph tags, setting up canonical URLs, or shipping new pages that need correct meta tags.
Routing patterns for Flutter projects — declaring routes with `go_router`, managing constants in `RoutePaths`, implementing bottom navigation with `StatefulShellRoute`, handling path parameters (`:recipeId`), using `context.go`/`context.push`. Triggers on phrases such as "add route", "go_router", "screen navigation", "navigation", "GoRoute", "StatefulShellRoute", "pathParameters", "deep link".
Frontend engineering standards — component architecture, state, async, forms, accessibility, performance and TypeScript discipline. Detects the project's framework and loads only the matching guidance. TRIGGER — load BEFORE writing or editing frontend code, not after: any .tsx, .jsx, .vue, .svelte, or component/hook file is being created or edited; the prompt names a component, hook, prop, state, form, modal, route, page, React, Next, Solid, SolidStart, solid-js, signal, useState, useEffect, createSignal, createStore, createResource, createAsync, <For>, <Show>, store, context, a11y, or web vitals. Trigger on plain feature requests in a frontend repo — "add a button", "wire up this form", "make this load faster", "fix this rerender" — the user will not say "best practices"; the component file is the trigger. Load it even when another skill (tdd, impeccable, simplify) is already active. SKIP only for backend-only work with no UI file touched.
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.