Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Creates or reconciles GitHub child task issues or Jira subtasks from an approved Phase 4 task plan, then updates docs/<KEY>-tasks.md with validated remote linkage. Use after the task plan has been clarified and the user has approved the exact platform writes plus scoped plan-file update. Does not plan tasks, implement code, commit changes, or mutate unrelated tracker state.
Design and audit data imports, customer migrations, bulk uploads, CSV/schema mapping, backfills, migration wizards, dry runs, validation, idempotency, reconciliation, rollback, progress visibility, and support handoffs. Use when moving product data between systems, onboarding customers from competitors, importing files, or migrating accounts without data loss.
Use when designing or critiquing aggregate boundaries — phrases like "aggregate", "aggregate root", "should these be one entity or two", "consistency boundary", "transactional consistency", "this aggregate is huge", "should I reference by ID or by object". Defines aggregates as transactional consistency boundaries and the rules for entity references within and across them
Use when identifying DDD anti-patterns and smells in code or design — phrases like "anemic domain model", "primitive obsession", "leaky repository", "smart UI", "transaction script", "god aggregate", "big ball of mud". Catalogs the common DDD anti-patterns with symptoms, why each is wrong, and the pattern skill that explains the fix
Use when mapping relationships between bounded contexts — phrases like "context map", "how do these two services talk", "should we use an anticorruption layer", "shared kernel vs separate ways", "upstream/downstream", "what integration pattern fits here". Catalogs the seven relationship patterns (Shared Kernel, Customer-Supplier, Conformist, Anticorruption Layer, Open Host Service, Published Language, Separate Ways) and the signals that pick one.
Use when the model is "working but feels off" and the user wants to deepen it — phrases like "supple design", "refactor toward deeper insight", "implicit concept", "the model isn't quite right yet", "what would a better model look like", "intention-revealing interfaces", "side-effect-free functions", "assertions in the domain", "conceptual contours". Covers Evans's Part III techniques for evolving a model past its first draft.
Use when the user wants to design a new domain model from scratch — phrases like "help me model X", "what's the bounded context for Y", "design a domain for this feature", "we need a domain model". Walks the user through ubiquitous language, bounded context, aggregate identification, and then routes to the relevant pattern skills. Do NOT use for code generation (route to ddd-implement) or refactoring existing code (route to ddd-refactor).
Use when modeling significant domain occurrences — phrases like "domain event", "OrderPlaced", "PaymentSettled", "something the business cares happened", "decouple these two aggregates", "eventual consistency across aggregates". Defines domain events, their naming (past tense, business-meaningful), and how they coordinate work across aggregates without violating aggregate boundaries
Use when behavior does not naturally belong to a single entity or value object—phrases like “domain service”, “this logic spans multiple aggregates”, “where does this go”, “the entity is starting to know too much”, “we need a calculator/coordinator that isn't a thing”. Defines when to introduce a stateless domain service instead of forcing behavior onto an entity. Distinguishes domain services from application and infrastructure services.
Use when creation of an aggregate or complex value object requires non-trivial work — phrases like "factory", "the constructor is doing too much", "construction has business meaning", "how do I create this aggregate", "constructor with twelve parameters". Defines when to introduce a factory and when a constructor or static creation method suffices
Use when the user wants concrete code that realizes a DDD pattern — phrases like "scaffold an entity for X", "write the Aggregate for Y", "give me the repository interface", "implement this value object". Drives the conversation through naming + invariants and then delegates code generation to a language adapter skill (e.g., ddd-kotlin-idioms for Kotlin). Do NOT use for refactoring (route to ddd-refactor), review (route to ddd-review), or design from scratch (route to ddd-design)
Use when designing how aggregates are persisted and retrieved—phrases like “repository”, “how should I load this aggregate”, “JPA repository vs DDD repository”, “leaky repository”, “finder methods”, “the repository is doing too much”. Defines a repository as the abstraction that gives the illusion of an in-memory collection of aggregates. One repository per aggregate root.
Use when the user asks for a PR-style code review for DDD smells—phrases like “is this DDD-clean”, “review this for domain modeling issues”, “what's wrong with this aggregate”, “audit this module for DDD”. Scans a file, diff, or module against the DDD anti-pattern catalog and reports specific violations with citations to the relevant pattern skill. Do NOT use when the user wants new code (route to ddd-implement) or wants to design from scratch (route to ddd-design).
Use when deciding where to spend modeling effort — phrases like "core domain", "supporting subdomain", "generic subdomain", "what's worth building vs buying", "where should the senior engineers work", "is this our competitive edge or just plumbing". Distinguishes Core (competitive edge), Supporting (custom but not differentiating), and Generic (commodity, buy/library) subdomains
Use when establishing or auditing a domain's shared vocabulary—phrases like “ubiquitous language”, “what should we call this concept”, “the team uses different words for the same thing”, “the code uses different names than the business”. Defines what a ubiquitous language is, how to grow one, and the smell tests that reveal a missing one. Do NOT use for code generation; this is a process/language skill.
Use when the user is modeling a descriptive concept with no identity — phrases like "value object", "Money", "Address", "DateRange", "primitive obsession", "wrap this primitive into a type", "two instances with the same attributes are the same". Distinguishes from entities; pairs with ddd-entity
Build, review, debug, migrate, or plan arbitrary-precision decimal math with decimal.js v10. Use for decimal.js, Decimal, Decimal.clone, Decimal.set, precision, rounding modes, ROUND_HALF_UP, ROUND_HALF_EVEN, toDecimalPlaces, toFixed, plus, minus, times, dividedBy, money/currency math, BigInt decimals, NaN/Infinity handling, trig/exp/ln, decimal.js-light, and comparisons with big.js or bignumber.js.
Export raw OpenTelemetry traces from an AI application to Confident AI's Observatory. TRIGGER when the user wants to send OpenTelemetry or OTLP traces/spans from an LLM app, agent, RAG pipeline, or chatbot to Confident AI; configure the Confident AI OTLP endpoint; set confident.span.* or confident.trace.* attributes; export AI-app traces without the deepeval Python package; wire an OTLPSpanExporter, OpenTelemetry Collector, or vendor-neutral OTel SDK to Confident AI; or pick the US vs EU OTLP endpoint. Language-agnostic: the mechanism is OTLP attribute keys plus an exporter endpoint. DO NOT TRIGGER for building DeepEval pytest eval suites, datasets, goldens, metrics, or deepeval test run (use the `deepeval` skill); for instrumenting with the DeepEval SDK's @observe decorator or framework integrations (use the `deepeval-tracing` skill); or for non-AI software such as web servers, CRUD backends, or infrastructure: the confident.* attributes describe AI components only.
Draft developer documentation with clear goals, outlines, titles, headers, procedures, scenario walkthroughs, lists, callouts, skimmable structure, and reusable templates. Use when writing or rewriting READMEs, getting-started docs, tutorials, how-to guides, concepts, API guides, troubleshooting pages, migration guides, SaaS topics, or release documentation.
Diagnose one bug by reproducing it, testing hypotheses, locating the root cause, and returning an evidence-backed diagnosis report. Use when the user wants root-cause analysis before implementation, or when triangulate-diagnosis delegates an independent diagnostic pass.
Inspect code diffs before opening a pull request or merging. This skill MUST be used when the user provides a code diff, pastes code changes, asks for a code or PR review, or when code is about to be submitted as a PR or merged. It MUST NOT be skipped solely because the diff is small. It SHOULD also be used before committing or handing back substantial or high-risk code changes. It MUST NOT be used when changes are limited to non-code content such as documentation, prose, images, or formatting. For small, low-risk self-changes, perform only a lightweight review without specialist dispatch. Checks requirement scope, correctness, security, compatibility, and test coverage. Triggers on: 幫我看程式 diff, 看一下程式改了什麼, review 程式碼, PR review, diff review, code review, 看看程式有沒有問題
Docker Compose for multi-container apps. Covers services, networks, and volumes. Use for local development environments. USE WHEN: user mentions "docker-compose", "docker-compose.yml", "multi-container", "service dependencies", "docker compose up", asks about "local dev environment", "microservices setup", "database + app setup", "docker networks", "docker volumes" DO NOT USE FOR: single container Dockerfiles - use `docker` skill instead, production orchestration - use `kubernetes` skill instead, CI/CD pipelines - use `github-actions` skill instead
Govern project documentation as an engineering asset: inventory and organize docs, map documentation to authoritative code/spec sources, detect drift, validate links and metadata, and build VitePress sites for local viewing and offline delivery. Use when a user asks to organize, audit, synchronize, migrate, document, or package project documentation. Do not use as a substitute for product decisions, business-domain approval, or code refactoring.
MUST USE for any task involving the dotenvx CLI tool — encrypting .env files, running commands with injected env vars, managing secrets across environments, and decrypting at runtime. Use this skill whenever the user mentions dotenvx, dotenv encryption, DOTENV_PRIVATE_KEY, encrypted .env files, or the dotenvx encrypt/run/set/get/decrypt/keypair commands. Also trigger when the user wants to: commit .env files safely to git, stop sharing secrets over Slack/chat, encrypt environment variables with public-key cryptography, set up multi-environment .env configs (production/staging/ci), manage secrets in a monorepo with -fk flag, migrate from python-dotenv or plain dotenv to encrypted envs, inject env vars into any process across any language (Node, Python, Ruby, Go, Rust, etc.), or configure CI/CD pipelines (GitHub Actions, Docker) with encrypted env files. This skill contains the authoritative CLI reference — without it, responses will hallucinate non-existent commands and flags.
Build, review, debug, configure, migrate, teach, or plan Drizzle ORM 1.0 RC (not 0.x) with kit, seed, validators, and Effect drivers. Use for drizzle-orm@rc, drizzle-kit@rc, drizzle-seed@rc, defineRelations RQBv2, pgTable/mysqlTable/sqliteTable, generate migrate push pull studio, drizzle-orm/zod|valibot|typebox|arktype|effect-schema, drizzle-orm/effect-postgres and other effect-* drivers on Effect 4, kit --output json/--hints/drizzle-kit/cli SDK, codecs, snakeCase, InferSelectModel, and 0.x-to-1.0 upgrades.
This skill should be used when the user is working with Effect-TS, asks to "write Effect code", "use Effect", "functional TypeScript", "handle errors with Effect", "dependency injection Effect", "Effect Layer", or needs expert-level guidance on Effect-TS patterns, error handling, concurrency, and best practices.
Use when designing enterprise systems, applying TOGAF framework, creating capability maps, implementing domain-driven design, or planning technology transformations - covers ADM phases, architecture domains, and governanceUse when ", " mentioned.
Estimate complexity, effort, and risks for JIRA tickets, features, or projects. Generates structured reports with time estimates, dependencies, risk analysis, and known unknowns. Use when user asks to "estimate", "size", or "analyze complexity" of work items.
Build, review, debug, configure, migrate, or plan evlog TypeScript logging with current docs. Use for evlog 2.29, initLogger, createLogger, createRequestLogger, useLogger, log.set, createError, parseError, withEvlog, createEvlog, drain pipelines, Axiom/Sentry/PostHog/OTLP/Datadog/Loki/ClickHouse/Better Stack/HyperDX/fs/NuxtHub adapters, sampling, redaction, catalogs, log.audit, createAILogger, evlog/eve, @evlog/telemetry, definePlugin, client HTTP drains, @evlog/cli map/doctor/init/agents, Nuxt/Next/Nitro/TanStack Start/Hono/Express/Elysia/Astro/AWS Lambda integrations, and wide-event observability.
Prevent, detect, and repair AI coding slop and dirty engineering in repositories. Use for planning features, writing code, changing tests, reviewing pull requests, refactoring, hardening CI, debugging regressions, or auditing agent-generated changes. Enforces behavioral contracts, focused diffs, test integrity, repo conventions, security boundaries, and evidence-based completion.
Use this skill when you need semantic codebase context before planning, explaining, or changing project code. It runs a bundled local Fast Context script that calls Windsurf Devstral directly, avoiding the Fast Context MCP server while preserving natural-language repository search, recursive context gathering, and definition/signature completeness checks.
Unified prototype analysis (Modao + Figma): Modao retrieves asset packages through the v2 asynchronous export API; Figma prototypes prefer Figma MCP for structure with the REST API as a fallback, and output developer-ready Markdown organized by page and gameplay module. Triggered when the user provides a Modao prototype link, or explicitly states that a Figma link is a prototype and asks for analysis. If there is only a Figma link without saying it is a prototype, or for a clearly identified Figma design file, UI Meta, or asset export request, it must not trigger — use figma-to-ui-meta instead.
This skill should be used when taking a single software feature from intent to shipped as a solo developer — goal-first, TDD, deterministic verification, evidence only where it earns its keep, and human judgment at the two moments that matter (goal approval, merge). Trigger when the user says "let's build feature X", "ship this feature", "run this through the factory", "write a goal contract", "feature-factory", or wants a disciplined intent→merge loop that resists process bloat. NOT for whole-product planning, multi-feature roadmaps, or autonomous multi-agent swarms.
Design and audit feature sunsets, API deprecations, plan removals, integration shutdowns, legacy workflow retirement, game event closure, migration alternatives, usage analysis, customer communication, contract exceptions, support readiness, kill dates, and post-sunset cleanup. Use when removing or materially changing a product capability without breaking trust.
Convert Figma designs to React code using Spirit Web components. Use when working with Figma designs, implementing UI from Figma files, converting Figma autolayouts to code, or when the user mentions Figma, Spirit components, or design-to-code conversion.
Helps developers use FineUI DataList: static list items, data binding, custom text-and-image content, single and multiple selection, grouping, list navigation and load more. For mobile lists, card-style lists, selectable data lists, and DataList/DataListItem questions. Covers F.js, FineUI.Pro, FineUI.Core MVC/RazorForms/RazorPages, and FineUI.Java. Trigger phrases: "FineUI DataList", "DataList", "DataListItem", "数据列表", "移动端列表", "列表分组", "列表多选", "SelectedValueArray", "EnableMultiSelect", "KeepCurrentSelection", "DataTextField", "DataValueField", "加载更多", "AppendData", "data-list", "data-list-item".
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.