Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Manage TestFlight beta groups and testers using the `asc` CLI tool. Use this skill when: (1) Listing beta groups for an app (`asc testflight groups list`) (2) Creating internal or external beta groups (`asc testflight groups create --internal`) (3) Listing testers in a group (`asc testflight testers list --group-id <id>`) (3) Adding a single tester by email (`asc testflight testers add`) (4) Removing a tester from a group (`asc testflight testers remove`) (5) Bulk-importing testers from a CSV file (`asc testflight testers import`) (6) Exporting testers to CSV for re-use (`asc testflight testers export`) (7) User says "add beta tester", "invite tester", "remove tester", "import testers", "export testers", "list beta groups", or any TestFlight tester management task
End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torch_npu PyTorch custom op) project. Use to design, generate, build, test, document, and tune a new AscendC operator from a name and a math/functional spec. Covers project init, two-level tiling design, op_host/op_kernel code generation, framework registration, compile/install/debug, PyTorch-style API docs, precision evaluation and root-cause debugging, torch_npu.profiler performance benchmarking, performance optimization, and security code review.
Write efficient data queries in B2C Commerce for products, customers, and orders. Use this skill whenever the user needs to search products on a storefront page, look up customer profiles, query orders, paginate search results, or fix slow category pages. Also use when they ask about performance problems with data access, replacing database-intensive APIs with index-backed alternatives, or choosing between search vs query methods — even if they just say "my category page is slow" or "how do I find customers by email".
Implement web service integrations in B2C Commerce using LocalServiceRegistry. Use this skill whenever the user needs to call external REST or SOAP APIs from a cartridge, configure service credentials and profiles in services.xml, handle HTTP requests with createRequest/parseResponse callbacks, set up FTP or SFTP file transfers, or troubleshoot circuit breaker errors. Also use when connecting to payment gateways, shipping providers, or third-party services -- even if they just say 'call an external API from my controller' or 'my service keeps timing out'.
Use when users explicitly ask to brainstorm, shape requirements, compare approaches, or produce a planning/design document before implementation. Turn rough ideas into validated brainstorming/design docs through focused dialogue, role-based analysis, and explicit user approval. Do not trigger this skill for straightforward implementation requests that do not need dedicated design exploration.
BullMQ queue system reference for Redis-backed job queues, workers, flows, and schedulers. Use when: (1) creating queues and workers with BullMQ, (2) adding jobs (delayed, prioritized, repeatable, deduplicated), (3) setting up FlowProducer parent-child job hierarchies, (4) configuring retry strategies, rate limiting, or concurrency, (5) implementing job schedulers with cron/interval patterns, (6) preparing BullMQ for production (graceful shutdown, Redis config, monitoring), or (7) debugging stalled jobs or connection issues
Use Chonkie for fast, lightweight text chunking in RAG pipelines. Covers all 11 chunker types (Token, Fast, Sentence, Recursive, Semantic, Late, Code, Neural, Slumber, Table, TeraflopAI), the Pipeline API for chaining fetch→process→chunk→refine→export→store workflows, embeddings refineries, vector DB handshakes (Chroma, Qdrant, Pinecone, etc.), tokenizer selection, recipe system, REST API server, and async/batch processing. Use when: splitting documents for embeddings, building ingestion pipelines, chunking code or markdown, setting up vector DB ingestion, or any text segmentation task for retrieval-augmented generation.
Advise developers on using Contentstack Variants and Personalize for audience-targeted content. Explain when to use variants versus separate entries, how variant groups work, and how to integrate Personalize with the CMS. Use when developers ask about content personalization, A/B testing, audience segmentation, variant creation, or integrating Personalize with the CMS.
Create a database migration to add a table, add columns to an existing table, add a setting, or otherwise change the schema of Ghost's MySQL database. Use this skill whenever the task involves modifying Ghost's database schema — including adding, removing, or renaming columns or tables, adding new settings, creating indexes, updating data, or any change that requires a migration file in ghost. Also use when the user references schema.js, knex-migrator, the migrations directory, or asks to "add a field" or "add a column" to any Ghost model/table. Even if the user frames it as a feature or Linear issue, if the implementation requires a schema change, this skill applies.
Interactive orchestrator that builds a feature from its CodeSpring plan. It interviews the user about what they're building, checks the feature has enough context (notes + Frontend/Backend PRDs) and a numbered task list, guides them to fill any gaps, then builds the Kanban tasks — optionally spawning up to 5 parallel sub-agents — while guarding the shared systems it could break. Use when the user wants to build/implement a feature they planned in CodeSpring. Triggers, "build this feature", "implement my feature", "start building from CodeSpring", "let's build X", "work through my Kanban tasks".
Audit dependency vulnerabilities, version health and license facts for Node.js, Python, Go, Rust, JVM and Ruby projects; use when the user asks to check package.json, lockfiles, requirements, go.mod, Cargo.toml, pom.xml or Gemfile.lock, or to generate an audit report that does not change dependencies
Set up local development environments with production parity for DigitalOcean App Platform. Use when setting up local dev, adding devcontainer to a project, running App Platform apps locally, or configuring backing services (Postgres, Redis, Kafka, S3).
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.
Run a read-only documentation drift audit for a feature, PR, branch, release, API, configuration change, workflow, CLI, package, or repository area. Use when the user asks whether docs are stale, missing, inconsistent with code, or need updates after code changes. Checks README files, setup guides, API docs, env docs, changelogs, examples, comments, generated docs, and user-facing instructions. This is not a general code review; it compares what the docs claim against what the code does.
Build React TypeScript web applications using Docyrus as a backend. Use when creating or modifying apps that authenticate with Docyrus OAuth2, fetch/mutate data via the @docyrus/api-client library, use auto-generated collections for CRUD operations, or build queries with filters, aggregations, formulas, pivots, and child queries against Docyrus data sources. Triggers on tasks involving @docyrus/api-client, @docyrus/signin, Docyrus collections, data source queries, or Docyrus-backed React app development.
Reverse JavaScript-based custom DSL/VM interpreters, non-standard WASM-like runtimes, and risk-control engines. Use when analyzing IIFE or switch-based opcode dispatchers, extracting instruction tables, recovering bytecode semantics, capturing VM state at runtime, or reconstructing execution flow.
Guide embedded technical engagements from ambiguous stakeholder need through discovery, framing, hypothesis, build, evaluation, deployment, adoption, measurement, and generalization while preserving evidence, decision rights, and field learning. Use when one accountable technical lead must carry continuity across customer or stakeholder discovery, implementation, production fit, adoption, and measurable outcomes. Do not use for a bounded repository change, product investment governance, ongoing reliability or platform ownership, an isolated specialist task, or advisory work that ends before implementation and adoption.
READ this skill when designing or planning any game system architecture — including combat, skills, AI, UI, multiplayer, narrative, or scene systems. Contains paradigm selection guides (DDD / Data-Driven / Prototype), system-specific design references, and mixing strategies. Works as a domain knowledge plugin alongside workflow skills (OpenSpec, SpecKit) or plan mode of an agent.
Invoke when the user asks about sprint planning, milestone tracking, scope management, risk assessment, scheduling, resource allocation, team velocity, or needs production coordination across the development team. Triggers on: "sprint", "milestone", "scope", "risk", "schedule", "resource", "velocity", "deadline", "crunch", "cut list". Do NOT invoke for creative vision (use game-creative-director) or architecture decisions (use game-technical-director). Part of the AlterLab GameForge collection.
Generate documentation from existing code or prototypes. Triggers on: "document this", "reverse document", "generate docs from code", "onboard to codebase", "document existing system". Do NOT invoke for writing new design docs from scratch (use game-brainstorm or game-design-review). Part of the AlterLab GameForge collection.
Use when generating Git commit messages, writing commit messages, committing code, or when the user mentions commit、提交、commit message、提交信息. Automatically stages all changes by default, uses LLM to judge if new files should be committed, generates Conventional Commits format messages in Chinese.
Creates Architecture Decision Records (ADRs) and Change Requests (CRs) for project governance. Activates on keywords like "ADR", "architecture decision", "CR", "change request", "governance", "technical decision", or "requirement change". Use for documenting technology choices, architectural patterns, or scope modifications.
Persistent, recoverable GSAP workflow for coding agents. Use when the user wants to animate a new page or section, or improve an existing page/component with GSAP. Route new/greenfield work to gsap-new and existing-code improvement work to gsap-refactor. Always use .gsap artifacts as the source of truth so any fresh agent session can resume without chat history.
Hutool Chinese Java utility library skill. Covers a feature selection matrix against Guava/Apache Commons, quick references for the most common string/collection/date/file/HTTP methods, HttpUtil vs OkHttp selection, and BeanUtil vs MapStruct responsibility split. Use when users need utility methods for Chinese scenarios (pinyin/ID card/phone number validation), HTTP requests, file operations, or encryption/decryption in a Java project. Prevents LLMs from reinventing the wheel instead of using Hutool.
Guide maintainable, resilient, test-double-friendly code: clear names, decomposition, safe defaults, idempotency, bounded retries, observability, and quality gates. Use for production code, jobs, queues, webhooks, APIs, refactors, reviews, plans, CI, config, or dependency-heavy code and tests. Skip disposable work.
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).
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.