Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Helps agents write and review Scala Cats Effect IO code. Use for suspending side effects and non-determinism in IO or F[_], choosing Sync/Async/Temporal/Concurrent/Clock/Random, handling blocking I/O, testing with TestControl, and composing resources, fibers, races, and structured concurrency safely.
This skill should be used when creating a skill for a CLI tool. Use when users ask to document a command-line tool, create CLI guidance, or build a skill for terminal commands. Essential for systematically introspecting CLI tools through help text, man pages, GitHub repos, and online research, then organizing findings into effective skill documentation.
Analyzes legacy COBOL programs and JCL jobs to assist with migration to modern Java applications. Extracts business logic, identifies dependencies, generates migration reports, and creates Java implementation strategies. Use when working with mainframe migration, COBOL analysis, legacy system modernization, JCL workflows, or when users mention COBOL to Java conversion, analyzing .cbl/.CBL/.cob files, working with copybooks, or planning Java service implementations from COBOL programs.
Owns repositories, data sources and mapping for Compose and Compose Multiplatform apps: DTO to domain to UiModel boundaries, Ktor clients and bearer auth, WebSocket and SSE, Room, DataStore, Paging 3, offline-first and data-layer tests. Use when writing or reviewing a repository, data source, DTO, mapper, HttpClient, bearer token, WebSocket, SSE, Room DAO, migration, DataStore, PagingSource, RemoteMediator, offline cache or MockEngine test. Do NOT use for ViewModel or UI wiring (compose-feature), composables (compose-ui), the MVI contract or error tiers (compose-architecture), Gradle modules (compose-project), or commonMain vs platform splits (compose-platform).
Use this skill first for any Jetpack Compose or Compose Multiplatform task: a new feature or screen, a change to existing code, a bug fix, a review, making code follow the kit, project or build setup, or a question. It picks the task path and the exact kit files to read. Not for Kotlin work outside a Compose or CMP app.
Owns platform splits for Compose Multiplatform apps: places declarations in commonMain, chooses expect/actual vs interface plus DI, wires host adapters and ports, and validates iOS/Swift interop, desktop and web targets, and platform lifecycle. Use when touching commonMain, expect, actual, iosMain, Swift, SKIE, Flow to Swift, desktop, wasm, web target, or platform-specific code. Do NOT use for routing or architecture (compose-architecture), feature slices (compose-feature), composables or resources (compose-ui), repositories or persistence (compose-data), or Gradle target setup (compose-project).
Use this skill to attach a USB device or emulator to ADB, list transports with `adb devices` / `adb devices -l`, disambiguate among multiple devices using `-s SERIAL`, `-d` (single USB), `-e` (single TCP/IP), or `-t TRANSPORT_ID`, gate scripts on a transport with the canonical `adb wait-for[-TRANSPORT]-<state>` syntax (TRANSPORT in {usb, local, any}; state in {device, recovery, rescue, sideload, bootloader, disconnect}), interpret device states (`device`, `offline`, `unauthorized`, `no permissions`, `recovery`, `sideload`, `bootloader`, `rescue`), accept the RSA fingerprint dialog on first connect, and install Linux udev rules. Use when the user mentions `error: more than one device/emulator`, `error: device not found`, `unauthorized`, `no permissions`, `daemon not running`, "wait for device to boot", `wait-for-device-online` (which is not a real subcommand), or asks how to script around emulator startup.
Retrieves authoritative, up-to-date technical documentation, API references, configuration details, and code examples for any developer technology. Use this skill whenever answering technical questions or writing code that interacts with external technologies. This includes libraries, frameworks, programming languages, SDKs, APIs, CLI tools, cloud services, infrastructure tools, and developer platforms. Common scenarios: - looking up API endpoints, classes, functions, or method parameters - checking configuration options or CLI commands - answering "how do I" technical questions - generating code that uses a specific library or service - debugging issues related to frameworks, SDKs, or APIs - retrieving setup instructions, examples, or migration guides - verifying version-specific behavior or breaking changes Prefer this skill whenever documentation accuracy matters or when model knowledge may be outdated.
Converts HTML/CSS to WPF CustomControl XAML with correct patterns and common pitfall solutions. Use when transforming web designs to WPF, converting CSS animations to Storyboards, implementing CSS border-radius clipping, CSS pseudo-elements (::before/::after), or CSS transforms in XAML.
Critical rules and common mistakes to avoid in Convex development. Use when reviewing Convex code, debugging issues, or learning what NOT to do. Activates for code review, debugging OCC errors, fixing type errors, or understanding why code fails in Convex.
Design and debug Dart asynchronous infrastructure with Future, Stream, isolates, cancellation, and lifecycle-safe ownership. Use for races, stale results, background CPU work, stream leaks, or async error handling; not for routine form-local validation or submission unless its underlying ordering mechanism is the task.
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
Shared resources and dependencies used by other do-* skills. Not a user-invocable skill. Contains the MCP capability registry, MCP discovery instructions, project skills/MCPs procedure and service readiness rules referenced by the do-* execution, review, QA and specification skills.
Drizzle ORM against PostgreSQL inside a Next.js App Router app. Covers client construction (globalThis singleton across HMR, serverless pool sizing, `prepare:false` behind PgBouncer/Supavisor, driver choice when you need interactive transactions, `server-only`), reads in Server Components under Next.js 16 Cache Components (`use cache` superseding `unstable_cache` and the `revalidate`/`dynamic` segment configs, Suspense boundaries, React `cache()` dedupe), Server Actions (authorization inside the action, `updateTag` vs `revalidateTag`, `after()`), Postgres schema types (timestamptz, identity vs serial, jsonb, numeric-as-string, bigint modes), drizzle-kit migrations (generate vs push, CONCURRENTLY outside the migrator, NOT VALID constraints, rename prompts), transactions and pooled connections, and Postgres query traps (keyset pagination, count cost, driver-dependent `db.execute()` shape, NOT IN nulls, prepared statements). Use when writing or reviewing Drizzle + Postgres code in Next.js.
Optimize and build programmatic prompt systems with Stanford DSPy. Signatures, modules (Predict, ChainOfThought, ReAct), optimizer/teleprompter selection, compilation, caching, evaluation. Use when doing programmatic prompt optimization or building compiled prompt programs. Do not use this skill for unrelated requests; route to the nearest named specialist.
Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.
Event sourcing patterns for functional TypeScript — persist state as an append-only log of past events and rebuild it by folding them. Use when implementing a Decider write model, an event store, projections and read models, event versioning, or snapshots. Builds on the Decider from domain-driven-design and the ports/adapters from hexagonal-architecture. Do NOT reach for it on CRUD, or when an audit log or the outbox pattern already suffices.
Guides design and implementation of evolutionary modular-monolith platforms with DDD (strategic + tactical), flat-by-aggregate organization, an Anti-Corruption Layer for vendor independence, a transactional outbox for events, smart resilience (backoff with jitter, circuit breakers, idempotency), and a polished architecture HTML document with elegant SVG diagrams. Use when designing a platform or backend, defining bounded contexts, organizing modules and folders, choosing monolith vs microservices, decoupling from an external service (ERP, storage, AI), making calls resilient, adding real-time push, picking a 2026 TypeScript stack (Nx, NestJS, React), or producing an architecture document or diagram. Also triggers on 'modular monolith', 'bounded contexts', 'flat-by-aggregate', 'ports and adapters', 'architecture diagram'. Do NOT use for simple CRUD, NestJS-only deep implementation (use nestjs-modular-monolith), or pure domain-model review (use tactical-ddd).
Complete browser-based FFmpeg system. PROACTIVELY activate for: (1) ffmpeg.wasm setup and loading, (2) Browser video transcoding, (3) React/Vue/Next.js integration, (4) SharedArrayBuffer and COOP/COEP headers, (5) Multi-threaded ffmpeg-core-mt, (6) Cloudflare Workers limitations, (7) Custom ffmpeg.wasm builds, (8) Memory management and cleanup, (9) Progress tracking and UI, (10) IndexedDB core caching. Provides: Framework-specific examples, header configuration, common operation recipes, performance optimization, troubleshooting guides. Ensures: Client-side video processing without server dependencies.
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
Use a small FlareSolverr JSON CLI for browser-backed GET and POST requests, readiness checks, and session lifecycle management when a site requires Cloudflare or DDoS-GUARD challenge handling. Do not use this skill for unrelated requests; route to the nearest named specialist.
Coordinate end-to-end delivery of a complete Flutter app or feature across UI, state, data, tests, bounded implementation review, and runtime verification. Use for broad vertical-slice ownership; not for data-only sync/cache, one screen or form, or contained work that merely touches multiple files or two domains
Implement, review, or verify Flutter routing, deep-link destinations, back-stack behavior, nested navigation, restoration, redirects, and URL synchronization. Use for route correctness; pair with flutter-device-testing on a concrete runtime, and do not introduce a routing package by default.
Design, implement, or repair production observability in Flutter using operational logs, error and crash capture, breadcrumbs, traces, release context, privacy controls, and verification. Use for diagnosability and incident signals; not product analytics, profiling-only optimization, or a general code review.
Provides one-command project creation for Flutter including project initialization, configuration, and template generation. Use when the user asks about creating Flutter projects, needs to initialize a new Flutter project, or generate Flutter project structure.
Design, review, simulate, and verify FPGA logic using explicit RTL contracts, clock and reset models, CDC analysis, timing constraints, and reproducible implementation evidence. Use for synthesizable HDL, fixed-point arithmetic, handshakes, testbenches, resource tradeoffs, timing closure, and FPGA release or bring-up planning. Do not use for ordinary MCU firmware, generic circuit design, a substitute vendor-tool manual, or unsupported claims of hardware or timing signoff.
Challenges an overly conservative, incremental, or compatibility-led proposal with a bold target model, a concrete kill/merge/split list, materially different options, and a falsifiable first proof point. Use when the user asks to think bigger, open the design space, or imagine the clean target without legacy constraints（打开格局、别太保守、不要被兼容绑架）. Use goudi to pressure-test how the chosen direction lands, and hai-idea to decide whether the idea deserves doing at all.
Master advanced Git workflows—including rebasing, cherry-picking, bisect, worktrees, and reflog—to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
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.