Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Svelte 5 development with runes ($state, $derived, $effect), SvelteKit full-stack framework, and modern reactive patterns. Use when building Svelte applications, implementing fine-grained reactivity, or working with SvelteKit routing and server functions.
Complete guide for implementing the Syncfusion WPF GridControl — an Excel-like, cell-based virtual grid for Windows Presentation Foundation applications. Use this when working with WPF GridControl or Syncfusion grid components, including cell types, virtual grids, formula cells, clipboard operations, and Excel import/export. Covers QueryCellInfo events, GridStyleInfo, GridModel, row/column management, and appearance customization for desktop applications.
Deep multi-phase implementation planning with parallel agent exploration, iterative user interviews, and structured plan output. Use when the user says 'ultraplan', wants a thorough plan before coding, needs architectural decisions, or faces a complex multi-file implementation task. Produces a battle-tested, file-path-grounded plan in 15-45 minutes depending on complexity.
Migrate react-native-unistyles from v2 to v3. Triggers on: "migrate unistyles", "upgrade unistyles", "v2 to v3", "unistyles migration", "update unistyles", "convert unistyles v2". Covers all API changes including StyleSheet.create, useStyles removal, theme configuration, variants, withUnistyles, Babel plugin setup, style spreading fixes, and third-party component wrapping.
Valkey (Redis-compatible) in-memory data store for caching, session storage, pub/sub, queues, and distributed locks. Use when configuring Valkey or Redis-compatible caching, choosing eviction policies, implementing rate limiting, setting up pub/sub or streams, writing Docker Compose services, migrating from Redis, or tuning performance. Use for valkey, redis, cache, session, pub/sub, streams, distributed-lock, rate-limit, sorted-set.
Deep performance optimization skill for Triton operators on Ascend NPU, dedicated to achieving the Triton operator performance improvements requested by users. Core techniques include but are not limited to Unified Buffer (UB) capacity planning, multi-token parallel processing, MTE/Vector pipeline parallelism, and mask optimization. Always trigger this skill when the user mentions the following: performance optimization of Vector-type Triton operators on Ascend NPU.
Use when writing, reviewing, or debugging code that imports from "@vueuse/shared" (or its utilities re-exported by "@vueuse/core"). Provides the v15.0.0 API surface, debounce and throttle defaults, watch variants, state-sharing patterns, and v14 to v15 migration rules.
Designs new features, extensions, or modifications to Uncle Bob's Acceptance Pipeline Specification — new mutation strategies, Gherkin syntax support, report formats, pipeline stages, IR fields, or handler patterns. Trigger when someone asks "how would I add X to the acceptance pipeline" or discusses spec-level changes to the parser, generator, runtime, mutator, or reporter components — even if they don't explicitly say "feature design." Works in tandem with the acceptance-pipeline-catalog skill, which provides the baseline spec reference.
Use when working with Bagisto's EAV attribute system — adding or changing an attribute, attribute family or group, reading or writing a product attribute value, or debugging a value that reads back empty or from the wrong locale or channel. Trigger phrases include "attribute", "EAV", "attribute family", "attribute group", "attribute option", "custom attribute", "value_per_locale", "value_per_channel", "product_flat", "swatch".
Automatically fetch design specifications from getdesign.md based on a brand name and generate matching UI code. Supports 62 top brand styles (Apple, Notion, Claude, Stripe, etc.), and Chinese or English brand names and mixed styles. Triggers when the user mentions "XX style", "make it feel like XX", or "reference XX's design".
Use this skill when a modeled process has to run or be operated—deploy it, start it with test data, find where a case is or why it's stuck, resolve incidents, complete tasks, publish messages, or cancel—even if Camunda or c8ctl isn't mentioned. Operates Camunda 8 clusters with c8ctl; it does not author models
Analyses git changed files in the workspace and makes atomic, functional, and semantic commits using conventional commits format. Use when the user asks to commit changes, create commits from staged/unstaged files, or organise working tree changes into meaningful commits.
Workflow for building and modifying content management systems across WordPress, Shopify, Wix, Squarespace, Drupal, WooCommerce, Joomla, HubSpot CMS Hub, Webflow, Adobe Experience Manager, and similar platforms. Use when working on CMS themes, plugins, apps, modules, admin panels, media uploads, content models, editors, markdown pipelines, or static export workflows.
Previews, provisions, or diagnoses a uv-managed local Python .venv with `databricks environments setup-local`. Use when the user wants to set up or fix one for Databricks Connect, cluster or serverless compute, `--job-task`, or a bundle target, or when setup-local fails.
API design from domain model — CQRS command/query separation, REST API endpoint design, data object conversion chain (PO→DO→DTO→VO), unified response format, OpenAPI/Swagger generation, BFF pattern, API versioning, and security design. Use when user asks about API design, REST API, OpenAPI, BFF, DTO design, 接口设计, or data object conversion.
Use when designing software architecture, refactoring code structure, solving recurring design problems, or when code exhibits symptoms like tight coupling, rigid hierarchies, scattered responsibilities, or difficult-to-test components. Also use when choosing between architectural approaches or reviewing code for structural improvements.
Inventing deterministic metrics — turning a fuzzy property like 'maintainability', 'risk', or 'how reducible this code is' into a deterministic, computable number an agent can trust and optimize. Covers the path from construct to adoption — operationalizing the construct, confronting computability limits (Kolmogorov, Rice) with sound proxies, picking the right measurement scale, proving properties (monotonicity, invariance, the Weyuker/Briand axioms), guaranteeing determinism, establishing construct validity (not just LOC in disguise), and hardening against Goodhart-style gaming when an agent optimizes the metric. Trigger when designing, reviewing, or validating a quantitative metric, score, measure, or index — and even when the user doesn't say 'metric' but wants to quantify, score, rank, or measure code/behavior, build a deterministic optimization target, or invent a measure for something previously unquantified (e.g., behavior-preserving codebase-size reduction).
Use this skill when the user runs doca_dpa_hl_tracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm primitive calls, RDMA WR submission, completion drain) — picking TRACE vs CRIT, tuning the JSON config (file-size limits + file_size_limit_policy, thread priorities/cores), decoding against the matching DPA-side ELF, or diagnosing empty/noisy captures. Trigger even when the user does not explicitly mention "DOCA DPA tracer" or "high-level tracer" — typical implicit phrasings include "DPA kernel returns wrong result but host completions look clean", "kernel-entry to first-comm latency is huge", "RDMA WR to drain gap on the DPA", "trace file truncated mid-run", "TRACE doubled my DPA latency", or "tracer wrote a file but parser shows zero events". Refuse and route elsewhere for writing DPA kernels, DPA-Comms/DPA-Verbs programming, raw per-cycle DPA profiling, host-side doca-dpa debugging, or production DPA telemetry — those belong to other skills.
Set up and orchestrate multi-container Docker applications using docker-compose, including service configuration, networking, volumes, and environment management. Use when the user requests docker compose setup or provides relevant inputs for this workflow.
Creates comprehensive Python library documentation including Google-style docstrings, Sphinx setup, API references, tutorials, and ReadTheDocs configuration. Use when writing docstrings, setting up Sphinx documentation, or creating user guides for Python libraries.
JavaScript/TypeScript SDK for Editframe's cloud video API, plus the editframe CLI for the installed local runtime. Create renders, upload media files, sign playback URLs, run video pipelines that transcribe audio, and request exports from the command line.
Implements error handling patterns, structured logging, retry strategies, circuit breakers, and graceful degradation. Use when designing error handling, setting up logging, implementing retries, adding error tracking, or when asked about error boundaries, log aggregation, alerting, or resilience patterns.
Library reference for @expo/ui SwiftUI components on iOS — covers Host boundaries, modifier composition, iOS 26 Liquid Glass and Human Interface Guidelines composition rules, layout/input/navigation/display catalogues, and ObservableState patterns. Use this skill whenever writing or reviewing React Native code that imports from @expo/ui/swift-ui or @expo/ui/swift-ui/modifiers — including new Expo apps adopting native SwiftUI views, migrations from React Native primitives to expo-ui, and code targeting iOS 26 features (Liquid Glass, GlassEffectContainer, sheet detents). Trigger even if the user does not explicitly mention "expo-ui" but is writing iOS-targeted Expo UI code that should bridge to SwiftUI.
Launches a fast autonomous meeting with automatically selected personas, then implements the decision, commits, creates an MR/PR, pushes, and publishes a summary in French — all without user intervention. Use when the user wants a decision to be made and executed end to end automatically (including code, commit, and MR/PR). For analysis or a decision without writing code, use meeting instead.
Core Feishu CLI platform capabilities, not a general fallback for Feishu requests: configuration and multiple profiles, Device Flow login, Token and scope preflight checks, diagnostics for enabling scopes on the app side, doctor, skill installation and CLI upgrades, OpenAPI schema lookup and API passthrough, global search (documents with folder/knowledge base/creator filters, messages, and apps), and user lookup by email or phone number, departments, and bots. Use when the user mentions Feishu login, expired Tokens, 99991672/99991679, switching profiles, skill or CLI version drift, calling an unwrapped interface, searching across Feishu for documents or messages, or looking up open_id. Use this Skill for schema lookup or raw API calls even when the endpoint is for approvals or meetings. Not for business operations involving documents, cloud storage and permissions, messages, spreadsheets, visualization, calendar/tasks/approvals/OKR, email, or meetings; use feishu-cli-docs/storage/messaging/data/visual/work/mail/meetings respectively.
Triage and fix review findings that already exist on a GitHub PR, then reply and resolve the threads. Use on a CodeRabbit review URL, a PR whose review comments still need working through, or a local /review-pr findings file. When the PR has no findings yet, /review-pr produces them first.
Multi-engine long-term memory for game AI agents. Deep Godot 4.7+ (99 skills, 27 genre blueprints) + Bevy docs-first parity — audited patterns, persona orchestration (Analyst · Auditor · Builder), production-grade engineering.
Multi-engine long-term memory for game AI agents. Deep Godot 4.7+ (99 skills, 27 genre blueprints) + Bevy docs-first parity — audited patterns, persona orchestration (Analyst · Auditor · Builder), production-grade engineering.
Write an implementation plan as one interactive HTML page - a tree of claims (why › what › how › where), each proved by one exhibit (UI mockup, state machine, call stack, schema or code), with the decisions the user has to make placed on the claim they change. Use when the user types /html-plan, or asks for a plan, RFC or design before building something that touches more than a couple of files.
Inngest event-driven functions in a Next.js (App Router) project — creating the client, the /api/inngest route handler, typed events with Zod schemas, durable event-triggered functions, scheduled cron functions, or fan-out orchestrators. Trigger when scaffolding Inngest patterns — and even if the user just says "add a background job", "process this async", "schedule X every hour", or "send an event when Y happens" in a Next.js codebase. Also trigger when reviewing existing Inngest code to enforce event-naming, function-id stability, and step-idempotency conventions.
Write, edit, and review MaaFramework (MaaFW) pipelines — creating tasks and sub-flows from scratch (breaking large tasks into nested reusable sub-flows, translating requirements into states, naming resource files and nodes, writing recognition/action nodes and defining ROIs, designing next chains with branches, loops, interrupts and timeout fallbacks, and self-checking reachability) and refactoring existing ones (surveying reusable nodes, searching the whole codebase for references before renaming, reviewing coordinate hygiene and anti-patterns). Use when authoring, editing, or reviewing any pipeline JSON in a MaaFW project — adding tasks, sub-flows, or nodes, breaking large tasks into nested reusable sub-flows, choosing TemplateMatch/OCR/ColorMatch or action types, sizing ROIs, designing next chains with branches, loops, interrupts, and timeout fallbacks, naming or renaming pipeline files, folders, nodes, or template images, or refactoring existing pipelines for coordinate hygiene and anti-patterns.
Yakit MITM hot patch topic. Use when the user needs to dynamically hijack or modify requests and responses with code in the MITM proxy, mirror traffic for analysis, tag and color flows before they are stored, or add mock guardrails for dangerous operations. Covers all hooks of hijackHTTPRequest / hijackHTTPResponseEx / the mirror series / hijackSaveHTTPFlow / mockHTTPRequest and the forward/drop semantics.
Pay-per-call access to the Nansen API via MPP (Tempo). Use when a user wants anonymous Nansen access without an API key and without managing their own Base/Solana wallet — they install the tempo CLI separately and call the API through `tempo request`.
Implement OpenTelemetry (OTEL) observability — Collector configuration, Kubernetes deployment, traces/metrics/logs pipelines, instrumentation, and troubleshooting. Use when working with OTEL Collector, telemetry pipelines, observability infrastructure, or Kubernetes monitoring.
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.