Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Compose look-and-feel traps: theme and colour tokens, artwork palettes, gradients and scrims, shimmer, glass and particle effects, animation, image loading, charts and stats displays (percent changes, shares, buckets). Use when a visual bands, pops, freezes or misleads.
Comprehensive guidance for Clean Architecture (整洁架构) — Robert C. Martin's Clean Architecture with Enterprise Business Rules, Use Cases, Interface Adapters, and Frameworks layers. Covers core entities, use case interactors, dependency rules, and full implementation steps with Java/Spring Boot examples. Use when user asks about Clean Architecture, 整洁架构, Robert Martin, Uncle Bob, use case driven architecture, or needs to implement DDD with clean architecture.
DDD architecture documentation generation — C4 model diagrams (Context/Container/Component/Code), ADR (Architecture Decision Records), domain model documentation, API documentation, architecture decision log, and team communication templates. Use when user asks about architecture documentation, 架构文档, ADR, C4 diagram, domain model doc, 架构决策记录, or needs to document DDD architecture for team.
DDD architecture evaluation and evolution — DDD maturity 5-level model (AdHoc/Aware/Applied/Scaled/Optimized), architecture fitness assessment (business alignment/team fit/tech fit/evolution capability), technical debt quantification with scoring, architecture evolution roadmap (4 phases), and migration risk assessment. Use when user asks about architecture evaluation, 架构评估, DDD maturity, 技术债务, architecture evolution, 架构演进, or needs to assess DDD implementation health.
Comprehensive guidance for DDD Layered Architecture (DDD 四层架构) — Traditional 3-layer to DDD 4-layer transformation with Interface/Application/Domain/Infrastructure layers. Covers complete directory structure, dependency inversion, ArchUnit validation, Spring Boot integration, and step-by-step migration guide. Use when user asks about layered architecture, DDD four-layer, 分层架构, traditional layering with DDD, or needs a simple DDD entry point for small to medium teams.
Provides comprehensive guidance for hexagonal architecture including ports and adapters, domain isolation, and dependency inversion. Use when the user asks about hexagonal architecture, needs to implement ports and adapters pattern, or structure applications with hexagonal architecture.
Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.
Audit a design proposal or diff against Exarchos's architectural invariants — event-sourcing integrity (INV-1), facade equivalence over shared dispatch core (INV-2), basileus-forward (INV-3), platform-agnosticity (INV-4), and agent-first interface design (INV-5a input ergonomics, INV-5b spec-aligned output contract, INV-5c Aspire-inspired control-plane verbs, INV-5d action discriminator pattern). Pairs with /axiom:backend-quality — this skill is project-specific (axiom is generic). Triggers: 'check invariants', 'design conformance', 'check #1118 / #1109', or /design-invariants.
Use this skill when the user has an existing DPDK application and is adding DOCA capabilities in-place — most commonly DOCA Flow hardware steering — without rewriting the data-plane in DOCA-native form: binding a DPDK port id to a `doca_dev` (`doca_dpdk_port_probe` / `doca_dpdk_port_as_dev`), converting `rte_mbuf` ↔ `doca_buf`, querying `doca_dpdk_cap_is_rep_port_supported`, or debugging `DOCA_ERROR_*` from a bridge call. Trigger even without "DOCA DPDK Bridge": "how do I add DOCA Flow to my DPDK app", "make a DPDK port visible to DOCA", "the bridge loads but every operation returns errors", "pkg-config --exists doca-dpdk-bridge fails", or "DOCA_ERROR_NOT_FOUND on port registration". Route elsewhere for fresh DOCA-native packet I/O (doca-eth), flow-rule programming (doca-flow), DOCA or DPDK install (doca-setup), or RDMA data movement (doca-rdma).
Génère ou met à jour un README.md en français, orienté Product Owner, avec diagrammes Mermaid. Revoit et améliore la documentation technique dans docs/. Génère aussi CLAUDE.md et AGENT.md si absents. Se déclenche sur : create readme, update readme, generate readme, générer le readme, mettre à jour le readme, generate docs, update docs, /docs.
.NET SDK and runtime installation across Windows, macOS, and Linux. Handles version detection, platform-specific installers (WinGet, Homebrew, apt, dnf), SDK vs runtime selection, offline installation, Docker setup, and troubleshooting. Auto-activates for .NET installation, setup, version management, and multi-platform deployment.
Manages .NET SDK installation (dotnet-install, workloads), project setup (.slnx, Directory.Build.props, CPM), MSBuild authoring, build optimization, performance (Span, ArrayPool, stackalloc), profiling (dotnet-counters, dotnet-trace), Native AOT/trimming, GC tuning, CLI apps (System.CommandLine, Spectre.Console, Terminal.Gui), ILSpy decompilation, VS Code debug config (launch.json, coreclr, remote), C# LSP (csharp-ls, OmniSharp), and version detection/upgrade. Spans 34 topic areas. Do not use for UI implementation or API security design.
Use this skill to set up a CI gate that fails the build when Compose stability silently regresses, using the `skydoves/compose-stability-analyzer` Gradle plugin (primary) or the `j-roskopf/ComposeGuard` plugin (alternative for non-Android multiplatform). Covers applying `com.github.skydoves.compose.stability.analyzer`, configuring the `composeStabilityAnalyzer { stabilityValidation { ... } }` DSL, generating a `.stability` baseline with `:stabilityDump`, committing it to version control, and wiring `:stabilityCheck` into a GitHub Actions or other CI job. Use when the team wants a stability SLO, when an unstable parameter slipped into a shared data class and went unnoticed until jank was reported, when migrating a large app to strong skipping, or when the user mentions stabilityCheck, stabilityDump, baseline drift, ComposeGuard, or "fail the build on stability regression".
Use this skill when developing, structuring, reviewing, or modifying FUI web modules. It provides strict guidelines for the metadata-driven architecture (the <fui-app> config block of index.vue), mandatory grid layout system, action protocols, and environment-aware workflow rules. Apply the canonical module structure in both editor and chat contexts. In editor or extension contexts with workspace access, work with the real module files. In chat or agent-chat contexts without workspace access, work from pasted artifacts while virtualizing the same module structure in the response.
Use when writing or modifying Python code that imports `genoray` to read genotypes/dosages from VCF, PGEN, or SparseVar (`.svar`) files. Covers the public API surface, mode constants, range queries, chunking, filtering, and the SparseVar workflow. Skip for unrelated bioinformatics work.
GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile. Triggers on: "optimize GPU training", "speed up CUDA", "reduce OOM", "migrate NumPy to CuPy", "manage GPU memory", "benchmark PyTorch".
Author-then-adversarial-review authoring pass for a single OpenSpec artifact — a subagent drafts it, `hrt-artifact-lint` clears the deterministic structure checks, then two subagents review it concurrently in fresh isolated contexts (a Destructive Critic for content/logic, a Structural Auditor for the structural judgement calls a linter cannot make), findings resolved before finalizing. Parameterized by artifact (specs or design). Use during the tempa-spec schema's `specs` and `design` phases.
Cross-artifact consistency review for OpenSpec's tempa-spec schema — checks proposal.md, specs/**/*.md, design.md, and tasks.md are mutually consistent and faithful to the requirements, BEFORE any code is written. One cycle is an ALIGN pass (deterministic structure and coverage via `hrt-artifact-lint`, then five judgement dimensions, a consequence gate, then HIGH/MEDIUM/LOW × MECHANICAL/DECISION — HIGH DECISION findings shown together and answered one by one, the rest in one digest), a fresh-context VERIFY pass (only when ALIGN raised a HIGH), then a human WALKTHROUGH led by specs and design; walkthrough feedback re-enters ALIGN. Exits on a clean walkthrough round or user sign-off; after 3 cycles it asks whether to keep going. Use during the tempa-spec schema's `align` phase.
Selects sufficient, low-noise local shell commands for repository exploration, git inspection, tests, and container checks. Use when choosing command scope or output detail, especially for token savings or terse workflows; not for incidental tool mentions or requests for full output.
Reviews an ADK integration documentation page (a Markdown file under docs/integrations/) or an integration pull request for correctness, structure, style, working code, valid links, and catalog conventions. Produces a prioritized review report, a recommended decision (approve, request changes, or close PR), a top-level review response, and draft line-anchored comments; only fixes issues when explicitly asked. Triggers on "integration-review", "review integration page", "review integration PR", "review this integration", "check integration docs".
Run the konsistent CLI, review all reported violations, and fix them in the codebase. Use when the user wants to "fix konsistent violations", "resolve konsistent errors", "clean up konsistent diagnostics", "make konsistent pass", "address structural convention violations", or asks to run konsistent and act on the results. The skill is interactive: it requires explicit user decisions when many violations stem from the same rule (rule vs. code question), explicit user confirmation before modifying any code, and a triage step for non-trivial violations. For editing `konsistent.json`, this skill defers to the `konsistent-config` skill.
Put local dev surfaces behind trusted HTTPS `.test` domains — real certs and DNS, not localhost:port — with the `lokei` CLI: framework-aware `run`, public tunnels via `share`/`--expose`, `docker up` and `.test.yaml` multi-service orchestration, and `doctor`/`routes`/`logs` diagnostics, backed by a one-time setup that mints and trusts a local CA and wires `.test` DNS and port forwarding. Never auto-runs setup, service-install, or uninstall — those wait for approval. Use for local HTTPS, named domains, tunnel sharing, or lokei diagnosis.
Write, register, and debug MaaFramework Custom recognition/actions — criteria for when to use Custom, host and registration paths, binding implementation and registration, parameter parsing and validation, reusing pipeline nodes, agent child process mode, and engineering conventions. Use when implementing MaaFW custom recognition or action logic, deciding registration path for your host, registering customs, parsing custom_action_param/custom_recognition_param, reusing pipeline nodes inside custom code, or setting up the agent child process mode.
Provider-independent production workflow for creating Manim-based explainer animations. Use when an agent must plan, code, render, QA, or hand off precise math, science, data, diagram, algorithm, or concept animations with Manim, including storyboard, scene architecture, formulas, coordinate systems, voiceover timing, accessibility, reproducibility, provenance, and delivery decisions.
Helps users generate, edit, and validate mirrord.json configuration files for mirrord (MetalBear). Use when the user wants to connect their local process to a Kubernetes environment, configure features (env/fs/network), or needs feedback on an existing mirrord.json. Always ensures output JSON is valid and schema-conformant.
Generates module specifications following amplihack's brick philosophy template. Use when creating new modules or documenting existing ones to ensure they follow the brick & studs pattern. Analyzes code to extract: purpose, public contract, dependencies, test requirements.
Opinionated, backend-agnostic Next.js 16 (App Router) architecture — authorization at the data layer, server-side loading with cache()+Promise.all, mutations through next-safe-action + typed route handlers, client/server boundaries ('use client' at leaves + TanStack Query), forms with RHF + Zod, UI via shadcn/ui + Tailwind + Base UI + next-intl, request handling in proxy.ts (Next.js 16's renamed middleware), and a Turbo monorepo of @app/* packages confining the backend behind one data-access package. Examples use Supabase but every rule states the transferable principle. Use when writing, reviewing, or refactoring Next.js 16 code. Trigger on server actions, route handlers, RSC vs 'use client' placement, TanStack Query, RHF/Zod, proxy.ts, or monorepo package layout — even when the user doesn't say 'patterns' or 'best practices'.
Practical Python craftsmanship guidance based on One Python Craftsman. Use when writing, refactoring, or reviewing Python code for naming, branching, data structures, functions, exceptions, loops, decorators, imports, file I/O, edge cases, and modern syntax choices. If the skills set includes friendly-python, suggest invoking it for better Python outcomes.
Validate and review Wallet MCP plugin files against the Plugin Specification. Use when writing a new plugin, preparing a plugin PR for submission, self-checking a plugin before opening a PR, or reviewing someone else's plugin PR. Triggers on requests like "check my plugin against the spec", "validate this plugin file", "review my plugin PR", "does this plugin conform to the spec", "prepare my plugin for submission", "write a plugin for X protocol".
Use to assemble a product roadmap for a GitHub repository — or a multi-repo product (an org or a set of repos as one product) — derived from issues and PRs via a reasoning graph. Triggers: «собери роадмап из issues/PR», «роадмап по продукту», «что в этом репо делать дальше», roadmap from repo/github, roadmap for my org, multi-repo roadmap, quick roadmap, product-roadmap. Plays the maintainer: the verified ground of the present, a weighed backlog as шабда, directions (bianhua), graph+markdown+HTML rendering. Composes iskronify, intake and assembly. Requires the gh CLI and iskron_* tools.
Bringing up a complete ROS2 system on a robot's onboard computer: systemd services, launch file composition, ordered startup, and production monitoring. Use this skill when configuring a robot to start ROS2 nodes on boot, writing systemd unit files for ROS2 launch, composing layered launch files for full robot stacks, setting up watchdog monitoring, configuring udev rules for deterministic device naming, or debugging boot-time race conditions. Trigger whenever the user mentions robot bringup, robot startup, systemd for ROS2, ROS2 on boot, launch file composition, robot boot sequence, udev rules for cameras or serial ports, automatic restart for ROS2 nodes, network configuration for multi-machine ROS2, log rotation for robots, graceful shutdown of robot stacks, or SSH-based remote debugging. Also trigger for sourcing workspaces in systemd, ordered startup with health checks, or running ROS2 systems as long-running production services. Covers systemd on Ubuntu 22.04/24.04 with ROS2 Humble, Iron, and Jazzy.
Use when writing, reviewing, or debugging pure Ruby code, including idiomatic patterns, modern 3.x+ features (pattern matching, Data.define, endless methods), error handling conventions (raise vs fail, result objects), memoization, and performance idioms. For Rails use rails-guides. For testing use minitest. For code style use sandi-metz-rules
Use when writing, reviewing, or debugging pure Ruby code, including idiomatic patterns, modern 3.x+ features (pattern matching, Data.define, endless methods), error handling conventions (raise vs fail, result objects), memoization, and performance idioms. For Rails use rails-guides. For testing use minitest. For code style use sandi-metz-rules
Design and enforce the internal layout of a single Rust crate — lib.rs/main.rs as a thin index, semantically named directory modules, `mod` declarations, `pub` visibility, and targeted re-exports. Use when users ask how to organize src/, write lib.rs, split a growing crate into subdirectories, choose between `foo.rs` and `foo/mod.rs`, name modules, avoid flat lib.rs "index plus glob re-export" anti-patterns, or migrate Java-style or Python-style flat projects to idiomatic Rust module trees.
Fetch, analyze, reproduce, and minimize GitHub issue reproductions. Use only when the user asks to check whether a GitHub issue reproduces, minimize a GitHub issue's repro, analyze a GitHub bug report, or scrub/triage a GitHub issue for reproducibility. Do not use for standalone reproduction requests without a GitHub issue.
Use this skill to install and verify Compose HotSwan end to end so a developer goes from zero to working sub-second hot reload on a real device or emulator in one session. Covers the JetBrains IDE plugin install, the `com.github.skydoves.compose.hotswan.compiler` Gradle plugin wiring, the canonical `hotSwanCompiler { enabled = true; debugOnly = true }` DSL block, the HotSwan tool window flow, and the first save-to-reload verification. Trigger when the user mentions HotSwan, Compose hot reload, instant UI update, "save and see", "no rebuild", live edit on device, fast Compose iteration, or already has the JetBrains plugin installed and asks how to apply the Gradle compiler plugin.
[AUTO-INVOKE] MUST be invoked BEFORE deploying contracts or writing deployment scripts (*.s.sol). Covers pre-flight checks, forge script commands, post-deployment validation, and verification. Trigger: any task involving forge script, contract deployment, or block explorer verification.
Use when executing R2 in the sdlc-dev product requirements Spec process: convert requirements/solution.md into a deliverable, verifiable, and testable requirements/prd.md while avoiding guessed paths, continuing even if solution.md is missing, and using “待确认问题/Open Questions” in place of a verification checklist.
Use when an application issues and validates its own first-party JWT access and refresh tokens, including authentication filters, password encoding, RBAC, and method security. For JWTs issued by Keycloak, Auth0, Okta, Cognito, or another authorization server, use oauth2-resource-server.
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.