Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use when managing a Forgejo or Gitea server from the terminal: issues, pull requests, repositories, file contents, labels, milestones, releases, webhooks, user settings, or any /api/v1 endpoint through a safe generic API command. Do not use this skill for unrelated requests; route to the nearest named specialist.
Use this skill for frontend UI work that must preserve or extend a product's real design system: new screens/components, high-fidelity rebuilds, restyles, non-trivial forms, role-gated UI, substantial behavior changes, or UI implementation that needs layout, experience, style-guide, clean implementation planning, and final code generation. This is the single frontend skill to install; it is self-contained and routes between lightweight UI edits and the full frontend workflow using bundled references.
Invoke when the user wants a game-specific code review, architecture check, or technical analysis of game code. Covers frame independence, hot path performance, state machine integrity, and resource lifecycle. Triggers on: "code review", "review my code", "check architecture", "game code quality". Do NOT invoke for design document review (use game-design-review) or general sprint planning (use game-sprint-plan). Part of the AlterLab GameForge collection.
Invoke when the user asks about game architecture, engine selection, performance budgets, technical debt, build pipeline, cross-platform, rendering pipeline, or CI/CD for games. Triggers on: "architecture", "engine selection", "performance budget", "tech debt", "build pipeline", "cross-platform", "rendering", "CI/CD". Do NOT invoke for creative vision (use game-creative-director) or engine-specific code (use engine specialists). Part of the AlterLab GameForge collection.
Rust CLI reference for the headless-ghidra pipeline. Covers command syntax, flags, output contract, artifact paths, and workspace layout for all ghidra-agent-cli subcommands. Load when: constructing a ghidra-agent-cli command, interpreting its output, resolving a flag or artifact path question, or debugging CLI behavior. Do not load for P0–P4 workflow sequencing — use the headless-ghidra skill family instead.
Google Agent Development Kit (ADK) for Python. Capabilities: AI agent building, multi-agent systems, workflow agents (sequential/parallel/loop), tool integration (Google Search, Code Execution), Vertex AI deployment, agent evaluation, human-in-the-loop flows. Actions: build, create, deploy, evaluate, orchestrate AI agents. Keywords: Google ADK, Agent Development Kit, AI agent, multi-agent system, LlmAgent, SequentialAgent, ParallelAgent, LoopAgent, tool integration, Google Search, Code Execution, Vertex AI, Cloud Run, agent evaluation, human-in-the-loop, agent orchestration, workflow agent, hierarchical coordination. Use when: building AI agents, creating multi-agent systems, implementing workflow pipelines, integrating LLM agents with tools, deploying to Vertex AI, evaluating agent performance, implementing approval flows.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Use this skill to install, uninstall, list, inspect, and reset Android apps via `adb install` (with `-r` reinstall, `-d` allow-downgrade, `-t` allow test packages, `-g` grant all runtime permissions, `--user` per-user install, `adb install-multiple` for split APKs) and the on-device `pm` tool (`pm list packages [-f|-d|-e|-s|-3|-i|-u]`, `pm path`, `pm clear`, `pm grant` / `pm revoke`, `pm enable` / `pm disable`, `pm uninstall [-k]`, `cmd package dump-profiles`). Calls out the canonical hermetic-reset pattern (`pm clear` wipes data; `am force-stop` does NOT) and the common install errors (`INSTALL_FAILED_USER_RESTRICTED`, `INSTALL_FAILED_VERSION_DOWNGRADE`, signing-conflict). Use when the user mentions "reset app between tests", `pm clear`, `am force-stop` confusion, install fails after debugger, split APK install, runtime permission grants, multi-user profile installs, or "how do I list third-party apps".
Review Java code for bugs, duplicate code, correctness risks, maintainability improvements, and missing tests. By default review files modified in git; when the user explicitly names files, classes, packages, or a diff, review that scope instead. Generate a detailed review.md report with actionable comments and fixes.
Search and reference the official Kuroco documentation (tutorials, reference, admin panel guide, FAQ) from files bundled with the skill. Use when accurate information based on the official documentation is needed, such as how to use Kuroco features, configuration methods, specifications, troubleshooting, or checking whether something exists, e.g. "does Kuroco have this feature or material?"
Workflow for learning CuTe Python DSL by reading, importing, profiling, and extracting reusable patterns from CUTLASS Blackwell example kernels. Use when: (1) studying CUTLASS CuTe DSL reference implementations, (2) importing CUTLASS examples into the project runtime infrastructure, (3) building CuTe DSL knowledge base entries from profiling experiments, (4) understanding CuTe DSL API patterns, TMA pipelining, warpgroup scheduling, or persistent kernel structure.
Unified LLM torch-profiler triage skill for `sglang`, including existing traces from SGLang Omni workloads, plus `vllm`, `TensorRT-LLM`, and `TokenSpeed`. Use it to inspect an existing `trace.json(.gz)` or profile directory, or to drive live profiling against a running server when supported and return one three-table report with kernel, overlap-opportunity, and fuse-pattern tables.
Establish useful memory for a project that already has development history, or improve an incomplete memory setup. Survey the project and its existing evidence, then initialize or enrich human-readable StrictDoc docs/ with current norms and historical context. Use Magic Context and other available memory alongside it where useful. No previous workflow, legacy folder convention, or pre-existing StrictDoc skeleton is assumed.
Use when adding animation to a React app with the Motion library (the framer-motion successor: npm package `motion`, import `motion/react`) — enter/exit animations, variants and stagger, AnimatePresence, layout and shared-element transitions, animated number tickers, gesture states — or when deciding whether a job needs Motion at all versus plain CSS/Tailwind transitions or AutoAnimate. Covers reduced-motion accessibility (MotionConfig, useReducedMotion, WCAG 2.3.3/2.2.2) as a first-class requirement, performance discipline (transform/opacity only), motion restraint for data-dense product UI, Radix/shadcn and router integration, and keeping tests stable (MotionGlobalConfig.skipAnimations). Keywords: motion, framer-motion, animation, AnimatePresence, layout animation, micro-interactions, reduced motion, page transitions, stagger, spring.
Opinionated house conventions for NestJS backends — module boundaries and layering, provider wiring and injection scopes, guards/interceptors/pipes/filters, DTOs and validation, domain exceptions, config, and the Nest 11 / Express 5 behaviour that compiles cleanly and fails at runtime. Use whenever the code is NestJS (`@nestjs/*` in package.json, or `@Module`/`@Injectable`/`@Controller`/`@Cron` in the file), including when the question sounds like plain TypeScript, an OOP refactor, a code review, or an ops problem — the Nest-specific answer differs from the generic one. Typical asks: scaffolding a module, adding a controller, provider, or endpoint, wiring an enhancer, a boot-time DI or circular-import failure, a response leaking entity fields despite `@Exclude()`, a cron job firing on every replica, upgrading NestJS, or reviewing a Nest diff. Not for plain Express or Fastify, Angular, frontend, SQL, or CI.
Provides comprehensive guidance for NestJS using the official documentation. Use when the user asks about NestJS architecture, controllers, providers, modules, middleware, guards, pipes, interceptors, dependency injection, GraphQL, WebSockets, microservices, OpenAPI/Swagger, security, or testing.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Version-pinned inventory of the telemetry (spans, metrics, logs, attributes) emitted by OpenTelemetry collector components and SDK instrumentation packages. Use when working with a covered component — what it emits at a given version, or how emission changed across versions — and when upgrading a component or SDK version, to see the telemetry after the change.
Use when: coordinating technical solutions with the engineering team, assessing technical feasibility, defining technical architecture, evaluating third-party services. Do NOT use when: the technical solution has already been decided by the engineering team, or when only a feature description is needed without technical evaluation.
Expert guide to end-to-end Python video pipelines combining FFmpeg, OpenCV, PyAV, ffmpegcv, Decord, VidGear, and Modal.com for scalable GPU-accelerated workflows. PROACTIVELY activate for: (1) FFmpeg+OpenCV in same pipeline (decode, process, re-encode); (2) color-format mismatches (BGR vs RGB across OpenCV, PIL, PyAV, FFmpeg); (3) frame dim ordering (HWC vs CHW) between OpenCV and ML frameworks; (4) audio stream loss in filter chains; (5) memory mgmt for long/large videos (streaming vs in-memory); (6) choosing ffmpegcv/Decord/VidGear/PyAV for performance; (7) GPU decode/encode on Modal.com; (8) parallel + chunk-based processing on Modal; (9) transcoding pipelines on serverless; (10) HLS generation on Modal; (11) upload -> process -> transcode -> HLS workflows; (12) batch sizing for GPU memory, pixel formats, large-video streaming. Provides: library selection matrix, integration recipes, Modal.com deployment examples, GPU pipeline tuning, production-ready workflow examples.
Create or improve concise, useful, agent-safe repository READMEs. Use for new README drafts, rewrites, quickstarts, local setup, getting started, contributor docs, or README reviews. Do NOT use for API reference, full product docs, changelogs, or landing pages.
Execute approved implementation plans phase by phase with automated and manual verification. Use when the user explicitly says "implement the plan", "execute the plan", or "start implementing" and has a plan file ready. Do not use for ad-hoc coding tasks without a plan.
This skill MUST be used for semantic Rust navigation and analysis: resolving definitions across crate boundaries, finding all references to a symbol, inspecting inferred types or trait implementations, searching symbols by name, and renaming symbols safely. SHOULD be preferred over grep or file reads whenever the task requires Rust-aware understanding.
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.