Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Autonomous loop that works through docs/STORIES.md one story at a time for a macOS app, building, snapshotting, comparing against reference screenshots, fixing, and committing, until a milestone is done. Use when the user says "keep going", "work through the backlog", "make it match the reference", or wants an unattended improvement loop.
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
Comprehensive guidelines for Obsidian.md plugin development including ESLint rules from eslint-plugin-obsidianmd v0.4.2, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, popout window compatibility, community.obsidian.md submission process, and Scorecard optimization. Use when working with Obsidian plugins, main.ts files, manifest.json, Plugin class, MarkdownView, TFile, vault operations, or any Obsidian API development.
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
Prioritized backlog of user stories with checkable acceptance criteria (docs/STORIES.md) for a macOS app, built from a brief, research, or screen index. Use after app-brief or clone, or when the user asks for user stories, a backlog, a feature list, or "what do we build first".
Reverse-engineer a SPEC document from an existing project. Analyzes code, config, tests, and structure to produce a comprehensive specification. Triggers on: code-to-spec, reverse spec, generate spec, 逆向规格, 生成规格文档, 生成设计文档, 生成设计方案, extract spec, document this project, what does this project do.
User guide for the local squash-safe `stack` CLI for stacked PR/MR repair on GitHub and GitLab. Use when someone asks how to inspect, track, sync, merge, document, or undo stacked pull requests / merge requests in squash-merge repositories. Prefer this tool over GitHub's `gh stack` command for this workflow.
Analyze a native mobile app's design system (colors, fonts, corner radii, margins, light/dark) and generate code that themes the Sumsub Mobile SDK to match it — Swift (SNSTheme subclass) on iOS, Kotlin (SNSTheme DSL) on Android. Use this whenever the user wants the Sumsub verification / KYC screens to match their app's look — "theme / brand / style the Sumsub SDK", "make the verification screen match my app", "match my KYC flow colors and fonts", "customize SNSMobileSDK appearance" — including when they don't say "theme" but ask to align the SDK's colors / fonts with their app. Detects the platform from the project (iOS Xcode/Swift vs Android Gradle/Kotlin). Scans for design tokens (iOS — asset-catalog `.colorset`, `Color`/`UIColor` & `Font` extensions, accent / tint; Android — `colors.xml` / `themes.xml` / `values-night`, Compose `ColorScheme` / `Typography`), derives a full palette, and writes the theme file. SKIP for theming the host app itself (this only styles the Sumsub SDK), web theming, and the SDK integration / setup (use `sumsub-integrate-msdk`).
Implements and debugs browser Web Neural Network API integrations in JavaScript or TypeScript web apps. Use when adding navigator.ml checks, MLContext creation, MLGraphBuilder flows, device selection, tensor dispatch and readback, or explicit fallback paths to ONNX Runtime Web or other local runtimes. Don't use for model training, server-side ML inference, or cloud AI APIs.
Optional command line and MCP server for a macOS app, so Claude Code, Codex, and scripts can drive it (list, add, change, search, act) through the running app. Use when the user wants agents to work with their app or its data, asks for a CLI, an MCP server, or automation for the app, or says "Claude should be able to use my app".
You are a documentation expert specializing in creating comprehensive, maintainable documentation from code. Generate API docs, architecture diagrams, user guides, and technical references using AI-powered analysis and industry best practices.
EIDE (Embedded IDE) project build tool for scanning .eide/eide.yml projects, listing build configurations (ConfigName), running build/rebuild/clean, and parsing build logs. Returns artifact paths that can be reused by jlink/openocd. Triggers automatically when users mention EIDE, Embedded IDE, eide.yml, unify_builder, the VS Code EIDE extension, or Cl.eide; also supports explicit /eide calls. Trigger this skill whenever the context involves an EIDE embedded project, even if the user only says "compile with EIDE" or "flash the board with EIDE".
Guides developers using Fusion Framework feature flags with MCP-backed framework retrieval first and bundled public-source fallback assets when MCP is unavailable. USE FOR: helping with `enableFeatureFlag`, `enableFeatureFlagging`, `useFeature`, rollout/cleanup guidance, and finding Fusion Framework feature-flag examples. DO NOT USE FOR: generic SaaS flag platforms, backend-only rollout systems, or inventing framework APIs.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
Upgrade React Spectrum v3 (Spectrum 1) codebases to React Spectrum S2. Use when developers mention migrating or upgrading from React Spectrum v3, Spectrum 1, S1, @adobe/react-spectrum, @react-spectrum/* packages, or codemod-assisted upgrades to @react-spectrum/s2.
Configure and operate a monorepo with Turborepo and pnpm. Covers separating apps and packages, internal dependencies via workspace:*, shared tsconfig, responsibility-focused packages, turbo.json task definitions and caching, generating package.json with pnpm commands, and incorporating non-JavaScript projects such as Cargo or Go. Use when adding packages, editing turbo.json, pnpm-workspace.yaml, or tsconfig, or changing the apps or packages structure.
Run an iterative code-improvement hill climb locally against real Datadog LLM-Obs data, with Claude Code as the agent. Establishes a baseline evaluation, makes one focused change, re-scores with the same harness, keeps the change if it improves the score toward the goal (labeling gains within noise as tentative), and repeats. Use when the user says "run an auto experiment", "hill-climb this code", "iteratively improve X and measure the delta", "optimize this prompt/file against my traces", "auto-optimize against LLM-Obs", or wants the local equivalent of the auto_experiments worker. Works from an ml_app, a dataset_id, an annotation_queue_id (a queue of human-labeled interactions), a list of trace_ids, or (by exception) a local dataset file. The corpus and its validation/test splits live in Datadog LLM-Obs Datasets, created once per run with timestamps in their names
Expert patterns for input handling covering InputMap actions, InputEvent processing, controller support, rebinding, deadzones, and input buffering. Use when setting up player controls, implementing input systems, or adding gamepad/accessibility features. Keywords InputMap, InputEvent, gamepad, controller, rebinding, deadzone, input buffer.
Add PostHog AI Observability to trace AI model usage. Use after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. Also handles initial PostHog SDK setup if not yet installed.
Online research for a macOS app before building it, run as parallel researcher subagents, saved to docs/research/. Use when the user asks what to build, which features matter, how the best apps in a category work, how a macOS API or integration works, or wants a feature comparison.
Create comprehensive HTML architecture diagrams showing data flows, business objectives, features, technical architecture, and deployment. Use when users request system architecture, project documentation, high-level overviews, or technical specifications.
Compose and Compose Multiplatform expert for UI development across Android, Desktop, iOS, and Web. Use whenever the user mentions Compose APIs (@Composable, remember, LaunchedEffect, NavHost, MaterialTheme, LazyColumn, Modifier, recomposition), Compose Multiplatform (commonMain, expect/actual, Res.*, ComposeUIViewController, UIKitView, ComposeViewport), Android TV (tv-material, D-pad, focus, Carousel), Material 3 motion, atomic design systems, design-to-code workflows, Paging 3, or navigation. Activates Review Mode on GitHub PR URLs and review phrases ("review this PR", "what's wrong with this"). Auto-detects Compose projects on session_start. Backed by actual androidx/androidx and JetBrains/compose-multiplatform-core source receipts. See "## When this skill applies" in SKILL.md for the full trigger surface.
Guides setup, development, and troubleshooting of the Next.js and Enonic XP headless integration (Next.XP framework). Covers Enonic adapter configuration, content type to React component mapping, Guillotine GraphQL data fetching, Content Studio preview mode, and draft/master branch switching. Use when building a Next.js frontend powered by Enonic XP, configuring the Next.XP adapter, mapping content types to components, fetching Enonic content via Guillotine in Next.js, or debugging Content Studio preview. Don't use for traditional server-side Enonic XP rendering, standalone Guillotine queries without Next.js, non-Next.js frontend frameworks with Enonic, or React4XP embedded rendering
Use when adding, retiring, or auditing feature flags. Triggers on "add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag debt", "LaunchDarkly", "GrowthBook", "Statsig", "Unleash", "Flipt", or any progressive-delivery question. Ships flag debt scanner, rollout planner, and kill-switch auditor (all stdlib Python), 4 references on flag taxonomy + provider trade-offs + rollout strategies + lifecycle, plus a /flag-cleanup slash command.
Build websites and web apps using 21st.dev — the largest marketplace of shadcn/ui-based React Tailwind components with 1400+ components. Use when user mentions "21st.dev", "21st", "ใช้ 21st", "จาก 21st", "build with 21st", "21st component", "21st magic MCP", or references the 21st.dev component registry in any language. Covers building complete sites (landing pages, dashboards, portfolios, e-commerce storefronts, auth pages), browsing and installing individual 21st.dev components into existing projects, and setting up the 21st.dev MCP server. Also trigger when user wants premium UI components specifically from the 21st.dev registry. Do NOT trigger for general web development, standard shadcn/ui, plain Tailwind CSS, React Native, API development, testing, deployment, or any task that doesn't explicitly reference 21st or 21st.dev.
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
Migrate Python SDK to Sentry span streaming (span-first trace lifecycle). Use when asked to "enable span streaming", "migrate to span streaming", "use trace_lifecycle stream", or switch from transaction-based to streamed span delivery in a Python project.
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.