Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Automatically generates a personal weekly report from Git commit history and code changes. Use this skill when the user asks to generate a weekly report, summarize work, or compile this week’s work. Supports custom date ranges, author filters, output formats, and levels of detail.
Integrates Power Pages generative-AI summarization APIs (PREVIEW) into a Single Page Application (SPA) site — the Search Summary API and the Data Summarization API — on any record-detail or list page. Generates per-target service code (CSRF-handled) and AI site settings; delegates Web API settings, table permissions, and web roles to `/integrate-webapi` and `/create-webroles`. Use whenever a user wants AI/Copilot output that condenses Dataverse content on a Power Pages site — an AI summary, AI-generated overview or "key insights" across a record or list, a search-results summary, a case/incident summary, or recommendation-chip refinement — even when phrased as "AI-generated paragraph", "insights", or "overview". Do NOT use for: generative pages in model-driven apps (use the model-apps `genpage` skill), Copilot Studio agents/chatbots, summarizing documents or PDFs, Power BI dashboards, plain keyword search with no AI summary, or plain Dataverse CRUD (use `/integrate-webapi`).
Mandatory for all Gemeente Amsterdam UI work. Use for pages, layouts, forms, dashboards, landing pages, React/JSX/TSX components, styling, theming, scaffolding frontend projects, or any visual interface. Covers @amsterdam/design-system-react, CSS tokens (--ams-*), BEM CSS with ams- prefixes, 4/8/12-column Grid, Spacious and Compact modes, and Tailwind CSS bridge patterns. Prefer this over generic UI libraries such as Material UI, shadcn, Chakra, Ant Design, or plain custom HTML/CSS.
Use when implementing the data layer in Android or KMP — the Repository pattern's layered error-propagation model (repository as the error boundary, sealed DataError, Result placement with and without a domain layer) and Room in commonMain (@ConstructedBy, BundledSQLiteDriver, per-target KSP).
Ark UI headless / unstyled component library. Based on Zag.js, with Chakra UI v3 as its foundation. Supports React / Solid / Vue / Svelte. asChild, RootProvider, createListCollection, createTreeCollection, Presence hideMode, useHotkey / useHotkeys, data-* selectors. Component APIs for Navigation Menu, TOC, Tour, Signature Pad, Image Cropper, Floating Panel, Angle Slider, and more.
Debug and find the root cause of AscendC operator precision issues. Use when an operator fails precision tests (allclose fails, results are off, output is all zeros/NaN, etc.). Workflow: analyze error distribution → review error-prone code → isolate experiments → instrument with printf/DumpTensor → verify the fix. Keywords: precision debugging, precision issues, inconsistent results, error localization, allclose failure, output deviation, NaN, all zeros, precision debug.
Organize git changes into clean, atomic commits for better history. Use when the user has accumulated multiple changes and wants to split them into separate, logical commits. Triggers on “atomic commits”, “split commits”, “organize my changes”, “clean commit history”, or when many unrelated changes are staged together.
Expert knowledge for Azure AI Immersive Reader development including best practices, limits & quotas, security, configuration, and integrations & coding patterns. Use when tuning read-aloud/translation, storing user prefs, Entra auth setup, JS SDK integration, or language support, and other Azure AI Immersive Reader related development tasks. Not for Azure AI Language (use azure-language-service), Azure AI Speech (use azure-speech), Azure Translator (use azure-translator), Azure AI services (use microsoft-foundry-tools)
Generates Draw.io diagrams based on the current project or code. Supports four types: technology stack, system architecture, data structure, and E-R diagrams. Outputs a .drawio file in Draw.io syntax (mxGraph XML) that can be imported directly into Draw.io for editing. Use when the user mentions a technology stack, system architecture, data structure, or E-R diagram
Generate HumanSignal Interfaces for Label Studio Enterprise: single-file JSX annotation screens that run in the sandboxed editor-shell iframe. Use when the user asks for a labeling UI, annotation screen, Document AI interface, data review workflow, or conversion of a React/Claude Design mockup into a Label Studio interface.
Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or any server that Claude should interact with via the MCP protocol. Supports both TypeScript and Python implementations.
Cron and scheduled task management. node-cron, cron expressions, Spring @Scheduled, APScheduler (Python), and distributed scheduling patterns. USE WHEN: user mentions "cron", "scheduled task", "cron job", "node-cron", "@Scheduled", "APScheduler", "periodic task", "crontab" DO NOT USE FOR: job queues with workers - use `job-queues`; one-off delayed tasks - use `job-queues`
Explains DeepBook V3 on Sui: the central limit order book (CLOB) design, how a Pool is built from Book, State, and Vault, the DEEP token's role in fees, staking and governance, the three integration models, and mainnet package and pool IDs. Use when the user asks what DeepBook is or how it compares to an AMM like Uniswap, asks about DeepBook Pool internals, BigVector, or order matching, asks whether to integrate via Move package, TypeScript SDK, or read-only queries, asks about DEEP fees, staking, whitelisted pools, or voting, or needs a DeepBook mainnet package ID, pool object ID, coin type, or fee tier.
DeepBook V3 TypeScript SDK integration. Use when building trading applications, bots, or scripts that interact with DeepBook pools using the @mysten/deepbook-v3 SDK. Covers client setup, BalanceManager lifecycle, placing limit and market orders, swaps, querying order books, order management, and fee handling. For DeepBook architecture and contract addresses, see the `deepbook-overview` skill. For Move smart contract integration, see the `deepbook-move` skill.
Comprehensive dependency health auditing for JavaScript/TypeScript projects. Run npm audit, detect outdated packages, check for security advisories, and verify license compliance. Prioritises vulnerabilities by severity and provides actionable fix recommendations. Use when: auditing project dependencies, checking for vulnerabilities, updating packages, preparing for release, or investigating "npm audit" warnings. Keywords: audit, vulnerabilities, outdated, security, npm audit, pnpm audit, CVE, GHSA, license.
Use when turning a requirement, spec, or feature brief into a single self-contained HTML design document in a fixed house style — one styled HTML page with a table-of-contents, architecture/sequence SVG diagrams, code/SQL/YAML blocks, callout boxes, an aligned-decisions (已对齐结论) panel, test cases, and a code index. Reuse for any new 需求/设计文档 that should look identical every time.
Make direct GitLab REST API calls for advanced queries and operations not covered by other glab commands. Use when accessing GitLab API endpoints directly, making custom API requests, or fetching data in JSON format. Triggers on API call, REST API, GitLab API, JSON query, advanced query.
Use when auditing or recalibrating game balance: build a source-driven Monte Carlo balance lab (Rust + rayon) that extracts live game data, simulates human playstyles (AFK→pro), emits win-rate/economy verdicts with confidence intervals, and bruteforce-tunes parameters. Trigger on unfair levels, unreachable shops, farm exploits, interest-curve cliffs, post-content recalibration, or CI balance JSON diffs. Keywords: balance lab, Monte Carlo, win rate, difficulty curve, economy career, playstyle simulation, Resource extraction, GDScript parser, bruteforce tuning.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
When the user wants to build GTM automation with code, design workflow architectures, use AI agents for GTM tasks, or implement the 'architecture over tools' principle. Also use when the user mentions 'GTM engineering,' 'GTM automation,' 'n8n,' 'Make,' 'Zapier,' 'workflow automation,' 'Clay API,' 'instruction stacks,' 'AI agents for GTM,' or 'revenue automation.' This skill covers technical GTM infrastructure from workflow design through agent orchestration. Do NOT use for technical implementation, code review, or software architecture.
Analyze candidate models before adapter implementation. Determine model implementation source (transformers or model-local), structural features, layer-by-layer loading requirements, and MoE fused weight risks. Use this skill when the user wants to: (1) assess model adaptation feasibility before creating msModelSlim adapters, (2) analyze model structure and type classification, (3) evaluate MoE compatibility for quantization. Trigger: user mentions "model analysis", "msModelSlim", "adapter", "transformers", "MoE", "layer-by-layer", "model assessment", "feasibility", "模型分析", "适配可行性", "模型评估", "MoE分析"
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
Refresh durable AI context for a Cargo WORKSPACE or package monorepo: a self-contained `CLAUDE.md` per member that Claude lazy-loads, plus a thin project-wide root, so changes in any member have local guidance without bloating the root. Discover each member's actual reachable surface, key files, wiring, and inter-member dependencies, then keep the root project-wide. A user-only maintenance workflow that mutates durable memory across members: it documents the actual exported/reachable surface (not raw `pub`/`export` counts), grounds every claim in code, and preserves locked root decisions. Use to refresh workspace-local context after refactors, member additions, or export changes.
Creates MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Activates on: “build an MCP server”, “create MCP tools”, “integrate API via MCP”, “write a FastMCP server”, “add an MCP server to an agent”, or any request to wrap an external API as LLM-callable tools in Python or Node/TypeScript.
Manual image asset optimization for Phaser 4 projects. Use only when the user explicitly invokes $phaser4-game-image-optimization. Inventory runtime bitmaps, generate compression candidates, verify image quality and channel compatibility, and replace assets under the current Work Item, task scope, path, and evidence controls. Side-effecting A4–A6 operations require separate approval.
Build n8n workflows using the Pinecone Assistant node or Pinecone Vector Store node. Use when building RAG pipelines, chat-with-docs workflows, configuring Pinecone nodes in n8n, troubleshooting Pinecone n8n nodes, or asking about best practices for Pinecone in n8n
Process substitution, named pipes (FIFOs), and advanced IPC patterns for efficient Bash data streaming (2025). Proactively activate for: (1) using process substitution with <(cmd) and >(cmd), (2) creating named pipes (mkfifo) for inter-process streaming, (3) avoiding intermediate temp files in pipelines, (4) tee-ing into multiple consumers, (5) feeding diff/comm with command output, (6) building shell-only producers and consumers, (7) reading from a FIFO with a timeout, and (8) signal-safe FIFO cleanup. Provides process substitution patterns, mkfifo recipes, multi-consumer tee patterns, and signal-safe cleanup with trap
Sharp-tongued product manager skill pack for gathering requirements, writing product documentation, and iterative updates. Key features: rejects vague answers, points out problems directly, pushes users to think things through, provides AI-enhanced suggestions, and detects conflicts.
Scan workspace repositories for cleanup opportunities using a read-only hygiene audit. Use when users ask to detect build/cache artifact buildup, stale large transient files, and prioritized cleanup chores by repository and directory.
Runs the forward-only Drift/SQLite schema-migration ritual — the most dangerous deterministic operation in an offline-first app: a bad migration silently destroys on-device rows that exist nowhere else. Enforces the exact ordered sequence: take a pre-migration file snapshot before the database is opened, bump schemaVersion by exactly one, write an append-only stepByStep forward step (never edit a shipped step, never write a down migration), commit the drift_dev make-migrations schema snapshot, regenerate, then prove it with tests covering every from→to path (incl. multi-version jumps), a write-at-v(n)/read-at-v(n+1) content test, PRAGMA integrity_check + foreign_key_check, and a forced mid-migration throw that restores the snapshot. Manual, side-effecting workflow. Use when adding or altering a Drift table, column, index, or CHECK; bumping schemaVersion; editing onUpgrade/stepByStep; or writing migration tests.
Use when an application should send image, video, or audio generation through a saved Runway Model Router configuration, or when the user asks to inspect or manage one. Resolve the live config and follow current router docs. For a fixed direct model endpoint, use runway-dev-models instead.
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.
Use when the user is configuring or extending tax in Spree 6 — tax categories (`tax_code`), tax rates by `country_code`/`state_code`, VAT-inclusive vs added-on pricing (`included_in_price`, market `tax_inclusive`), per-market tax providers and `Spree.default_tax_provider`, writing a custom tax provider (`estimate`/`commit`/`void`/`refund`), `Spree::TaxLine` rows, the `carts.recalculate_totals.set_tax_line_context` hook, B2B tax identifiers (VAT numbers) and exemption certificates, or connecting Avalara/an external tax engine. Common phrasings include "tax not calculated", "tax is zero", "VAT included in price", "EU VAT", "US sales tax", "tax per state", "integrate Avalara / TaxJar / Stripe Tax", "custom tax calculation", "tax exempt customer", "reverse charge", "VAT number at checkout", "tax on shipping", "tax on fees"
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.