Top Agent Skills

Pattern for separating repository code from user data and notebooks. Trigger: organizing scientific pipelines, separating code from data

Scale alignment for RNA-protein cross-modal integration - BOTH modalities must be z-scored

GPU-aware PPO training configuration for A100/H100. Trigger when training is slow or GPU utilization is low.

CPI/GDP/retail sales date awareness and VIX regime scaling for calendar features

Cache yfinance sector data permanently to avoid Yahoo Finance rate limits. Trigger when: (1) 401 errors during sector fetching, (2) sector updates take too long, (3) need selective sector refresh.

Patterns for H5AD-backed Shiny apps with Excel fallback, groovy data in .uns, scVI QC validation, Leiden clustering merge, per-donor tissue extraction

Notebook Cell References

Migrate improperly structured plugins to correct .claude-plugin/ layout

Integrates Mem0 Platform SDK for persistent memory in AI applications. Use when building agents or chatbots that need to remember user preferences, past interactions, or personalized context across sessions. Covers Python and TypeScript SDKs, plus LangChain, CrewAI, OpenAI Agents, LlamaIndex, AutoGen, and LangGraph integrations.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.

AI-optimized web search using the Tavily API for current events, domain-filtered research, answer summaries, and raw content extraction. Use when live web research needs cleaner LLM-ready results than generic search.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Comprehensive guide for Manim Community - Python framework for creating mathematical animations and educational videos with programmatic control

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Bagman

Helps users discover and install agent skills from the open ecosystem. Use when the user asks "how do I do X", "find a skill for X", "is there a skill that can...", or expresses interest in extending Claude's capabilities with a new skill or tool.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Comprehensive Polymarket skill covering prediction markets, API, trading, market data, and real-time WebSocket data streaming. Build applications with Polymarket services, monitor live trades, and integrate market predictions.

Write persuasive marketing copy including landing pages, product descriptions, email campaigns, CTAs, taglines, and brand messaging. Use when writing to persuade, convert, or sell rather than inform. Also trigger for 'landing page copy', 'product description', 'marketing copy', 'email campaign', 'CTA', 'tagline', 'ad copy', 'sales page', or 'conversion copy'.

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

Write end-user documentation including tutorials, how-to guides, walkthroughs, onboarding flows, and feature documentation. Use when creating documentation for non-technical or semi-technical end users. Also trigger for 'user guide', 'tutorial', 'how-to', 'walkthrough', 'onboarding docs', 'help article', 'user manual', or 'getting started guide'.

Brainstorm and develop game concepts, exploring genres, themes, target audiences, and unique selling points. Use when starting a new game project from scratch or pivoting an existing idea. Also trigger for "game idea", "what kind of game", "I want to make a game", "game pitch", or "explore game concepts".

Design game user interfaces and user experience flows including HUD, menus, inventory screens, accessibility, and player feedback systems. Use when designing how the player interacts with game systems visually. Also trigger for "game UI", "game UX", "HUD design", "menu design", "inventory UI", "game accessibility", or "game interface".

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

Recommend model families and validation strategy based on data, constraints, and objective. Use when: (1) choosing algorithms, (2) balancing bias/variance, (3) planning benchmark baselines. NOT for: final legal/compliance sign-off.

Define the visual identity of a game including art style, color palettes, character design language, environment aesthetics, and asset pipelines. Use when establishing the look and feel of a game project. Also trigger for "art style", "visual style", "game aesthetics", "color palette", "character art", "pixel art", or "game graphics".

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Create professional, visually polished GitHub README files with badges, diagrams, structured sections, and modern markdown design patterns. Use when creating or redesigning a repo's README for maximum GitHub impact.

Write release notes, changelogs, migration guides, deprecation notices, and version announcements that communicate changes clearly to users and developers. Use when shipping a new version, deprecating features, or guiding users through breaking changes. Also trigger for 'release notes', 'changelog', 'migration guide', 'breaking changes', 'deprecation notice', 'version update', 'what's new', or 'upgrade guide'.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Design in-game economies including currencies, progression systems, loot tables, monetization, and resource flow. Use when building the economic backbone of a game. Also trigger for "game economy", "loot table", "drop rates", "currency system", "progression design", "monetization strategy", or "reward system".

Design telemetry systems, define KPIs, analyze player behavior data, and set up dashboards for data-driven game design decisions. Use when instrumenting a game for analytics or interpreting player data. Also trigger for "game telemetry", "player analytics", "game metrics", "KPIs", "player retention", "funnel analysis", or "player behavior".

Balance game systems including difficulty curves, stat tuning, economy rates, matchmaking fairness, and player power progression. Use when tuning numbers and systems for fair, engaging gameplay. Also trigger for "game balance", "difficulty tuning", "stat balancing", "nerf", "buff", "power curve", or "difficulty curve".

Build and organize knowledge bases, help centers, FAQ systems, and troubleshooting guides optimized for self-service support and search. Use when creating a structured support documentation system. Also trigger for 'knowledge base', 'help center', 'FAQ', 'troubleshooting guide', 'support docs', 'self-service support', 'help article', or 'support article'.

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

Write business reports including executive summaries, status updates, postmortems, competitive analyses, data analyses, and quarterly reviews. Use when communicating findings, decisions, or status to stakeholders. Also trigger for 'executive summary', 'status report', 'postmortem', 'incident report', 'competitive analysis', 'quarterly review', 'business report', or 'data analysis report'.

Kalshi prediction market data (prices, odds, orderbooks, trades). Use for prediction markets, Kalshi, betting odds, election and sports betting, market forecasts. Provides real-time market data, event series information, and comprehensive trading analytics.

Sports betting fundamentals including spreads, moneylines, totals, parlays, teasers, props, and futures. Use when analyzing sports betting markets, converting odds formats, evaluating bet types, or building a sports betting strategy. Also trigger for 'point spread', 'moneyline', 'over under', 'parlay', 'prop bet', 'teaser', 'sports odds', or 'sportsbook'.

Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.

A technical writer who crafts clear, comprehensive documentation. Specializes in README files, API docs, architecture docs, and user guides.

Loads an implementation plan, executes tasks in batches with verification, and reports progress for review between batches.

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process: (1) create section outlines with key points using research-lookup, (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

Plan and execute rapid game prototypes to validate mechanics, test assumptions, and find the fun before committing to full production. Use when building playable proofs-of-concept. Also trigger for "prototype", "game jam", "proof of concept", "find the fun", "playable demo", or "rapid prototype".

Design and document core game mechanics, systems interactions, feedback loops, and emergent behavior. Use when defining how the game plays at a systems level. Also trigger for "game mechanics", "gameplay systems", "game loop", "game rules", "combat system", "crafting system", or "progression system".

Produce low/mid-fidelity wireframe specifications and annotations for handoff. Use when: (1) early concepting, (2) comparing layout options, (3) PM/engineering alignment. NOT for: high-fidelity branding work.

Understand and trade futures contracts on commodities, indices, crypto, and event outcomes. Covers contract mechanics, margin, settlement, spreads, and risk. Use when analyzing futures markets, understanding contract specs, evaluating margin requirements, or building futures strategies. Also trigger for 'futures contract', 'commodities trading', 'futures margin', 'contract specs', 'futures spread', 'oil futures', 'crypto futures', or 'index futures'.

Use when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist.

Design leakage-safe feature engineering strategies for tabular/time-series datasets. Use when: (1) preparing model-ready features, (2) selecting transformations and encodings, (3) documenting feature lineage. NOT for: model serving or infra provisioning.

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

Autonomously runs iterative experiment loops to optimize code against a measurable metric. Use when the user wants to improve execution time, memory usage, test pass rate, or any numeric performance goal across repeated experiments — NOT for one-shot bug fixes or simple code review.

Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

Technical writing proficiency covering clarity principles, audience analysis, information structure, editing techniques, and style enforcement. Use when writing or improving any technical content — docs, specs, guides, or explanations. Also trigger for 'technical writing', 'write clearly', 'simplify this', 'rewrite for clarity', 'plain language', 'writing style', or 'editing pass'.

Design multiplayer systems including networking architecture, matchmaking, social features, anti-cheat, and multiplayer game modes. Use when adding online or local multiplayer to a game. Also trigger for "multiplayer", "online play", "co-op design", "PvP design", "matchmaking", "netcode", or "multiplayer architecture".