Manage solution outline documents - standards, examples, validation, and deliverable extraction

**Autonomously create** filters, throttles, and classification rules to implement new workloads or manage workload lifecycle in response to changing operational needs

Advanced middleware logic for security and routing. Use for global rate limiting, security headers, and protection of admin routes.

Handles backend logic that cannot run in the browser. Use for sensitive tasks like price calculation, cleanup, or payment verification.

Handles the authentication flow including Login, Signup, OAuth, and Password Recovery. Use when building auth pages or logic.

Use this skill when working with UFC fighter images including downloading from multiple sources (Wikimedia, Sherdog, Bing), detecting and replacing placeholder images, handling duplicates, normalizing image sizes, validating image quality, syncing filesystem to database, or running the complete image pipeline. Handles missing images, batch downloads, and multi-source orchestration.

Configures GitHub Actions workflows and CI/CD pipelines. Manages automated releases via Changesets, PR validation, and Husky hooks. Troubleshoots CI failures. Triggers on: GitHub Actions, CI pipeline, workflow, release automation, Husky hooks, gh CLI, workflow failure.

Comprehensive prompt engineering for Claude 4.5: creation, analysis, optimization, guardrails, context management.

Managing session continuity across Claude conversations by saving structured context (tasks, files, errors, git state) to JSON and loading in new sessions. Use when user asks how session continuity works, explaining session protocol functionality, understanding session state management, describing what gets saved in sessions, ending a session with unfinished work, starting a session with existing session-protocol.json, or when user mentions 'save progress', 'save session', 'save my work', 'continue later', 'session context', 'pick up where left off', 'load session', 'restore session', or explicitly invokes /save-session-protocol or /load-session-protocol commands.

This skill helps maintain tag hygiene by finding inconsistencies and consolidating similar tags.

marimo-notebooks

Sync markdown projects to Confluence using the markdown_confluence tool. Use for publishing, crawling, and managing Confluence pages from local markdown files.

Converts documents to markdown (PDFs, Word docs, PowerPoint, Confluence exports) with Windows/WSL path handling. Activates when converting .doc/.docx/PDF/PPTX files to markdown, processing Confluence exports, handling Windows/WSL path conversions, extracting images from PDFs, or working with markitdown utility.

Atlas Simulator scan flow and next-step guidance for markdowntown. Use when working on folder scanning, tool detection, cwd handling, results panels, or scan-to-workbench CTAs.

Master TAM/SAM/SOM calculations, market sizing methodologies, and validation frameworks. Use when assessing market opportunity, validating business viability, planning market entry, estimating revenue potential, or determining if a market is worth pursuing. Covers bottom-up, top-down, and value theory sizing methods, competitive analysis, and systematic validation approaches.

This skill should be used when starting the work day for marketing and PR work, planning content production, managing campaigns, organizing media relations, or coordinating multi-platform content distribution. Use it for daily content planning, automated content creation with agents, campaign coordination, and productivity reporting. Integrates with Linear MCP and other marketing skills (brand-voice-guardian, twitter-thread-creator, media-outreach-coordinator, multi-brand-manager, launch-campaign-orchestrator).

Create HTML diagrams for Marp slides and capture them as PNG screenshots using Playwright MCP

This skill should be used when Claude Code needs to perform basic arithmetic calculations. It provides a Python script that safely evaluates mathematical expressions including addition, subtraction, multiplication, division, exponentiation, and square roots.

Implement comprehensive mathematical theorem proving capabilities with SFT+GRPO training, MCP/A2A agent integration, and imatrix quantization protection to surpass Boreas-phi3.5-instinct-jp in formal proof generation and scientific discovery. Use when building mathematical reasoning systems, formal verification tools, or AI-assisted theorem proving environments.

Build MCP Apps - interactive UI components that render inside AI hosts like Claude, ChatGPT, and VSCode. This skill should be used when creating tools with rich UI, building dashboards or forms for AI interactions, or adding visual interfaces to MCP servers.

Connect to any MCP server without bloating context with tool definitions.

Execute complex multi-tool MCP workflows directly using TypeScript or Python. As the MCP executor agent, you have MCP servers configured and write code that composes multiple tool calls. Use for 3+ MCP tool calls, complex data processing, parallel operations, or retry logic. This skill is colony-aware - you execute code directly via Bash without subagents.

This skill provides guidance for using Firecrawl MCP for web scraping and content extraction. Use when scraping web pages, crawling websites, searching the web with content extraction, mapping site URLs, or extracting structured data from web pages.

Deep code intelligence via Narsil MCP providing 76 tools for security scanning (OWASP, CWE, taint analysis), call graph analysis (CFG, DFG, callers/callees), structural queries (symbols, definitions, references), and supply chain security (SBOM, license compliance). Accessed via Code Mode for token efficiency.

Automatically invoke MCP opportunity discovery and publication pipeline when discussing marketplace opportunities, automation tools, or MCP server development

Prevent massive MCP responses from WordPress, Playwright, Notion, and other MCPs that can kill conversations on first call. Sophisticated token management for all MCP tool usage.

Convert MCP servers to typed TypeScript APIs for efficient code execution. Reduces token usage by 98%+ by transforming tool calls into programmatic access. Use when building agents that need to interact with multiple MCP servers efficiently, when context window is a concern, or when native control flow (loops, conditionals) would simplify multi-step workflows.

Convert markdown files to Jupyter notebooks (.ipynb). Splits markdown by `---` delimiters into cells, extracts code blocks (```python```, ```sql```) as code cells, and handles YAML front matter removal. Use when converting documentation, tutorials, or structured markdown into interactive Jupyter notebooks.

Performs mean-variance portfolio optimization to find the tangency portfolio. This skill should be used when users want to calculate optimal portfolio weights, the tangency portfolio, or perform mean-variance optimization with multiple assets. The skill interactively collects expected returns, standard deviations, correlations, and the risk-free rate, then computes and explains the tangency portfolio that maximizes the Sharpe ratio.

Analyze relationships across multiple SAE features - co-activation patterns, shared drivers, and subsystem identification

Convert experiment results to Markdown research notes and optionally update research state with evidence

Produce and assemble multimedia assets (images, videos, and graphics) to communicate pilot findings and narratives. Use when creating visuals, video explainers, infographics, or media-rich presentations for stakeholders and leadership.

通用自媒体文章自动发布工具。支持百家号、搜狐号、知乎三个平台的自动化发布流程。使用Playwright MCP工具实现平台导航和发布页面进入，支持通过storageState管理Cookie实现账号切换。当用户需要发布文章到自媒体平台、打开平台发布页面、切换自媒体账号时使用此skill。工作流程：1)检查并打开指定平台 2)验证登录状态 3)自动关闭广告弹窗 4)导航到发布文章页面 5)收集发布信息 6)自动填写并发布。

Summarize meetings into clear, actionable notes with decisions and next steps

Use when extracting product signals from meeting transcripts - systematically identifies asks, problems, quotes, and evidence across time windows with customer attribution

member-experience

meme-pumper

Use this skill to verify whether restaurants actually have Planted products on their current menu. Crawls restaurant websites, parses PDF menus, and updates venue verification status in Firestore.

Expert guidance for creating syntactically correct Mermaid diagrams. Use when creating flowcharts, sequence diagrams, class diagrams, state diagrams, Gantt charts, ER diagrams, or data lineage visualizations.

Fix and validate Mermaid diagrams using mermaid-cli (mmdc). Use when Claude needs to fix parsing errors in Mermaid diagrams, validate diagrams, or when encountering Mermaid syntax issues. This skill reads rules from .claude/rules/mermaid.md and updates it with newly discovered patterns.

World-class creation of valid, beautiful, and accessible Mermaid diagrams. Use when users request diagrams, flowcharts, sequence diagrams, entity relationship diagrams, state machines, Gantt charts, class diagrams, or any visual representation that can be expressed in Mermaid syntax. Handles all Mermaid diagram types with expert knowledge of syntax, styling, and best practices.

Create diagrams and visualizations using Mermaid.js v11 syntax. Use when generating flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines, architecture diagrams, or any of 24+ diagram types. Supports JavaScript API integration, CLI rendering to SVG/PNG/PDF, theming, configuration, and accessibility features. Essential for documentation, technical diagrams, project planning, system architecture, and visual communication.

Extracts web content and performs reliable searches when standard tools fail due to access restrictions, rate limiting, or validation errors. Use when encountering 403/429/422 errors, blocked documentation sites, or silent search failures. **Direct tool execution often fails for these scenarios - search-plus agent delegation provides the most reliable results.**

Calculates pathway activity scores for metabolic pathways across different cell groups and subsets. This process quantifies the metabolic activity of each pathway per group, generating visualizations (heatmaps and violin plots) to compare metabolic states between clusters or conditions. Based on the methodology from Xiao et al.

Write Metal/MPS kernels for PyTorch operators. Use when adding MPS device support to operators, implementing Metal shaders, or porting CUDA kernels to Apple Silicon. Covers native_functions.yaml dispatch, host-side operators, and Metal kernel implementation.

Metaxy is a metadata layer for multi-modal Data and ML pipelines that manages and tracks feature versions, dependencies, and data lineage across complex computational graphs.

End-to-end bisulfite sequencing workflow from FASTQ to differentially methylated regions. Covers Bismark alignment, methylation calling, and DMR detection with methylKit. Use when analyzing bisulfite sequencing data.

Use when establishing metrics for new product, feature, or initiative - orchestrates North Star alignment, funnel mapping, proxy selection, and counter-metric identification to create comprehensive measurement framework