发现 Skills

Core software engineering principles (SOLID, DRY, YAGNI, KISS) with detection patterns and refactoring guidance. Load when reviewing code quality, planning architecture, or identifying technical debt.

Analyze commits on the current branch vs main, write a two-block PR description (non-technical summary for managers up top, technical detail for developers below), and open a GitHub PR. Use when asked to open a PR, create a pull request, or write a PR description.

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.

Deploy F# full-stack applications with Tailscale sidecar for private network access without public ports or authentication. Use when deploying to production, setting up Docker compose with Tailscale, or need private networking setup. Creates docker-compose.yml with app + Tailscale sidecar pattern for secure private access. Includes Portainer deployment, troubleshooting, and configuration for F# Giraffe + Elmish applications.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Create a PRD through user interviews, codebase exploration, and module design, saved locally to prds/. Use when the user wants to write a PRD, create a product requirements document, or plan a new feature. Don't use this for refactoring plans, bug reports, or very small changes.

Generate Ian-style Chinese inline illustrations. Used when a user requests tasks such as “bizarre”, “Xiao Hei”, “hand-drawn”, “inline illustration”, “article illustration”, “illustration suggestions”, “shot list”, or “remove title/change image” for Chinese articles, posts, blogs, Notion documents, workflow documents, methodologies, processes, structures, states, metaphors, or viewpoints. The default visual style uses the Xiao Hei IP: pure-white hand-drawn artwork, minimal red/orange/blue annotations, and a clean yet whimsical visual language.

Expert guidance for Google Ads Script development including AdsApp API, campaign management, ad groups, keywords, bidding strategies, performance reporting, budget management, automated rules, and optimization patterns. Use when automating Google Ads campaigns, managing keywords and bids, creating performance reports, implementing automated rules, optimizing ad spend, working with campaign budgets, monitoring quality scores, tracking conversions, pausing low-performing keywords, adjusting bids based on ROAS, or building Google Ads automation scripts. Covers campaign operations, keyword targeting, bid optimization, conversion tracking, error handling, and JavaScript-based automation in Google Ads editor.

Write efficient C code with proper memory management, pointer arithmetic, and system calls. Handles embedded systems, kernel modules, and performance-critical code. Use PROACTIVELY for C optimization, memory issues, or system programming.

Backup consensus ledger and curiosity metrics databases with versioned snapshots. Use when the collective needs to preserve deliberation history, create recovery points, or archive autonomy metrics.

Access the Office.js Excel JavaScript API for Excel Add-in development. Use this when you need to interact programmatically with Excel workbooks, worksheets, ranges, tables, charts, pivot tables, and other Excel objects within the Office Add-in environment.

Analyze code quality based on "Clean Code" principles. Identify naming, function size, duplication, over-engineering, and magic number issues with severity ratings and refactoring suggestions. Use when the user requests code quality checks, refactoring advice, Clean Code analysis, code smell detection, or mentions terms like code review, code quality, refactoring check.

Use when executing approved actions from /Approved folder via MCP servers. Processes email sends, payments, social posts, and other external actions.

Implement RESTful CRUD endpoints with validation, filtering, pagination, and user isolation. Use when building task management APIs, resource endpoints, or any user-scoped data operations in FastAPI.

Apply backend TypeScript conventions when generating, editing, or reviewing server-side code. Use when writing services, repositories, route handlers, domain models, error classes, or any non-React TypeScript. Covers module structure, class patterns, file naming, error handling, data access, and code style. This is a foundational skill - use it alongside more specific skills (e.g. database, Fastify) when those apply.

Go development workflow that includes verification commands and a self-review checklist. Use when modifying Go code in internal/, pkg/, or cmd/ directories.

Transform STORY-MAP.md and ARCHITECTURE-DOC.md into a phased project roadmap with vertical slices and wave-based parallelism. Use when user needs release planning, slice ordering, delivery sequencing, or wants to organize stories into an implementable roadmap.

Transcribe Vaam videos using Google Gemini AI. Takes a Vaam share URL, downloads the video, and returns a full text transcription. Supports any language without translation.

Task Monitoring Skill. Used to automatically monitor Agent task progress and push updates to a group. **Use cases:** - Automatically create monitoring when the CEO assigns a task - Periodically check the target Agent's session status - Push to the work group when new messages are discovered - Remove monitoring after the task is completed **Integration with cron:** - Create a cron job when creating a task - The cron job periodically checks the Agent's status - Delete the cron job when the task is completed

Semi-automated fact-checking, disinformation detection, and media literacy skill. Use when a user asks to verify a claim, check if something is true, detect misinformation, fact-check an article or social media post, evaluate source reliability, compare two sources, or request a prebunking briefing. Trigger phrases: "is this true?", "is this fake?", "fact check this", "compare these sources", "проверка на факти", "истина ли е", "дезинформация ли е", "сравни тези източници", "какви фалшиви наративи има за X". Works with text, URLs, screenshots, and dual-source comparison. Produces HTML Fact-Check Cards with verdict, confidence, source scoring, red flags, origin tracing, educational tips, and share-safe summary. Multi-language source verification (BG, EN, RU).

Landing Page CRO Analysis

Extracts architectural, business, and operational context from existing systems. Use to build mental models of unfamiliar codebases.

Test-strategy planner pre-execute, evidence-based test-coverage reviewer post-execute. No lead role — does not set architectural direction.

Validate your MCP server against best practices and catch common anti-patterns