Menu
Check changed code against MMPS project conventions and report violations with fix suggestions
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | review-style |
| description | Check changed code against MMPS project conventions and report violations with fix suggestions |
Scan changed or specified files for MMPS code convention violations and report them with fix suggestions.
Determine scope: If the user specified files or directories, use those. Otherwise, find changed files via git diff --name-only HEAD and git diff --cached --name-only. Only check .ts files.
Check for these violations by grepping the target files:
| # | Violation | Pattern to find | Fix |
|---|---|---|---|
| 1 | interface usage | ^export interface or ^interface | Change to type X = { |
| 2 | Default exports | export default | Use named exports only |
| 3 | .then() chains | .then( | Refactor to async/await |
| 4 | JSDoc comments | /** ... */ multi-line doc blocks (not single-line // comments) | Remove JSDoc, use inline // comments only if needed |
| 5 | Missing readonly on type properties | Type alias properties without readonly modifier | Add readonly to type properties |
| 6 | Stale import: @services/telegram-grammy | from '@services/telegram-grammy' | Change to from '@services/telegram' (the path was consolidated; telegram-grammy no longer exists) |
| 7 | Wrong import: node-telegram-bot-api | from 'node-telegram-bot-api' | Use grammY via @services/telegram |
| 8 | Wrong keyboard util | getInlineKeyboardMarkup | Use buildInlineKeyboard from @services/telegram |
| 9 | Missing barrel exports | New .ts files in a directory that has an index.ts but doesn't re-export the new file | Add export to index.ts |
| 10 | this.bot.api.* in controllers | this.bot.api. in *.controller.ts files inside handler methods that receive ctx | Use ctx.reply(), ctx.deleteMessage(), etc. instead |
Report format: For each violation found, output:
file_path:line_number — violation descriptionSummary: End with a count — e.g., "Found 3 violations in 2 files" or "No violations found."
Do NOT auto-fix unless the user explicitly asks to fix them. Only report.
Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.
Research an external website, API, tool, or service and produce an MMPS-specific feasibility + integration plan
Plan new MMPS features by exploring the codebase and producing a structured implementation plan that follows project conventions
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.