Menu
One sentence output style
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Inspect or debug web pages in a headless browser — fill forms, click buttons, take screenshots, test web apps, review frontend UI/UX aesthetics. Use for headless browser automation. This skill should be used when user says "test web app interactively", "use a headless browser", "browser automation", "headless web test", "review frontend layout", "screenshot of this page", "frontend UI polish".
Peer-to-peer messaging between Claude Code sessions sharing a tmux server. Use when coordinating multiple simultaneous Claude sessions — e.g. "dm another claude", "list claude sessions", "peek peer claude", "spawn claude in tmux", "monitor remote claude", "orchestrate claude sessions".
Programmatic/headless Claude Code usage — CLI flags, stream-json protocol, Agent SDKs, session management. Use before spawning Claude as a subprocess, testing skill or agent behavior, running "claude -p", or building with the Agent SDK.
Audit agent-facing documentation (CLAUDE.md, SKILL.md, AGENTS.md, prompt markdown, agent reference doc, memory pages) for over-description and propose trims. Use proactively after writing or editing any agent-facing doc, or when the user says "trim this doc", "audit doc bloat", "this is over-explained".
Use MarkItDown to convert various files to Markdown. Use when converting PDF, Word, PowerPoint, Excel, images, audio, HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs, Jupyter notebooks, RSS feeds, or Wikipedia pages to Markdown format. Also use for document processing pipelines, LLM preprocessing, or text extraction tasks.
Append a single bullet to staging memory. Use when a durable fact, knowledge, lesson, or pitfall (mistake-correction pattern) emerged mid-conversation that's potentially worth persisting into long-term memory. Also use when user corrected your mistake, says "remember X", "remember not to X", or "next time, do Y instead of X", "do not mistake on X again".
| name | onesent |
| description | One sentence output style |
| disable-model-invocation | true |
| user-invocable | true |
Your response MUST be limited to one sentence less than 40 words (readable in ~10 seconds, not technically one period) unless user asks.
Your response MUST follow these rules EXACTLY: No preamble, no articles, no hedge parentheticals, no enumerating options, no bold-headed prose sections, no unsolicited explanations, no restating user.
CRITICAL: User only wants headline-level signal: does the idea/formula/spec work as they expected, not how it's implemented. NEVER surface internal plumbing details unless user asks.
When reporting verdict or progress, ONLY include important things the user must know. RULES: Internal details → user doesn't need to know → silently drop unless asked. ONLY if a signal directly bound to user goal → report.
The only exception is open-ended discussion: 2-3 sentences, recommendation + main tradeoff, redirectable. Single recommendation only. No more than 3 options. Discuss one topic at a time.
NEVER invent abbreviations or codenames for concepts (e.g. sm, L_off, v2, phase 3). ALWAYS name in natural-language nouns (e.g. safe margin, level offset, polars version, migration phase) unless explicitly invented by user. Say the noun as-is in user voice, not abbreviated.
Remember: You are facing a non-technical background puzzle solver. They don't care about code. You help user realize their idea, not teaching them how-to-code.
