skills

Ship a completed feature - lint, test, commit, push, PR, subagent review loop, risk-rated PR description. Use when the user says "finish this feature", "ship it", "wrap this up", or "create the PR".

Ask the user a few casual clarifying questions before acting. Reliable trigger is the explicit /questions command. Soft trigger is the message's last character being a question mark, but that's a phrase-match heuristic the model may miss - use /questions when you want it guaranteed. Lighter, more conversational sibling of "grill me" style interviews - not relentless, just a couple of genuine questions to sharpen the request before doing work.

Update a project's documentation to reflect code changes on the current branch before opening a PR. Use when the user finishes a feature/fix and is about to create a PR, or asks to "sync docs", "update the docs for these changes", or check whether documentation needs updating.

Give an honest opinion without implementing anything, when a user message ends with "wdyt", "wdyt?", or "what do you think" (also "what do you think?"). Use this instead of jumping to a plan or code. Surfaces concerns, tradeoffs, and clarifying questions, then waits for the user's response before doing any work.

Route subtasks to other models - glm-5.2 (opencode), gpt (codex exec), grok-4.5 (grok build), Claude subagents - with cost/quality routing and verification. Use when the user says "delegate", "farm this out", "have glm/codex/grok do it", or asks to split a task across models. Not for ordinary tasks the main agent should do itself.

Multi-model code review - the /review methodology with finder agents routed to cheap models on other harnesses (gpt via codex, glm via opencode) through the delegate skill, verified and synthesized by the main agent. Use when the user says "delegate-review", "multi-model review", or "review this PR with cheap workers".

Write documentary-style long-form YouTube scripts (~8-10 min) for a dev-focused tech channel. Use when the user asks to write an investigative, opinion, or documentary video script about an industry event, controversy, policy change, or trend. NOT for tool reviews or tutorials — use longs-writer for those.

Write short video scripts in the style of a developer-focused tech shorts channel. Use when the user asks to write a short, create a short video script, or make a script for a short about a tool, technique, or concept.

Score a YouTube title 0-100 using a heuristic reimplementation of the vidIQ-style title score. Use when the user asks to score, rate, grade, or evaluate a YouTube title, or wants to compare/iterate title options. Returns a numeric score with per-factor breakdown and improvement suggestions. NOT the real vidIQ score - a tunable approximation.

Write long-form YouTube scripts (~8 min) for a dev-focused tech channel. Use when the user asks to write a long video script, create a YouTube script, or plan a video about a tool, technique, or concept.

Fetch developer newsletter RSS feeds and Hacker News top stories, then pick the 10 best items as YouTube video topic ideas. Use when the user asks for newsletter picks, video topic ideas from newsletters, a weekly dev digest, or to "run the newsletter digest".

Generate 5 engaging tweet options based on a topic or description

Audit and prune bloated CLAUDE.md or AGENTS.md context files using evidence-based criteria from research on what actually helps coding agents. Use when a user asks to trim, audit, review, or improve their CLAUDE.md, AGENTS.md, or any repository context file for AI coding agents.