Agent skills for ChatGPT

Use when you need to run arbitrary JS in a page, inspect cookies/localStorage, check computed styles, emulate devices, or drive real…

Executes browser-based user workflows from /workflows/browser-workflows.md using Claude-in-Chrome MCP.

Autonomous browser agent for complex multi-step web tasks.

Browser automation. MUST invoke before calling Playwright. Use when browsing websites, checking UI, filling forms, or automating web…

Generate stable platform-ready AI illustrations for WeChat official account articles, Xiaohongshu notes, Zhihu posts, Toutiao posts, and…

Build, extract, and maintain design systems - tokens with roles, typographic scale, spacing scale, color, radius, shadow, dark mode, and…

This skill turns a resume and a short set of criteria into a repeatable job search: find listings that fit, keep a log so nothing is…

BiSheng C safe zones. When you write _Safe functions, _Unsafe escape blocks, or decide where the safety boundary goes, use this Skill.

Run an explicitly authorized, conservative BT6 merge train that processes validated pull requests one at a time and reconciles repository…

Audit one pull request in a BT6 research or support repository at an exact head SHA, covering correctness, research integrity, security…

Use when writing or editing documentation — project docs, CLAUDE.md, READMEs, SKILL.md, docstrings, inline comments.

Use after verify passes for the future maintainer's audit — sit in the chair of the person who'll touch this code in 3-6 months and ask…

Generate and open an interactive visualization of Buddy guard-mode reasoning data using Buddy's local CLI command.

Systematically finds and fixes bugs using proven debugging techniques.

Creates a structured bug report from a description, or analyzes code to identify potential bugs.

Build a source-backed dashboard or monitoring view with clear metrics, filters, visual hierarchy, definitions, refresh context, and QA.

Build a new Fivetran connector from a description.

Build a web page using the kunchenguid design system.

Build a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval criteria.

Build AI that answers questions about your database.

Build an ML pipeline — from data to trained model to serving endpoint.