菜单
Full feature development workflow. Explores codebase, designs, writes PRD, implements, reviews, fixes, and creates PR. Use with "/dev <feature description>".
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/browseros-ai/BrowserOS-agent --skill dev命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | dev |
| description | Full feature development workflow. Explores codebase, designs, writes PRD, implements, reviews, fixes, and creates PR. Use with "/dev <feature description>". |
| disable-model-invocation | true |
| argument-hint | ["feature description"] |
Run the full feature development pipeline by invoking sub-skills sequentially. Start by invoking /dev1-start $ARGUMENTS. Each sub-skill will automatically chain to the next one.
/dev1-start — High-level code exploration/dev2-design — Design options (user picks one)/dev3-prd — Questions + PRD/dev4-implement — Implementation/dev5-review — Code review + commit/dev6-review-fix — Apply review fixes + commit (skipped if review is clean)/dev7-pr — Create PR, wait for Greptile, address comments, pushInvoke /dev1-start $ARGUMENTS now. It will chain through the rest of the pipeline automatically. Each skill writes artifacts to .llm/<feature_name>/ and hands off to the next skill.
Skills that need user input (design choice, question answers, PR approval) will pause and wait before continuing.
Search for a product across multiple retailers in parallel, save pricing data to disk, and produce an HTML report with the best deals and direct product links. Use when the user asks to compare prices, find the best deal, or check prices across stores.
Research a topic across multiple sources using parallel tabs, save raw content and findings to files, then produce an HTML report and PDF. Use when the user asks to research, investigate, or gather information on a topic.
Extract structured data from web pages — tables, lists, product info, pricing — into clean CSV, JSON, or markdown tables. Parallelizes across hidden tabs for multi-source extraction and saves results to disk incrementally. Use when the user asks to scrape, extract, or pull data from a page.