Token导航 LogoToken导航TokenDH.com
效率只读clawhub未标认证来源可访问clear审计通过

brd-reviewerBRD reviewer 文档

Agent Skill

brd-reviewer 用于辅助前端页面、组件、样式和交互逻辑开发,适合在 OpenClaw 中需要维护前端项目、生成组件或检查界面实现时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

7,512

周安装

313

GitHub Stars

1

下载量

2,504
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:brd-reviewer(BRD reviewer 文档)
来源仓库:https://github.com/chipmunkrpa/brd-reviewer
安装命令:
openclaw skills install brd-reviewer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install brd-reviewer

简介

用于审查 .docx 格式的业务需求文档(BRD),提取关键信息。

  • 生成澄清问题与段落级上下文摘要,提升理解准确性。
  • 适合产品经理与开发团队之间的需求对齐场景。brd-reviewer 属于效率类 Skill,可作为该场景下的辅助能力补充。
  • 使用时需上传完整 BRD 文件以确保覆盖所有细节。
  • 安装前请核实权限范围及是否会触发文件读取操作。

SKILL.md

name
brd-reviewer
description
Review Business Requirements Documents in .docx format by reading the existing BRD, extracting paragraph-level context, drafting clarification questions for unclear statements, and producing a final Word document that combines comments and tracked changes. Use when the user wants a BRD reviewed, challenged for ambiguity, or redlined with proposed wording improvements while preserving Word-native review features.

BRD Reviewer

Overview

Review a BRD paragraph by paragraph, capture clarification questions for ambiguous or incomplete requirements, and generate a single .docx with Word comments plus tracked revisions.

Prefer the bundled pipeline so the final deliverable is a Word-native review artifact instead of chat-only notes.

Workflow

  1. Confirm the source BRD .docx path.
  2. Initialize the paragraph review JSON:
   python scripts/brd_review_pipeline.py init-review \
     --input <brd.docx> \
     --output <brd.review.json>
  1. Read the BRD and fill the review JSON.

- For every paragraphs[] item, keep paragraph_index, style_id, heading_path, and source_text unchanged. - Set needs_comment to true when the paragraph is unclear, incomplete, internally inconsistent, or missing acceptance criteria, data definitions, ownership, dependencies, assumptions, or edge cases. - Write comment_question as a concise reviewer question suitable for a Word comment. - Set needs_revision to true when the paragraph should be rewritten for precision, completeness, grammar, or testability. - Write proposed_replacement as full replacement language, not fragments. - Use issue_tags to make the reason explicit. Prefer tags such as ambiguity, scope, actor, data, workflow, exception, dependency, acceptance-criteria, nonfunctional, term-definition, or conflict.

  1. Materialize the final reviewed DOCX in the same folder as the source BRD:
   python scripts/brd_review_pipeline.py materialize \
     --input <brd.docx> \
     --review-json <brd.review.json> \
     --output <brd.reviewed.docx> \
     --author "Codex BRD Reviewer"
  1. Verify output quality.

- Confirm the reviewed file exists beside the source BRD. - Confirm Word comments appear on paragraphs with needs_comment=true. - Confirm tracked changes are visible for paragraphs with needs_revision=true. - If the BRD relies heavily on tables or special layout, use the $doc skill workflow to render and visually inspect the result before delivery.

Review standard

  • Question every paragraph that leaves implementation choices unresolved.
  • Favor reviewer comments for missing information and tracked changes for proposed wording.
  • Rewrite requirements into concrete, testable statements.
  • Flag undefined actors, systems, interfaces, calculations, timing, permissions, and exception handling.
  • Do not silently invent business rules. If the BRD lacks a critical detail, ask for it in the comment instead of guessing.
  • Keep comments short and specific enough to be actionable in a comment balloon.
  • Keep proposed replacements professional and directly usable in the document.

Output contract

  • Always produce:

- <name>.review.json - <name>.reviewed.docx

  • Place both outputs in the same folder as the source BRD unless the user explicitly requests another path.
  • Treat chat analysis as supplemental only. The .docx is the primary deliverable.

Resources

  • Paragraph review schema: references/review-json-schema.md
  • Main tool: scripts/brd_review_pipeline.py

Dependencies

Install once if missing:

python -m pip install python-docx lxml

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

73.47%
按下载量换算1,840

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills