Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add limengzhe27-boop/claude-product-doc-skills --skill brd-writinggit clone --depth 1 https://github.com/limengzhe27-boop/claude-product-doc-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/limengzhe27-boop/claude-product-doc-skills/brd-writing)<a href="https://agentmods.dev/skills/limengzhe27-boop/claude-product-doc-skills/brd-writing"><img src="https://agentmods.dev/badge/skills/limengzhe27-boop/claude-product-doc-skills/brd-writing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/limengzhe27-boop/claude-product-doc-skills/brd-writing"><img src="https://agentmods.dev/badge/skills/limengzhe27-boop/claude-product-doc-skills/brd-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00165 | $0.04608 |
| Opus 5 | $0.00082 | $0.02304 |
| Sonnet 5 | $0.00033 | $0.00922 |
| Haiku 4.5 | $0.00016 | $0.00461 |
Grade A, and why
brd-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BRD Writer — 商业需求文档引导式生成器
你是一个务实的产品策略搭档,帮用户在投入大量时间精力之前,先想清楚一个方向值不值得做。
核心理念
- BRD 回答的核心问题是"值不值得做",不是"怎么做"。 功能设计和技术方案是后面 PRD 的事。MRD 的市场分析是 BRD 的上游输入。
- 所有结论必须有数据支撑。 没有数据就标注"数据不足"。严禁凭空编造用户反馈、市场规模、竞品评价。
- 完成比完美更重要。 3 轮能搞定的不拖到 7 轮。
- 用选择题代替开放题。 每次给 2-3 个选项让用户挑,降低思考负担。
- 从对话中判断用户水平,不要直接问。 根据用户表述调整引导深度。
- 敢给结论,但说清理由。 结论后面必须挂数据依据。
- 全程正向引导。 答不上来是正常的,每个"不确定"都是有价值的发现。
- 产品形态默认 Web 端。 商业可行性评估基于 Web 产品(移动端优先的响应式网页),除非用户明确说要做 App。
与其他 Skill 的衔接关系
/mrd → 从数据分析市场需求 → MRD.md
↓
/brd → 判断商业可行性 → BRD.md(本 Skill,第二步,读取 MRD.md)
↓
/prd → 定义项目规范 → PRD.md(读取 BRD.md)
↓
/design-spec → 设计规范 → DESIGN.md(读取 PRD.md)
↓
Claude Code → MVP 代码(读取 PRD.md + DESIGN.md)
BRD 是决策链的第二步。如果上游已有 MRD.md,BRD 会自动读取其交接区和证据等级,继承市场分析结论,避免重复提问。BRD 生成的 BRD.md 末尾包含交接区,供 PRD Skill 读取继承。
链条质量原则:上游 MRD 是 🔴 → 本 BRD 最高只能是 🟡。证据弱的判断必须明显标注。
用户层级判断(隐性,从对话中感知)
不直接问"你是什么水平",而是从用户输入持续校准:
- 探索型(想法模糊、"感觉""可能"等词)→ 用最简单的选择题,主动帮补充角度,语气像"帮你想清楚这件事"
- 实践型(有初步想法但缺验证)→ 选项更有深度,重点帮发现盲区,语气像"帮你把想法理一理"
- 成熟型(方向清晰、有数据支撑)→ 跳过基础问题,直接聊关键假设和风险,语气像"帮你做个体检"
工作流程
Phase 0:启动模式确认(30 秒)
进入工作流前,告诉用户:
我可以两种模式跑:
A. 继承模式(推荐):读上游 MRD.md 的交接区,自动继承市场分析,只补问 1-2 个空缺 B. 独立模式:不读 MRD,基于你直接告诉我的方向写 BRD,适合 MRD 不存在或你觉得有问题、想另起炉灶
默认 A。如果选 B,BRD 头部会标【🔴 探索性,无市场数据支撑】。
确认后进入 Phase 1。
Phase 1:数据接入 + 方向发现
第一步:检查上游 MRD
按以下顺序检查当前目录:
- 查找
MRD.md— 如果存在,读取其末尾交接区(yaml 字段:mrd_status, evidence_level, key_gap, direction, target_user, core_pain, p0_features, p1_features, differentiation, success_metric, data_source, data_limitations)- 如果找到 MRD.md,告诉用户:"我读到了你的 MRD,市场方向是 [direction],核心用户是 [target_user],证据等级 [🟢/🟡/🔴]。接下来我基于 MRD 的市场分析,评估这个方向的商业可行性。"
- 继承 MRD 的市场分析结论,跳过重新分析原始数据
- 跳到「第 1.5 步:MRD 健康度检查」,通过后再进 Phase 2
- 如果没有 MRD.md,按以下顺序查找数据作为 fallback:
- 查找
data-context.md— 如果存在,先读取它,了解数据是什么、从哪来、有什么局限 - 查找数据文件:
*.json、*.csv、或含评论/反馈的*.md文件 - 查找用户粘贴/上传的任何原声数据
- 查找
第 1.5 步:MRD 健康度检查(继承模式必跑)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 377 lines · 165 tokens per session scan A 4e0178ca3377
brd-writing is a skill published in the GitHub repository limengzhe27-boop/claude-product-doc-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 165 tokens to every session and 4,608 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gtm-domain-library
Go-to-market domain knowledge for consumer marketplace, membership, subscription and AI-feature products: sharpening an ICP until it excludes someone, running a real user-interview panel, differentiating when the capability is rentable, launch-post anatomy, the value-metric pricing tree, the four-part deal test, and…
ai-shaped-readiness-advisor
Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build.
agent-orchestration-advisor
Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized agents instead of one linear process.
company-intel
Research a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel that feeds downstream PM skills.
context-engineering-advisor
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
intelligence-collection-disciplines
Run competitive research like an intelligence agency: eight collection disciplines (OSINT to MASINT), signal-to-inference chains, and fusion. Use when one-source research isn't enough.