brd-interviewer skillA
brd-interviewer is agent-read markdown (skill) from testany-io/testany-agent-skills: BRD interview, 业务需求访谈。Use when: 需要将模糊的业务想法梳理成 BRD、"帮我梳理业务需求"、"老板说要做 XXX"、"这个需求不太清楚"、"写 BRD"。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# BRD Interviewer - 业务需求梳理 执行前读取 [工作流执行约定](../../references/workflow-execution.md)：先读取用户材料，从本次安装位置定位资源，按真实工具能力工作。 ## 触发范围 用于把业务想法梳理成 BRD、访谈业务需求或整理已有业务材料。仅修改已有文档片段时，只处理指定片段，不重启全套访谈。不用于替代 API/HLD/LLD 设计或业务批准。 ## 必守约束 - 保留原始意图，BRD 聚焦 WHAT/WHY、目标用户、范围、成功定义、依赖与约束。 - 已知事实直接引用；不确定信息标记假设，不代替用户决定或批准。 - 访谈每轮最多 2-3 个关键问题；尊重用户指定的检查点。 - 先按 [访谈模式与事实标准](../../references/interview-modes.md) 选择 `interview` / `synthesis` / `gap_followup`。量化不是所有任务的硬门禁；实测、估算、测量计划、离散验收分别记录。 - 默认跟随用户语言，显式语言要求优先。字段名、枚举、ID 与 comment markers 保持英文，见 [语言规则](../../references/language-policy.md)。 ## 最小工作流 1. 读取指定材料、原始目标和已有批准依据；不因文件名或标签认定批准。 2. 判断本次需要局部编辑、访谈或材料整理；不要向用户重复索取已有内容。 3. 资料充分就直接整理；仅有局部歧义就只问缺口。需要访谈时，按 [访谈问题库](references/interview-question-bank.md) 的相关阶段补全，不从头照读每个问题。 4. 生成文档时按用户语言读取 [中文模板](assets/brd-template.md) 或 [英文模板](assets/brd-template.en.md)。使用用户已指定的路径；没有路径时选工作区内合理默认并说明。 5. 检查范围、成功定义、依赖和假设。缺少历史数值仍可交付明确标注的草稿；不猜数字、不按假设数量阻塞。只要求草稿就保持草稿，正式批准必须有对应版本/范围的真实依据。 6. 返回实际文件、来源、未决项和交付状态，不主动进入实施或发布。 ## 按需资源 | 情况 | 资源 | |---|---| | 需要具体问题、分支或当前准出清单 | [访谈问题库](references/interview-question-bank.md) | | 需要问题组织方法 | [访谈框架](references/interview-framework.md) | | 需要沟通技巧 | [顾问风格](references/consultant-persona.md) | …
Read the whole file at its exact version.
How to install
mdr add testany-io/testany-agent-skills/brd-interviewer@git:20260914.a55b8c5mdr add testany-io/testany-agent-skills/brd-interviewer@sha256:66596802d8c618dbPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_rf26w3fgitn6nuyb)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260914.a55b8c5 latest | 2026-09-14 | a55b8c5 | 3,478 B | A | view · diff |
| git:20260331.40884ae | 2026-03-31 | 40884ae | 21,418 B | A | view · diff |
| git:20260307.f7f51c1 | 2026-03-07 | f7f51c1 | 21,029 B | A | view · diff |
| git:20260121.98ba0de | 2026-01-21 | 98ba0de | 21,027 B | A | view · diff |
| git:20260114.c88b8cd | 2026-01-14 | c88b8cd | 21,330 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3478 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
testany-io/testany-agent-skills · 82 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rf26w3fgitn6nuyb GET https://markdownregistry.com/api/v1/resolve?ref=testany-io/testany-agent-skills/brd-interviewer GET https://markdownregistry.com/api/v1/blob/66596802d8c618db2fe6339787bbde027ab1aa0cbb7a68fb776e40ba0c3d2c1e
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.