context-to-prd SKILL.md skillA
context-to-prd from mingdui/ai-product-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mingdui/ai-product-skills/context-to-prd@git:20261013.be4849dPins git:20261013.be4849d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mingdui/ai-product-skills
- Path
skills/context-to-prd/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261013.be4849d, committed Oct 13, 2026
- First version recorded
- Oct 13, 2026
- Size
- 5,042 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
把已经聊透的需求上下文直接落成 PRD，不做采访。适用于你已经跟 AI 把问题、边界、方案讨论清楚，只差成文的场景；需求还停在口头、边界没问清时改用 requirement-clarify，要复用已有产品体验基线或做增量 PRD 时用 prd-write。产物与 prd-write 完全同构，落在 docs/prd/<feature-name>/prd.md。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 上下文成文 把「已经聊透的需求」直接写成 PRD。**不采访**——你手上已经有足够的上下文，再问一遍是浪费。 ## 使用边界 - **适用**：需求已经跟 AI 讨论清楚，问题、用户、范围、边界都有结论，只差落到文档。 - **不适用**： - 需求还停在口头、边界没问清 → 先用 `requirement-clarify` 采访一轮 - 要复用已有产品体验基线，或要做增量 PRD（只写本次变化）→ 用 `prd-write` - 要评审已成文的 PRD → 用 `grill-with-prd` ### 与 `prd-write` 的关系（重要） 两者产出**同一套结构**：都以 [template.md](../prd-write/template.md) 的 0–10 节为骨架， 写同一个文件 `prd.md`。差别只在过程： | | 本 Skill | `prd-write` | |---|---|---| | 是否采访 | 不采访 | 不采访 | | 是否强制读产品体验基线 | 不强制。有就读并写进第 2 节，没有就写「无基线」 | **必须查**。增量模式要靠它写清「复用 / 局部 / 候选 / 偏离」 | | 典型场景 | 聊透了，一次成文 | 迭代中的功能，要跟已有规范对齐 | **两个都产出同一个 `prd.md`，不要连着跑。** 写完一个就够了，另一个是用来替补的。 ## 开始前 1. 确定功能名，用**小写短横线**（`user-auth`、`payment-flow`）；目标 `docs/prd/<feature-name>/prd.md`。 2. 已有同名 PRD 时先问用户：**更新、另建功能目录、还是保留原文**——不要静默覆盖。 3. 查 `docs/product/<project-name>/`。有基线就读进来写进第 2 节；没有就写「无基线」， 不要凭空造产品级规则。 ## 流程 ### 1. 梳理上下文 把这次对话里**已经定下来**的东西挑出来：问题、目标角色、范围、**明确不做**、已知约束、验收口径。 没定下来的**不要替它定**——写进第 9 节「待决问题」，标明归属人。 「明确不做」这一条最容易漏，主动回头找一遍：聊的过程中有没有排除了什么。 ### 2. 探索代码库 还没了解代码库就先看一遍。全文使用项目的领域词汇，遵守相关区域已有的架构决策记录（ADR）。 ### 3. 梳理模块（本 Skill 的独有产出） 梳理需要新建或修改的主要模块，主动找**可独立测试的深度模块**机会： > **深度模块**：封装大量功能，对外暴露简单且稳定的接口，便于独立测试。 > 反过来，浅层模块把复杂度摊在外面，测试和改动都会牵连一片。 …
Read the whole file at its exact version.
How to install
mdr add mingdui/ai-product-skills/context-to-prd@sha256:df4330ca0b622246The line at the top of this page pins the label git:20261013.be4849d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_w5v7y2khlbgybd4e)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Oct 13, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261013.be4849d latest | 2026-10-13 | be4849d | 5,042 B | A | view · diff |
| git:20261013.60e8978 | 2026-10-13 | 60e8978 | 2,462 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 (5042 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
mingdui/ai-product-skills · 12 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_w5v7y2khlbgybd4e GET https://markdownregistry.com/api/v1/resolve?ref=mingdui/ai-product-skills/context-to-prd GET https://markdownregistry.com/api/v1/blob/df4330ca0b622246a83efa865a5a86e0d2c36ab6f4b65f56211798ecc4109e0e
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.