Agent skill

Product Feature Tech Design

by digoal in digoal/blog

将 PRD 翻译成「可独立测试」的功能设计文档。文档的下游使用者包括开发者、评审者、测试者,且三方互相隔离(测试者看不到开发者写的代码),所以必须把行为、状态、接口、数据、权限、异常、验收标准全部显式化,让测试者能独立从文档推导用例。输入是一份已写好的 PRD 文档,输出是一份完整的 Markdown 功能设计文档,保存到当前项目的 markdown/…

GPL-2.0Auto-check passedProduct & Project Management

Install Product Feature Tech Design

skills CLI
$ npx skills add digoal/blog --skill product-feature-tech-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install digoal/blog product-feature-tech-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/product-feature-tech-design .claude/skills/product-feature-tech-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
product-feature-tech-design
GitHub stars
8.6k
Token cost
~770 tokens
SKILL.md length
156 words
Files
6 (incl. references)
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

将 PRD 翻译成「可独立测试」的功能设计文档。文档的下游使用者包括开发者、评审者、测试者,且三方互相隔离(测试者看不到开发者写的代码),所以必须把行为、状态、接口、数据、权限、异常、验收标准全部显式化,让测试者能独立从文档推导用例。输入是一份已写好的 PRD 文档,输出是一份完整的 Markdown 功能设计文档,保存到当前项目的 markdown/…

  • Works in 6 steps: 通读 PRD 并提取产物 → 按 references/feature-design-template.md… → 深化关键章节(优先级从高到低) → …
  • Tasks that involve PRD writing
  • SKILL.md covers 核心约束(决定一切), 输入, 工作流 and 文档与下游的契约, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Product Feature Tech Design is an agent skill from digoal/blog. 将 PRD 翻译成「可独立测试」的功能设计文档。文档的下游使用者包括开发者、评审者、测试者,且三方互相隔离(测试者看不到开发者写的代码),所以必须把行为、状态、接口、数据、权限、异常、验收标准全部显式化,让测试者能独立从文档推导用例。输入是一份已写好的 PRD 文档,输出是一份完整的 Markdown 功能设计文档,保存到当前项目的 markdown/ 目录。适用于:写功能设计文档、技术设计文档、Tech Design、详细设计说明书、FDD、Functional Design Doc、Detailed Design、模块设计文档、把 PRD 翻译成开发设计、把需求拆成可开发/可测试/可评审的规格。

Its SKILL.md is about 770 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `agents/openai.yaml`, `references/api-spec-template.md` and `references/feature-design-template.md`).

It sits in Product & Project Management, covering PRD writing, Architecture decision records and Markdown. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

When your agent uses it

  • Tasks that involve PRD writing
  • Tasks that involve Architecture decision records
  • Tasks that involve Markdown

Example prompts

  • “/product-feature-tech-design”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 通读 PRD 并提取产物
  2. 按 references/feature-design-template.md 起骨架
  3. 深化关键章节(优先级从高到低)
  4. 验收标准必须可执行
  5. 自检(见下方质检清单)
  6. 保存

What it can do on your machine

Read from SKILL.md and the folder at commit ad6fcb7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Product Feature Tech Design loads about 770 tokens when it runs, and up to ~9.9k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 156 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~770
With references · SKILL.md plus every file in references/, read only if the agent opens them
~9.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from digoal/blog at commit ad6fcb7, republished under its GPL-2.0 licence (© digoal). 156 words, ~770 tokens.

Download SKILL.mdSave it as .claude/skills/product-feature-tech-design/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
product-feature-tech-design
description
将 PRD 翻译成「可独立测试」的功能设计文档。文档的下游使用者包括开发者、评审者、测试者,且三方互相隔离(测试者看不到开发者写的代码),所以必须把行为、状态、接口、数据、权限、异常、验收标准全部显式化,让测试者能独立从文档推导用例。输入是一份已写好的 PRD 文档,输出是一份完整的 Markdown 功能设计文档,保存到当前项目的 `markdown/` 目录。适用于:写功能设计文档、技术设计文档、Tech Design、详细设计说明书、FDD、Functional Design Doc、Detailed Design、模块设计文档、把 PRD 翻译成开发设计、把需求拆成可开发/可测试/可评审的规格。

Product Feature Tech Design

核心约束(决定一切)

测试者看不到开发者的代码。功能设计文档是三方的唯一共同依据:

角色从文档里读什么看不到
开发者接口契约、数据模型、行为规则、边界条件— (有文档)
评审者设计原则、权衡取舍、验收标准— (有文档)
测试者用例推导的完整基础开发者的源代码

→ 文档必须把行为写死,不留给实现者自由发挥的空间;同时不规定实现细节(避免越界成架构图)。这条边界是这份文档的灵魂。

输入

  • 一份 PRD 文档(本项目 markdown/ 下,或用户提供的路径)。
  • 用户的额外约束(若有):技术栈、性能指标、合规要求等。

如果输入没有 PRD,先停下来问用户要 PRD,不要凭空白生成功能设计文档。

工作流

  1. 通读 PRD 并提取产物

    • 目标用户、核心场景、成功指标、范围切片。
    • 所有功能模块、用户故事、边界条件、权限点。
    • 显式列出 PRD 中没说清的地方,作为"待确认项"记入文档,不擅自补全。
  2. 按 references/feature-design-template.md 起骨架

    • 不要跳过任何章节。允许"本章不适用"标注,但不能整章删除。
    • 每章用 PRD 中的事实填充,缺数据时标"待确认",不要瞎编。
  3. 深化关键章节(优先级从高到低)

    • 接口规格 → 读 references/api-spec-template.md,每个端点都给出:请求/响应字段表、错误码表、幂等性、限流、鉴权点。
    • 状态机 → 读 references/state-machine-template.md,每个实体都要画出状态转移图,包括非法转移。
    • 测试矩阵 → 读 references/test-matrix-template.md,用维度(角色 × 操作 × 数据状态 × 环境)穷举测试面,测试者直接按矩阵写用例。
  4. 验收标准必须可执行

    • 全部用 Given/When/Then 写,每条只测一个点。
    • 包含:正常路径、异常路径、权限路径、数据边界、并发/超时、跨模块交互。
    • 性能/可用性指标给出具体数值(p99 ≤ 200ms、错误率 < 0.1%),不给"较快"。
  5. 自检(见下方质检清单)

    • 如果任一项不过,补完后再交付。
  6. 保存

    • 路径:markdown/<topic>-feature-design-<YYYYMMDD>.md
    • 如果生成了 SVG 图,保存为 markdown/<topic>-<diagram-name>-<YYYYMMDD>.svg,在文档中用相对路径引用。

文档与下游的契约

给开发者(可实现)
  • 完整的数据模型:实体、字段、类型、约束、生命周期、索引建议。
  • 完整的接口契约:路径、方法、入参/出参/错误码、幂等、限流、鉴权。
  • 业务规则用自然语言 + 决策表 / 伪代码,不规定框架、不规定语言、不规定文件结构。
  • 状态机:所有合法/非法状态转移。
  • 依赖关系:对外部模块/服务的契约要求。
给评审者(可检查)
  • 设计决策与备选方案(为什么选 A 不选 B)。
  • 非功能性指标(性能、可用性、安全、可观测性)的具体数值。
  • 与 PRD 的对齐情况(每条 PRD 需求都有对应设计章节)。
  • 风险点与缓解措施。
给测试者(可独立写用例,最关键的读者)
  • 每个功能的前置条件、操作步骤、期望结果(逐字段,不要"返回成功"这种模糊描述)。
  • 输入数据矩阵:合法、非法、边界值(0、最大值、Unicode、SQL 注入字符、超长字符串等)。
  • 状态前置:基于哪一状态才能触发此操作。
  • 并发与时序:重入、双击、过期、跨时钟。
  • 错误码表:每种错误码对应的触发条件 + 用户可见提示。
  • 不变量:无论什么操作,系统都应保持的性质(如"用户余额永远 ≥ 0")。

质检清单(交付前自检)

  • 每个 PRD 中的功能点都能在文档中找到对应章节。
  • 每个对外接口都有完整的请求/响应/错误码表。
  • 每个有状态的实体都有状态机图,且包含非法状态。
  • 每条业务规则都用 Given/When/Then 或决策表表达,无歧义。
  • 测试矩阵覆盖:角色 × 操作 × 数据状态 × 环境,且每个单元格都有预期结果。
  • 性能/可用性指标都有具体数值,不是"较快/较稳定"。
  • 权限矩阵明确:每个角色对每个资源的可见/可操作/不可操作。
  • 至少 1 张图(系统上下文、流程、状态机、时序均可,优先 Mermaid)。
  • "待确认项"清单存在,每项都标明对哪条设计有影响。
  • 文档不规定具体语言/框架/库/目录结构(只规定行为和契约)。

输出

  • 一份 Markdown 文件,保存到当前项目 markdown/ 目录(不存在则创建)。
  • 文件名:<topic>-feature-design-<YYYYMMDD>.md,其中 <topic> 用 PRD 的主题拼音/英文 slug。
  • 文档用中文(除非用户要求其他语言)。
  • 文档长度没有硬性上限,但应详尽到让测试者能独立写用例为准;不要为简洁而省略边界。

参考资料

  • references/feature-design-template.md — 完整模板(16 章节),骨架必读。
  • references/api-spec-template.md — 接口契约子模板,深化"对外接口"章节时使用。
  • references/state-machine-template.md — 状态机子模板,深化"状态机"章节时使用。
  • references/test-matrix-template.md — 测试矩阵子模板,深化"验收标准"章节时使用。

© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/product-feature-tech-design of digoal/blog.

  • SKILL.md
  • agents/openai.yaml
  • references/api-spec-template.md
  • references/feature-design-template.md
  • references/state-machine-template.md
  • references/test-matrix-template.md

Open the folder on GitHubat commit ad6fcb7

Compare with similar skills

Product Feature Tech Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Product Feature Tech Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Product Feature Tech Design this skilldigoal/blog8.6k—~770Automated safety check: PassGPL-2.0
Use Case Writerphucnt-bazone-vietnam/use-case-writer143—~4.1kAutomated safety check: PassMIT
Schematicblader/schematic241—~2.2kAutomated safety check: PassMIT
Shep Workstreamsshep-ai/shep264—~2.5kAutomated safety check: PassMIT
Write Update Tidb Docspingcap/docs616—~2.3kAutomated safety check: PassCustom licence
App Spec Packagerinstructa/agent-skills139—~1.5kAutomated safety check: PassNone

Similar skills

  • Use Case Writer

    phucnt-bazone-vietnam/use-case-writer

    Generate Use Case specifications in English Markdown following the IT BA standard 13-field template (Karl Wiegers / IIBA).

    143 GitHub stars~4.1k tokensUpdated 4 mo ago
    Product & Project ManagementAuto-check passed
  • Schematic

    blader/schematic

    Reverse engineer a detailed product and technical specification document from a git branch's implementation.

    241 GitHub stars~2.2k tokensUpdated 7 mo ago
    Product & Project ManagementAuto-check passed
  • Shep Workstreams

    shep-ai/shep

    A skill your agent uses when a large body of work (a version milestone, an epic, a roadmap, a set of PRDs/design docs) needs to be broken into parallel workstreams and executed with the shep CLI.

    264 GitHub stars~2.5k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Write new TiDB documentation or update existing TiDB documentation from code changes, PRs, issues, design docs, product specs, rough drafts, existing docs, or short feature descriptions.

    616 GitHub stars~2.3k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • App Spec Packager

    instructa/agent-skills

    A skill your agent uses when the user wants to turn an application, product, startup idea, SaaS, mobile app, web app, API, AI product, or internal tool into a production-ready Markdown specification…

    139 GitHub stars~1.5k tokensUpdated 12 days ago
    Product & Project ManagementAuto-check passed
  • Bmad Help

    aj-geddes/claude-code-bmad-skills

    Orchestration spine and "what do I do next?" router for the BMAD Planning & Orchestrator plugin.

    488 GitHub stars~1.7k tokensUpdated 3 mo ago
    Product & Project ManagementAuto-check: notes

More from digoal/blog

All 98 skills in this repo
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated yesterday
    Auto-check passed
  • Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…

    8.6k GitHub stars~4k tokensUpdated yesterday
    Auto-check passed
  • Digoal

    digoal/blog

    Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

    8.6k GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • 从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

    8.6k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Questions about Product Feature Tech Design

What does Product Feature Tech Design do?

将 PRD 翻译成「可独立测试」的功能设计文档。文档的下游使用者包括开发者、评审者、测试者,且三方互相隔离(测试者看不到开发者写的代码),所以必须把行为、状态、接口、数据、权限、异常、验收标准全部显式化,让测试者能独立从文档推导用例。输入是一份已写好的 PRD 文档,输出是一份完整的 Markdown 功能设计文档,保存到当前项目的 markdown/…. Product Feature Tech Design is an agent skill from digoal/blog.

When should I use Product Feature Tech Design?

Product Feature Tech Design fits situations like: tasks that involve PRD writing; tasks that involve Architecture decision records; tasks that involve Markdown.

How do I install Product Feature Tech Design in Claude Code?

Run `npx skills add digoal/blog --skill product-feature-tech-design -a claude-code`. Or copy the skill folder (skills/product-feature-tech-design in digoal/blog) into .claude/skills/product-feature-tech-design in your project. Claude Code loads it when a task matches its description.

How do I install Product Feature Tech Design in Codex?

Run `npx skills add digoal/blog --skill product-feature-tech-design -a codex`. Or copy the skill folder (skills/product-feature-tech-design in digoal/blog) into .agents/skills/product-feature-tech-design in your project. Codex loads it when a task matches its description.

Can I use Product Feature Tech Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill product-feature-tech-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/product-feature-tech-design, .gemini/skills/product-feature-tech-design, .github/skills/product-feature-tech-design and .opencode/skills/product-feature-tech-design in your project.

What does Product Feature Tech Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Product Feature Tech Design is instructions for the agent only.

Does Product Feature Tech Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Product Feature Tech Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Product Feature Tech Design use?

Product Feature Tech Design is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Product Feature Tech Design use?

About 770 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.1k tokens, read only when the agent opens those files.

What are the alternatives to Product Feature Tech Design?

Skills that share tags, products or a category with Product Feature Tech Design: Use Case Writer (phucnt-bazone-vietnam/use-case-writer, 143 stars), Schematic (blader/schematic, 241 stars), Shep Workstreams (shep-ai/shep, 264 stars) and Write Update Tidb Docs (pingcap/docs, 616 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Product Feature Tech Design?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,588 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 9, 2026.

Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.