Agent skill

Write Brd

by digoal in digoal/blog

Write a practical Business Requirements Document (BRD) from a product idea, feature concept, customer request, business problem, or rough product opportunity.

GPL-2.0Auto-check passedDevelopment

Install Write Brd

skills CLI
$ npx skills add digoal/blog --skill write-brd -a claude-code

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

GitHub CLI
$ gh skill install digoal/blog write-brd --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/write-brd .claude/skills/write-brd && 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
write-brd
GitHub stars
8.6k
Token cost
~1.4k tokens
SKILL.md length
749 words
Files
4 (incl. references, assets)
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

Write a practical Business Requirements Document (BRD) from a product idea, feature concept, customer request, business problem, or rough product opportunity.

  • Works in 7 steps: Clarify the idea just enough → Reframe the idea as a business decision → Build the BRD from three lenses → …
  • The user asks to write
  • SKILL.md covers Purpose, Default Output, Workflow and Evidence Rules, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Write Brd is an agent skill from digoal/blog. Write a practical Business Requirements Document (BRD) from a product idea, feature concept, customer request, business problem, or rough product opportunity. Use when the user asks to write, draft, generate, refine, or save a BRD/business requirements document/product business case in Markdown, especially when the output should be saved under the current project's markdown directory and include diagrams using Mermaid, SVG, or ASCII.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files and assets (for example `agents/openai.yaml`, `assets/brd-template.md` and `references/brd-writing-guide.md`).

It sits in Development, covering Diagrams, PRD writing and Markdown. It works with Mermaid. 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

  • The user asks to write
  • Save a BRD/business requirements document/product business case in Markdown
  • Especially when the output should be saved under the current projects markdown directory and include diagrams using Mermaid

Example prompts

  • “/write-brd”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Clarify the idea just enough
  2. Reframe the idea as a business decision
  3. Build the BRD from three lenses
  4. Use the BRD template
  5. Add diagrams that explain decisions
  6. Write success and stop conditions
  7. Save and verify

What it can do on your machine

Read from SKILL.md and the folder at commit 69fb793. 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

Write Brd loads about 1.4k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 749 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.8k

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 69fb793, republished under its GPL-2.0 licence (© digoal). 749 words, ~1,445 tokens.

Download SKILL.mdSave it as .claude/skills/write-brd/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
write-brd
description
Write a practical Business Requirements Document (BRD) from a product idea, feature concept, customer request, business problem, or rough product opportunity. Use when the user asks to write, draft, generate, refine, or save a BRD/business requirements document/product business case in Markdown, especially when the output should be saved under the current project's markdown directory and include diagrams using Mermaid, SVG, or ASCII.

Write BRD

Purpose

Turn a rough product idea into a decision-ready BRD Markdown file saved in the current project's markdown/ directory. The BRD should help stakeholders decide whether to invest, what user problem is real, what scope is in or out, and how success will be verified after launch.

This skill writes BRDs, not PRDs. Keep implementation detail high enough for feasibility and handoff, but do not expand into screen-by-screen product specs unless the user asks.

Default Output

  • Save one Markdown file to markdown/<topic>-BRD-<YYYYMMDD>.md.
  • Use a Chinese topic name when the user writes in Chinese; otherwise use kebab-case English.
  • Include at least one useful diagram inside the BRD.
  • Use Mermaid by default. Use ASCII for tiny flows. Use SVG only when layout or richer visual explanation is needed.
  • If using SVG, save it as a separate file in the same markdown/ directory, named figure-1-<topic>-BRD-<YYYYMMDD>.svg, then reference it from the Markdown with ![描述](figure-1-<topic>-BRD-<YYYYMMDD>.svg).

Workflow

1. Clarify the idea just enough

If the user's idea is too thin to write a credible BRD, ask at most 3 questions. Prefer assumptions over long interrogation.

Ask only for missing information that changes the BRD materially:

  • Target user or customer
  • Business goal or pain point
  • Product context or company type
  • Constraints such as time, budget, compliance, existing systems

If the user gives no detail beyond an idea, proceed with explicit assumptions and mark low-confidence sections.

2. Reframe the idea as a business decision

Before writing sections, convert the idea into this chain:

text
business loss/opportunity -> target user -> current workaround -> proposed capability -> success metric -> delivery boundary -> stop/continue rule

Reject pure feature-first framing. Do not start the BRD from "we need feature X" unless you immediately explain why the business should fund it.

3. Build the BRD from three lenses

Use these lenses in every BRD:

  1. Investment lens: What loss, revenue, cost, risk, or strategic option justifies the work?
  2. User evidence lens: Who has the problem, in what scenario, what do they do today, and what behavior should change?
  3. Delivery lens: What is in scope, what is out, what depends on other teams or systems, and how will completion be verified?
4. Use the BRD template

Read assets/brd-template.md when drafting the document. Adapt headings to the user's context, but keep the core decision logic intact.

For extra guidance on evidence, diagrams, validation, and wording, read references/brd-writing-guide.md.

5. Add diagrams that explain decisions

Every BRD must include at least one diagram that supports reasoning, not decoration. Good diagram choices:

  • Business value chain: problem -> opportunity -> scope -> metric -> decision
  • User workflow: current process -> pain point -> proposed process
  • Scope boundary: in scope / out of scope / future phase
  • Delivery dependency map
  • Post-launch validation loop

Use Mermaid unless SVG is clearly better. If using SVG, create a standalone SVG file and reference it in Markdown.

Show full SKILL.md (299 more words)Show less
6. Write success and stop conditions

Every BRD must include:

  • Baseline metric or "baseline unknown; must be measured before build"
  • Target metric and time window
  • Data source or owner
  • Launch success criteria
  • Stop, shrink, or pivot condition

Do not let "launch completed" stand in for "business value achieved".

7. Save and verify

After writing the Markdown file:

  • Confirm it exists under the current project's markdown/ directory.
  • Confirm at least one diagram exists in the Markdown.
  • If any SVG is referenced, confirm the SVG file exists beside the Markdown file.
  • Check that the BRD contains in-scope, out-of-scope, success metrics, risks, dependencies, and post-launch validation.
  • Tell the user the saved file path and any assumptions made.

Evidence Rules

  • If current market data, competitor claims, regulations, pricing, or product facts matter, browse or otherwise verify with reliable sources before writing.
  • If evidence cannot be verified, label it as an assumption instead of presenting it as fact.
  • Prefer concrete observations over vague claims: "5 interviewed users spent 2-4 hours weekly reconciling data" is better than "users strongly need efficiency".
  • Do not invent customer quotes, user counts, revenue, conversion rates, or benchmark data.

Writing Style

  • Write in clear, decision-oriented business language.
  • Keep the BRD practical and readable; avoid inflated product management jargon.
  • Use tables for structured scope, metrics, risks, dependencies, and milestones.
  • Use concise paragraphs for context and rationale.
  • Separate "known facts", "assumptions", and "open questions".

Minimum BRD Sections

If adapting the template, keep these sections at minimum:

  1. Title and one-line decision
  2. Executive summary
  3. Background and business problem
  4. Target users and evidence
  5. Objectives and success metrics
  6. Proposed solution and alternatives
  7. Scope: in, out, later
  8. Requirements at BRD level
  9. Dependencies and constraints
  10. Risks and mitigations
  11. Milestones and ownership
  12. Post-launch validation
  13. Open questions

© 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 3 other files (references, assets) in skills/write-brd of digoal/blog.

  • SKILL.md
  • agents/openai.yaml
  • assets/brd-template.md
  • references/brd-writing-guide.md

Open the folder on GitHubat commit 69fb793

Compare with similar skills

Write Brd 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.

Write Brd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Write Brd this skilldigoal/blog8.6k—~1.4kAutomated safety check: PassGPL-2.0
Markdown Mermaid Writingneflibata-feng/MyArxiv-Agent1265 repos~3.8kAutomated safety check: NotesApache-2.0
Design Decknicobailon/pi-design-deck291—~4.3kAutomated safety check: PassNone
Chatbot Mvp Distillationpdsuwwz/chatgpt-vue3-light-mvp578—~722Automated safety check: PassMIT
Chatbot Mvp Distillation Zhpdsuwwz/chatgpt-vue3-light-mvp578—~414Automated safety check: PassMIT
Markdown Mermaid WritingK-Dense-AI/scientific-agent-skills48k1 repos~4.2kAutomated safety check: NotesApache-2.0

Similar skills

  • Markdown Mermaid Writing

    neflibata-feng/MyArxiv-Agent

    Comprehensive markdown and Mermaid diagram writing skill that establishes text-based diagrams as the DEFAULT documentation standard.

    126 GitHub starsUsed in 5 repos~3.8k tokens
    DevelopmentAuto-check: notes
  • Design Deck

    nicobailon/pi-design-deck

    Present visual options for architecture, UI, and code decisions with high-fidelity side-by-side previews.

    291 GitHub stars~4.3k tokensUpdated 2 mo ago
    Product & Project ManagementAuto-check passed
  • Chatbot Mvp Distillation

    pdsuwwz/chatgpt-vue3-light-mvp

    Distill the chatgpt-vue3-light-mvp project into reusable architecture for building similar ChatGPT-style web products in other repositories.

    578 GitHub stars~722 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Chatbot Mvp Distillation Zh

    pdsuwwz/chatgpt-vue3-light-mvp

    将 chatgpt-vue3-light-mvp 项目蒸馏为可迁移到其他项目的中文架构指南。适用于设计或实现类似 ChatGPT 的 Web 对话产品,包括 SSE/fetch 流式响应、模型适配器契约、打字机渲染、Markdown/代码/KaTeX/Mermaid 渲染、推理过程展示,以及从本 Vue 3 MVP 迁移到其他项目的方案规划。

    578 GitHub stars~414 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Markdown Mermaid Writing

    K-Dense-AI/scientific-agent-skills

    Writes scientific Markdown documentation and Mermaid diagrams for workflows, relationships, timelines, and schemas.

    48k GitHub starsUsed in 1 repo~4.2k tokens
    DevelopmentAuto-check: notes
  • Power Platform Architect

    github/awesome-copilot

    Official

    A skill your agent uses when the user needs to transform business requirements, use case descriptions, or meeting transcripts into a technical Power Platform solution architecture, including…

    40k GitHub starsUsed in 1 repo~3.6k tokens
    DevelopmentAuto-check passed

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 10 days ago
    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 10 days ago
    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 10 days ago
    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 10 days ago
    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 10 days ago
    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 10 days ago
    Auto-check passed

Works with

Questions about Write Brd

What does Write Brd do?

Write a practical Business Requirements Document (BRD) from a product idea, feature concept, customer request, business problem, or rough product opportunity. Write Brd is an agent skill from digoal/blog. Write a practical Business Requirements Document (BRD) from a product idea, feature concept, customer request, business problem, or rough product opportunity.

When should I use Write Brd?

Write Brd fits situations like: the user asks to write; save a BRD/business requirements document/product business case in Markdown; especially when the output should be saved under the current projects markdown directory and include diagrams using Mermaid.

How do I install Write Brd in Claude Code?

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

How do I install Write Brd in Codex?

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

Can I use Write Brd 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 write-brd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/write-brd, .gemini/skills/write-brd, .github/skills/write-brd and .opencode/skills/write-brd in your project.

What does Write Brd need to run?

SKILL.md names no scripts, command-line tools or credentials: Write Brd is instructions for the agent only.

Does Write Brd 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 Write Brd 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 Write Brd use?

Write Brd 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 Write Brd use?

About 1.4k tokens (SKILL.md is roughly 5.8k 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 1.4k tokens, read only when the agent opens those files.

What are the alternatives to Write Brd?

Skills that share tags, products or a category with Write Brd: Markdown Mermaid Writing (neflibata-feng/MyArxiv-Agent, 126 stars), Design Deck (nicobailon/pi-design-deck, 291 stars), Chatbot Mvp Distillation (pdsuwwz/chatgpt-vue3-light-mvp, 578 stars) and Chatbot Mvp Distillation Zh (pdsuwwz/chatgpt-vue3-light-mvp, 578 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Write Brd?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,587 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on September 28, 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.