Agent skill

Write Mrd

by digoal in digoal/blog

Generate a market requirements document (MRD) from a product idea and save it as Markdown under the current project's markdown/ directory.

GPL-2.0Auto-check passedProduct & Project Management

Install Write Mrd

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

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

GitHub CLI
$ gh skill install digoal/blog write-mrd --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-mrd .claude/skills/write-mrd && 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-mrd
GitHub stars
8.6k
Token cost
~1.2k tokens
SKILL.md length
584 words
Files
4 (incl. references, assets)
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

Generate a market requirements document (MRD) from a product idea and save it as Markdown under the current project's markdown/ directory.

  • Works in 6 steps: Normalize the idea → Choose MRD depth → Build the MRD argument → …
  • The user asks to write
  • SKILL.md covers Purpose, Inputs, Required Workflow and MRD Writing Rules, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Write Mrd is an agent skill from digoal/blog. Generate a market requirements document (MRD) from a product idea and save it as Markdown under the current project's markdown/ directory. Use when the user asks to write, draft, create, produce, or refine an MRD, market requirements document, product opportunity document, market demand analysis, product idea validation document, or asks for "写 MRD", "市场需求文档", "产品立项文档", "产品机会分析", especially when input is only an idea and the output should be structured, visual, and decision-oriented.

Its SKILL.md is about 1.2k 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/mrd-template.md` and `references/mrd-playbook.md`).

It sits in Product & Project Management, covering PRD writing 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

  • The user asks to write
  • Market requirements document
  • Product opportunity document
  • Market demand analysis

Example prompts

  • “市场需求文档”
  • “产品立项文档”
  • “产品机会分析”
  • “/write-mrd”

Workflow steps

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

  1. Normalize the idea
  2. Choose MRD depth
  3. Build the MRD argument
  4. Add useful visuals
  5. Save files
  6. Self-check before final response

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 Mrd loads about 1.2k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 125 tokens; SKILL.md has 584 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~125
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

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). 584 words, ~1,193 tokens.

Download SKILL.mdSave it as .claude/skills/write-mrd/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
write-mrd
description
Generate a market requirements document (MRD) from a product idea and save it as Markdown under the current project's markdown/ directory. Use when the user asks to write, draft, create, produce, or refine an MRD, market requirements document, product opportunity document, market demand analysis, product idea validation document, or asks for "写 MRD", "市场需求文档", "产品立项文档", "产品机会分析", especially when input is only an idea and the output should be structured, visual, and decision-oriented.

Write MRD

Purpose

Turn a product idea into a decision-ready MRD. The MRD must prove why the opportunity is worth pursuing before drifting into PRD-level feature details.

Default output: a Markdown file saved to the current project's markdown/ directory. Create the directory if missing.

Inputs

Accept any of these:

  • A one-line product idea.
  • A product concept plus target users, market, competitors, or business model.
  • A rough draft MRD to rewrite.
  • A request to generate a lightweight MRD, full MRD, or opportunity analysis.

If the idea is understandable but incomplete, proceed and mark missing facts as Assumptions or To Validate. Ask a question only when the product idea, target user, and use scenario are all too ambiguous to infer.

Required Workflow

  1. Normalize the idea

    • Extract product name or working title, target customer, user scenario, pain point, existing alternatives, proposed value, business goal, and unknowns.
    • If the user gives no title, create a concise Chinese or English title from the idea.
  2. Choose MRD depth

    • Use a lightweight MRD for small features, early exploration, or vague ideas.
    • Use a full MRD for new products, new markets, major capabilities, monetization changes, or user requests for complete/正式 MRD.
    • In both cases, keep MRD distinct from PRD: MRD explains why worth doing, PRD explains how exactly to build.
  3. Build the MRD argument

    • Follow references/mrd-playbook.md for the writing logic.
    • Use assets/mrd-template.md as the output skeleton when useful.
    • Do not mechanically fill every field if evidence is weak; label assumptions and validation needs clearly.
  4. Add useful visuals

    • Include at least one diagram in every MRD.
    • Prefer Mermaid for opportunity flow, user journey, stakeholder map, decision tree, or metric logic.
    • ASCII text is acceptable for compact comparisons or small decision paths.
    • If SVG is best, save it as a separate .svg file in the same markdown/ directory and reference it from the MRD with ![description](filename.svg).
    • Diagrams must clarify reasoning, not decorate the article.
  5. Save files

    • File naming:
      • Chinese: markdown/<产品或主题>-MRD-<YYYYMMDD>.md
      • English: markdown/<product-or-topic>-mrd-<YYYYMMDD>.md
    • Use kebab-case or compact Chinese names; avoid spaces.
    • If generating SVG, name it markdown/<same-prefix>-figure-1.svg, figure-2.svg, etc.
    • Include source links when web/current facts are used.
  6. Self-check before final response

    • The MRD answers: target customer, scenario pain, existing alternatives, market opportunity, differentiation, high-level capabilities, success metrics, risks, and falsification conditions.
    • It does not over-specify UI, APIs, database schemas, or detailed implementation unless the user explicitly asks.
    • It contains at least one visual.
    • It names assumptions and unknowns instead of pretending uncertain facts are known.
    • It ends with a concrete validation/watchlist section.
    • The Markdown file exists in markdown/; any SVG references point to existing files.
Show full SKILL.md (154 more words)Show less

MRD Writing Rules

  • Start from the market problem, not the feature list.
  • Treat MRD as a "market bet memo": it should help the organization decide whether to invest.
  • Use concrete user scenarios: "who is blocked, when, by what, and what they do now."
  • Write high-level capabilities, not button-level implementation.
  • Include "not doing now" to prevent scope creep.
  • Use measurable signals: adoption, retention, conversion, task success, paid intent, sales cycle, support load, or cost saved.
  • Include falsification: what evidence would make the team stop, narrow, or rethink the idea.

Optional Web Research

For current market size, regulations, competitor claims, pricing, recent product launches, or funding/news, browse and cite reliable sources. If browsing is unavailable or unnecessary, write "market data pending verification" rather than inventing numbers.

Final Response

Keep the final reply short:

  • Link to the generated MRD file.
  • Link to generated SVG files if any.
  • Mention whether assumptions were made or web research was used.

© 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-mrd of digoal/blog.

  • SKILL.md
  • agents/openai.yaml
  • assets/mrd-template.md
  • references/mrd-playbook.md

Open the folder on GitHubat commit 69fb793

Compare with similar skills

Write Mrd 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 Mrd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Write Mrd this skilldigoal/blog8.6k—~1.2kAutomated safety check: PassGPL-2.0
Use Case Writerphucnt-bazone-vietnam/use-case-writer142—~4.1kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Trellis Brainstormanjiemo/SunnyBeach1787 repos~4kAutomated safety check: PassApache-2.0
Adversarial Speczscole/adversarial-spec5561 repos~8.3kAutomated safety check: NotesMIT

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).

    142 GitHub stars~4.1k tokensUpdated 4 mo ago
    Product & Project ManagementAuto-check passed
  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Ralph Tui Create Beads

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed
  • Trellis Brainstorm

    anjiemo/SunnyBeach

    Guides collaborative requirements discovery before implementation.

    178 GitHub starsUsed in 7 repos~4k tokens
    Product & Project ManagementAuto-check passed
  • Adversarial Spec

    zscole/adversarial-spec

    Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree.

    556 GitHub starsUsed in 1 repo~8.3k tokens
    Product & Project ManagementAuto-check: notes
  • Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).

    2.5k GitHub starsUsed in 1 repo~2.8k tokens
    Product & Project ManagementAuto-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

Questions about Write Mrd

What does Write Mrd do?

Generate a market requirements document (MRD) from a product idea and save it as Markdown under the current project's markdown/ directory. Write Mrd is an agent skill from digoal/blog. Generate a market requirements document (MRD) from a product idea and save it as Markdown under the current project's markdown/ directory.

When should I use Write Mrd?

Write Mrd fits situations like: the user asks to write; market requirements document; product opportunity document; market demand analysis.

How do I install Write Mrd in Claude Code?

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

How do I install Write Mrd in Codex?

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

Can I use Write Mrd 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-mrd -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-mrd, .gemini/skills/write-mrd, .github/skills/write-mrd and .opencode/skills/write-mrd in your project.

What does Write Mrd need to run?

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

Does Write Mrd 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 Mrd 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 Mrd use?

Write Mrd 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 Mrd use?

About 1.2k tokens (SKILL.md is roughly 4.8k 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 Mrd?

Skills that share tags, products or a category with Write Mrd: Use Case Writer (phucnt-bazone-vietnam/use-case-writer, 142 stars), CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars) and Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Write Mrd?

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.