Agent skill

Prd Master

by majiayu000 in majiayu000/spellbook

PRD writing and product definition expert. An agent skill from majiayu000/spellbook.

MITAuto-check passedProduct & Project Management

Install Prd Master

skills CLI
$ npx skills add majiayu000/spellbook --skill prd-master -a claude-code

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

GitHub CLI
$ gh skill install majiayu000/spellbook prd-master --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/majiayu000/spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prd-master .claude/skills/prd-master && 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
prd-master
GitHub stars
287
Token cost
~3.4k tokens
SKILL.md length
418 words
Files
6
Skills in repo
97
Repo updated
First seen
Licence
MIT

At a glance

PRD writing and product definition expert. An agent skill from majiayu000/spellbook.

  • Works in 3 steps: Survey users with paired questions → Categorize responses: Basic,… → Prioritize: Cover basics first, then…
  • Acceptance criteria
  • SKILL.md covers Core Principles, Hard Rules (Must Follow), Quick Reference and PRD Structure, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prd Master is an agent skill from majiayu000/spellbook. PRD writing and product definition expert. Use when writing PRDs, user stories, acceptance criteria, or prioritizing features. Covers RICE/MoSCoW frameworks, agile requirements, and specification best practices.

Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files (for example `reference/acceptance-criteria.md`, `reference/extended.md` and `reference/prioritization.md`).

It sits in Product & Project Management, covering PRD writing, User stories and Prioritization frameworks. The repository describes itself as: Cross-runtime skills for Claude Code, Codex, and multi-agent workflows. The licence is MIT.

When your agent uses it

  • Acceptance criteria
  • Prioritizing features

Example prompts

  • “/prd-master”

Workflow steps

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

  1. Survey users with paired questions
  2. Categorize responses: Basic, Performance, Delighter, Indifferent
  3. Prioritize: Cover basics first, then performance, then delighters

What it can do on your machine

Read from SKILL.md and the folder at commit ed52af7. 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 (its code samples are markdown and gherkin).

    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

Prd Master loads about 3.4k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 418 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k

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 majiayu000/spellbook at commit ed52af7, republished under its MIT licence (© majiayu000). 418 words, ~3,357 tokens.

Download SKILL.mdSave it as .claude/skills/prd-master/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
prd-master
description
PRD writing and product definition expert. Use when writing PRDs, user stories, acceptance criteria, or prioritizing features. Covers RICE/MoSCoW frameworks, agile requirements, and specification best practices.

PRD Master

Core Principles

  • Living Document — PRDs evolve throughout product lifecycle
  • Stakeholder Collaboration — Early involvement prevents late rework
  • Measurable Goals — Replace vague with quantifiable targets
  • Focused yet Flexible — Lean structure enables adaptation
  • Problem-First — Define the problem before jumping to solutions
  • User-Centered — Ground decisions in user research and data

Hard Rules (Must Follow)

These rules are mandatory. Violating them means the skill is not working correctly.

No Vague Metrics

All metrics and requirements must be quantifiable. Vague descriptions are forbidden.

❌ FORBIDDEN:
- "The app should be fast"
- "Support many users"
- "Good user experience"
- "The system should be reliable"
- "Easy to use interface"

✅ REQUIRED:
- "Page load time < 2s on 4G, < 500ms on WiFi (P95)"
- "Support 10,000 concurrent users with 99.9% uptime"
- "NPS > 50, Task completion rate > 85%"
- "99.9% availability, MTTR < 1 hour"
- "User can complete checkout in < 3 clicks"
Problem Before Solution

Never propose a solution without clearly defining the problem first.

❌ FORBIDDEN:
"We should add a search bar to the navigation"

✅ REQUIRED:
"Problem: Users can't find products quickly (40% exit rate on catalog).
They need a way to filter 1000+ products by attributes.
Proposed solutions: search bar, smart filters, AI recommendations."
INVEST-Compliant Stories

All user stories must pass the INVEST criteria checklist.

❌ FORBIDDEN:
- Dependent stories that can't be delivered independently
- Stories without acceptance criteria
- Stories too large to complete in one sprint
- Stories without clear user value

✅ REQUIRED:
- [ ] Independent — Can be delivered alone
- [ ] Negotiable — Details can be discussed
- [ ] Valuable — Clear user/business value
- [ ] Estimable — Team can estimate effort
- [ ] Small — Fits in one sprint
- [ ] Testable — Has acceptance criteria

Quick Reference

When to Use What
ScenarioApproachTool/Framework
Feature prioritizationScoring modelRICE, ICE
Release planningMust/Should/Could/Won'tMoSCoW
Customer satisfactionDelight vs basicsKano Model
Sprint planningUser stories + BDDGiven-When-Then
Complex requirementsTraditional PRDFull template
Agile iterationLean requirementsUser stories + acceptance criteria

PRD Structure

Essential Components
markdown
## 1. Executive Summary
- Problem statement (2-3 sentences)
- Proposed solution (1-2 sentences)
- Success metrics (3-5 key metrics)

## 2. Context & Background
- Why now? Market opportunity or user pain
- Strategic alignment with company goals
- What happens if we don't build this?

## 3. Goals & Success Metrics
- Business objectives (revenue, retention, growth)
- User objectives (satisfaction, engagement)
- Success criteria (quantifiable targets)

## 4. Target Users & Personas
- Primary users (who benefits most?)
- Secondary users (indirect beneficiaries)
- User needs, pain points, motivations
- Jobs to be done

## 5. User Stories & Use Cases
- Core user flows
- Edge cases and error scenarios
- Integration with existing features

## 6. Requirements
- Functional requirements (what it does)
- Non-functional requirements (performance, security)
- Acceptance criteria (how we verify)

## 7. Out of Scope
- What we're explicitly NOT building
- Future considerations for later phases

## 8. Design & UX
- Link to design files (Figma, etc.)
- Key design decisions
- Accessibility requirements (WCAG 2.2 AA)

## 9. Technical Considerations
- Architecture overview
- Dependencies and integrations
- Data model changes
- API contracts

## 10. Rollout & Launch Plan
- Phased rollout strategy
- Feature flags and A/B tests
- Monitoring and alerts
- Rollback plan

## 11. Open Questions & Risks
- Unknowns requiring research
- Technical risks and mitigations
- Dependencies on other teams

User Story Writing

Standard Format
As a [persona/role],
I want to [action/goal],
So that [benefit/value].
The Three C's
Card          — Brief description on index card
              → Captures essence, not details
              → Placeholder for conversation

Conversation  — Discussion between team members
              → Explore edge cases
              → Clarify assumptions
              → Uncover hidden requirements

Confirmation  — Acceptance criteria
              → Defines "done"
              → Testable conditions
              → Given-When-Then format
INVEST Criteria
Independent   — Story stands alone, minimal dependencies
Negotiable    — Details emerge through conversation
Valuable      — Delivers value to users or business
Estimable     — Team can estimate effort
Small         — Completable within one sprint
Testable      — Clear acceptance criteria
Examples
markdown
## Good User Stories

### Feature: Password Reset
As a user who forgot my password,
I want to reset it via email,
So that I can regain access to my account without contacting support.

**Acceptance Criteria:**
- Given I'm on the login page
- When I click "Forgot Password"
- Then I see a form requesting my email address

- Given I've entered my registered email
- When I submit the form
- Then I receive a password reset link within 2 minutes

- Given I click the reset link within 24 hours
- When I set a new password (min 8 chars, 1 number, 1 symbol)
- Then I'm logged in automatically

### Feature: Bulk Upload
As a content manager,
I want to upload multiple products via CSV,
So that I can save time compared to manual entry.

**Acceptance Criteria:**
- Given I'm on the products page
- When I click "Bulk Upload" and select a CSV file
- Then the system validates the file format (max 10MB, .csv only)

- Given the CSV has 1000 rows
- When I start the upload
- Then I see a progress bar showing completion percentage

- Given the upload completes
- When I view the results
- Then I see: success count, error count, downloadable error report
Common Mistakes
❌ Too technical
"As a user, I want the API to return a 200 status code"
→ Focus on user benefit, not implementation

❌ Too vague
"As a user, I want the system to be fast"
→ Define measurable performance targets

❌ Missing the "so that"
"As a user, I want to filter products by price"
→ Add the value: "so that I can find items within my budget"

❌ Too large (Epic)
"As a user, I want a complete e-commerce checkout experience"
→ Break into smaller stories: cart, address, payment, confirmation

Acceptance Criteria

Given-When-Then (BDD Format)
Given [precondition/context]
When [action/trigger]
Then [expected outcome]

And [additional context/outcome]
Best Practices
✓ Keep scenarios focused (one behavior per scenario)
✓ Maintain clear separation of Given/When/Then
✓ Avoid UI-specific details (test behavior, not implementation)
✓ Make criteria testable and measurable
✓ Include both happy path and edge cases
✓ Use real user interactions, not hypothetical
Examples
gherkin
## E-commerce Checkout

Scenario: Successful payment with saved card
  Given I have items in my cart
  And I'm logged in with a saved payment method
  When I click "Place Order"
  Then I see an order confirmation page
  And I receive a confirmation email within 2 minutes
  And my cart is emptied

Scenario: Payment declined
  Given I'm at the payment step
  When I submit payment and the card is declined
  Then I see an error message: "Payment declined. Please try another card."
  And I remain on the payment page
  And my cart items are preserved

Scenario: Session timeout during checkout
  Given I've been idle for 30 minutes
  When I attempt to place an order
  Then I'm redirected to login
  And my cart items are preserved after re-authentication

## Search Feature

Scenario: Search with results
  Given I'm on the homepage
  When I search for "laptop"
  Then I see results within 500ms
  And results are ranked by relevance
  And I see result count: "Showing 1-20 of 156 results"

Scenario: Search with no results
  Given I'm on the search page
  When I search for "xyznonexistent"
  Then I see "No results found for 'xyznonexistent'"
  And I see search suggestions or alternative queries
Alternative Format: Checklist
markdown
For simpler features, use a checklist:

## File Upload Acceptance Criteria
- [ ] Supports formats: PDF, DOCX, XLSX (max 10MB each)
- [ ] Shows upload progress bar
- [ ] Displays file name and size after upload
- [ ] Allows removal of uploaded files
- [ ] Shows error message for unsupported formats
- [ ] Shows error message for files exceeding size limit
- [ ] Scans files for malware before processing
- [ ] Works on mobile (iOS Safari, Android Chrome)

Prioritization Frameworks

RICE Scoring
RICE Score = (Reach × Impact × Confidence) / Effort

Reach      — How many users affected per time period?
             (users/quarter, transactions/month)
Impact     — How much does it improve their experience?
             3 = Massive, 2 = High, 1 = Medium, 0.5 = Low, 0.25 = Minimal
Confidence — How certain are we?
             100% = High data, 80% = Medium, 50% = Low
Effort     — Person-months required
             (engineering + design + PM time)

Example:

FeatureReachImpactConfidenceEffortRICE Score
Password reset5000/month3100%115,000
Dark mode10000/month0.580%22,000
Export to PDF500/month250%0.51,000

When to use: Managing many ideas, need quantitative comparison, have user data.


ICE Scoring
ICE Score = (Impact + Confidence + Ease) / 3

Impact     — 1-10: How much business/user value?
Confidence — 1-10: How certain are we?
Ease       — 1-10: How easy to implement? (10 = very easy)

Example:

FeatureImpactConfidenceEaseICE Score
One-click login9867.7
AI recommendations10536.0
Email notifications6998.0

When to use: Quick prioritization, weekly grooming, growth experiments, speed over precision.


Show full SKILL.md (156 more words)Show less
MoSCoW Method
Must Have      — Critical for launch, non-negotiable
                 Without this, the product fails

Should Have    — Important but not vital
                 Painful to omit, but workarounds exist

Could Have     — Nice to have, "vitamins not painkillers"
                 Include if time/resources allow

Won't Have     — Explicitly out of scope
                 Defer to future releases

Example: MVP E-commerce Site

Must HaveShould HaveCould HaveWon't Have
Product listingProduct reviewsWishlistAR try-on
Shopping cartRelated productsGift wrappingLive chat
CheckoutOrder trackingDiscount codesLoyalty program
Payment (Stripe)Email receiptsSocial sharingMobile app
User accountsGuest checkoutProduct comparisonSubscriptions

When to use: Sprint planning, MVP scoping, release boundaries, stakeholder alignment.


Kano Model
Basic Needs       — Must-haves, assumed by users
                    Absence = dissatisfaction, presence = neutral
                    Example: Website loads, checkout works

Performance       — More is better, linear satisfaction
                    Example: Faster page load, more payment options

Delighters        — Unexpected features that wow
                    Absence = neutral, presence = delight
                    Example: Free shipping, personalized recommendations

Indifferent       — Users don't care either way
                    Example: Animated logo, theme customization

When to use: Customer-driven decisions, balancing basics vs innovation, UX improvements.

Process:

  1. Survey users with paired questions:
    • "How would you feel if we HAD feature X?"
    • "How would you feel if we DIDN'T have feature X?"
  2. Categorize responses: Basic, Performance, Delighter, Indifferent
  3. Prioritize: Cover basics first, then performance, then delighters

Hybrid Approach
Best practice: Combine frameworks

1. Use MoSCoW to define release scope
   → Separate must-haves from nice-to-haves

2. Use RICE to rank must-haves
   → Sequence within release based on impact

3. Use Kano to ensure balance
   → Don't over-invest in basics, under-invest in delight

Example:
- All "Must Have" items → Score with RICE → Build in RICE order
- Validate with Kano → Ensure we have delighters, not just basics

Extended Reference

Detailed material starting at ## Agile Requirements Management has been moved to reference/extended.md to keep this skill concise. Load that reference when the task requires the moved examples, command catalogs, checklists, platform details, or implementation templates.

© majiayu000, MIT. 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 in skills/prd-master of majiayu000/spellbook.

  • SKILL.md
  • reference/acceptance-criteria.md
  • reference/extended.md
  • reference/prioritization.md
  • reference/user-stories.md
  • templates/prd-template.md

Open the folder on GitHubat commit ed52af7

Compare with similar skills

Prd Master 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.

Prd Master compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prd Master this skillmajiayu000/spellbook287—~3.4kAutomated safety check: PassMIT
Bmad Prdaj-geddes/claude-code-bmad-skills488—~1.8kAutomated safety check: NotesCustom licence
Extract Featuresnurettincoban/ai-prd-workflow298—~1kAutomated safety check: PassMIT
Oma Pmfirst-fluke/oh-my-agent1.3k—~1.9kAutomated safety check: PassMIT
Requirement SummarizerArabelaTso/Skills-4-SE253—~1.8kAutomated safety check: PassApache-2.0
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT

Similar skills

  • Bmad Prd

    aj-geddes/claude-code-bmad-skills

    PRD facilitator (John the PM). An agent skill from aj-geddes/claude-code-bmad-skills.

    488 GitHub stars~1.8k tokensUpdated 3 mo ago
    Product & Project ManagementAuto-check: notes
  • Extract Features

    nurettincoban/ai-prd-workflow

    Turn PRD.md into FEATURES.md: permanent feature IDs, MoSCoW priorities, acceptance criteria and the PRD requirement each feature comes from.

    298 GitHub stars~1k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Oma Pm

    first-fluke/oh-my-agent

    Turn product requirements into scoped tasks with dependencies and acceptance criteria.

    1.3k GitHub stars~1.9k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Requirement Summarizer

    ArabelaTso/Skills-4-SE

    Extract and summarize core features, constraints, and priorities from requirement documents.

    253 GitHub stars~1.8k tokensUpdated 1 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
  • Agile Product Owner

    alirezarezvani/claude-skills

    Writes INVEST-checked user stories with acceptance criteria, splits epics, plans sprints from velocity and ranks the backlog with a weighted score.

    28k GitHub starsUsed in 3 repos~3.2k tokens
    Product & Project ManagementAuto-check passed

More from majiayu000/spellbook

All 97 skills in this repo
  • Skill Ecosystem Doctor

    majiayu000/spellbook

    Audits and repairs how coding-agent Skills are owned, copied and exposed across runtimes, from canonical sources to quarantine and retirement.

    287 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed
  • AGENTS.md Scaffold

    majiayu000/spellbook

    Scans a repository for real evidence and proposes, or on request writes, a small stack of root and scoped AGENTS.md files with validation commands and generated-file boundaries.

    287 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Product Demo Builder

    majiayu000/spellbook

    Plans, produces or diagnoses evidence-backed product demo videos: script, capture plan, pacing checks and verified final media built on real product behavior.

    287 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed
  • Flowguard Task Guard

    majiayu000/spellbook

    Single entry point that routes long or ambiguous agent tasks, checks live state, bounds autonomous loops and leaves a resumable handoff.

    287 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • npm Supply Chain Check

    majiayu000/spellbook

    Scans a repository, its lockfiles and node_modules for known malicious npm package versions and install-time indicators, using a read-only Python scanner.

    287 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Product Manager Toolkit

    majiayu000/spellbook

    Product management helpers: a RICE scoring script, an interview transcript analyzer and PRD templates for prioritizing features, synthesizing research and writing requirements.

    287 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

Questions about Prd Master

What does Prd Master do?

PRD writing and product definition expert. An agent skill from majiayu000/spellbook. Prd Master is an agent skill from majiayu000/spellbook. PRD writing and product definition expert.

When should I use Prd Master?

Prd Master fits situations like: acceptance criteria; prioritizing features.

How do I install Prd Master in Claude Code?

Run `npx skills add majiayu000/spellbook --skill prd-master -a claude-code`. Or copy the skill folder (skills/prd-master in majiayu000/spellbook) into .claude/skills/prd-master in your project. Claude Code loads it when a task matches its description.

How do I install Prd Master in Codex?

Run `npx skills add majiayu000/spellbook --skill prd-master -a codex`. Or copy the skill folder (skills/prd-master in majiayu000/spellbook) into .agents/skills/prd-master in your project. Codex loads it when a task matches its description.

Can I use Prd Master 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 majiayu000/spellbook --skill prd-master -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prd-master, .gemini/skills/prd-master, .github/skills/prd-master and .opencode/skills/prd-master in your project.

What does Prd Master need to run?

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

Does Prd Master 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 Prd Master 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 Prd Master use?

Prd Master is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prd Master use?

About 3.4k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prd Master?

Skills that share tags, products or a category with Prd Master: Bmad Prd (aj-geddes/claude-code-bmad-skills, 488 stars), Extract Features (nurettincoban/ai-prd-workflow, 298 stars), Oma Pm (first-fluke/oh-my-agent, 1.3k stars) and Requirement Summarizer (ArabelaTso/Skills-4-SE, 253 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prd Master?

majiayu000 (a GitHub user) maintains it in majiayu000/spellbook, which has 287 GitHub stars. The repository holds 97 skills in this directory. The repository was last updated on October 8, 2026.

Source: majiayu000/spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.