Agent skill

Prd Template

by mohitagw15856 in mohitagw15856/pm-claude-skills

Create a Product Requirements Document following proven PM template structure.

MITAuto-check passedProduct & Project Management

Install Prd Template

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill prd-template -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills prd-template --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prd-template .claude/skills/prd-template && 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-template
GitHub stars
1.4k
Token cost
~3k tokens
SKILL.md length
1,194 words
Files
4 (incl. references)
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Create a Product Requirements Document following proven PM template structure.

  • Works in 9 steps: Overview → Context & Background → User Stories & Use Cases → …
  • Asked to write a PRD
  • SKILL.md covers Where this sits — the middle…, The loop, Required Inputs and Reads from / Writes to the Brain, plus 9 more sections
  • Calls python3

What it does

Prd Template is an agent skill from mohitagw15856/pm-claude-skills. Create a Product Requirements Document following proven PM template structure. Use when asked to write a PRD, product spec, feature specification, or requirements document for a new feature or product. Produces a complete PRD with problem statement, user stories, functional requirements, technical considerations, and success metrics.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/success-metrics-guide.md`, `references/worked-example.md` and `templates/prd-skeleton.md`).

It sits in Product & Project Management, covering PRD writing. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked to write a PRD
  • Feature specification
  • Requirements document for a new feature

Example prompts

  • “/prd-template”

Requirements

  • Python 3

Workflow steps

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

  1. Overview
  2. Context & Background
  3. User Stories & Use Cases
  4. Requirements
  5. Design & User Experience
  6. Technical Considerations
  7. Implementation Plan
  8. Open Questions
  9. Appendix

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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

    Shell commands in SKILL.md call:

    • python3

    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 Template loads about 3k tokens when it runs, and up to ~7k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 1,194 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7k

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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 1,194 words, ~3,021 tokens.

Download SKILL.mdSave it as .claude/skills/prd-template/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
prd-template
description
Create a Product Requirements Document following proven PM template structure. Use when asked to write a PRD, product spec, feature specification, or requirements document for a new feature or product. Produces a complete PRD with problem statement, user stories, functional requirements, technical considerations, and success metrics.
version
1.0.0

PRD Template Skill

This skill helps create professional Product Requirements Documents following industry best practices.

Where this sits — the middle of the spine

Second in the product-decision spine: /assumption-mapper → prd-template → /rice-prioritisation → /roadmap-narrative. It receives the riskiest assumption from /assumption-mapper (if that ran, read its map instead of re-guessing the risks) and hands /rice-prioritisation the PRD's success metric — the one baselined number that becomes RICE's Impact. Shared terms (problem statement, hypothesis, success metric, provenance) live once in docs/craft/product-decisions.md; use them exactly.

The loop

A PRD is written outside-in — problem before solution, always — in four phases. Phase 1 is load-bearing: a PRD built on a fuzzy problem is polished the whole way down and still wrong.

  1. Lock the problem statement. One sentence: who has what problem, when, and the cost of leaving it. No solution language. Everything below must ladder to this. Done when: the problem statement stands alone with no feature named in it, and a stranger could tell what "solved" means.
  2. Baseline the success metric. The one number that proves the problem got solved — with its current baseline and the move that counts as success. Carry any upstream /assumption-mapper risk here as an Open Question, not a silent bet. Done when: the metric has a baseline (or is explicitly flagged un-baselined), and it measures the problem, not activity.
  3. Draft the sections, each tracing up. Fill the template (below) so every requirement and story traces to the problem statement; drop anything that doesn't. Tag facts with provenance — a guessed number is a [hunch], labeled. Done when: every requirement traces to the problem statement, and every claimed fact carries [data]/[hunch]/[assumption].
  4. Hand off. Surface the success metric and the initiative(s) so /rice-prioritisation can score Impact from this metric, not a re-invented one. Done when: the PRD names the metric and scope /rice-prioritisation would need to score it without re-asking.

Required Inputs

Ask the user for these if not provided:

  • Feature or product name
  • Problem being solved (from the user's perspective)
  • Target user (role, context, what they're trying to accomplish)
  • Success metrics (how will you know it worked?)
  • Scope (MVP vs full vision — what's in and out of scope)
  • Key stakeholders (who needs to review and approve)

Reads from / Writes to the Brain

If a professional-brain (brain/) exists, use it instead of asking for context you already have:

  • Read first: context.md (product, metrics definitions, voice), knowledge/strategy.md (where the product is going), any related hypotheses/ and the matching entities/ feature file. Run python3 ../professional-brain/scripts/brain_query.py ./brain "<feature>" to pull grounded facts, and carry their provenance tags into the PRD (don't present a [hunch] as a settled requirement).
  • Write after: save the feature as/into entities/<feature>.md, log any scoping decision to decisions/, and add new assumptions to hypotheses/. Tag each with its provenance.

Deeper Materials

This skill ships with two support files — use them when they're available:

  • templates/prd-skeleton.md — a fill-in PRD skeleton with a "what good looks like" hint per section. Start from it when the user wants a document to complete themselves rather than a generated draft.
  • references/success-metrics-guide.md — calibration for the Success Metrics section: the four-part metric test, the standard adoption/outcome/business/guardrail set, and the common traps. Consult it whenever writing or reviewing the metrics table.

Template Structure

Every PRD should include these sections in order:

1. Overview
  • Problem Statement: What problem are we solving? (2-3 sentences)
  • Proposed Solution: High-level description of what we're building (2-3 sentences)
  • Success Metrics: How we'll measure success (3-5 key metrics)
2. Context & Background
  • Why Now: Why is this the right time?
  • Strategic Alignment: How does this align with company objectives?
  • User Research Summary: Key insights from research (if applicable)
3. User Stories & Use Cases

Format: "As a [user type], I want to [action] so that [benefit]"

  • Include 3-7 primary user stories
  • Add acceptance criteria for each
4. Requirements

Functional Requirements:

  • Must-have features (P0)
  • Should-have features (P1)
  • Nice-to-have features (P2)

Non-Functional Requirements:

  • Performance expectations
  • Security considerations
  • Accessibility requirements
5. Design & User Experience
  • Link to design mocks or wireframes
  • Key user flows
  • Edge cases and error states
6. Technical Considerations
  • Architecture implications
  • Dependencies on other systems
  • Technical risks and mitigations
7. Implementation Plan
  • Phase 1 (MVP): What goes in first version
  • Phase 2: What comes next
  • Phase 3: Future enhancements
8. Open Questions
  • Decisions that still need to be made
  • Stakeholders to consult
  • Research needed
Show full SKILL.md (479 more words)Show less
9. Appendix
  • Research links
  • Related documents
  • Competitive analysis

Writing Guidelines

Tone: Clear, concise, actionable Audience: Engineers, designers, stakeholders Length: Aim for 3-6 pages for features, 8-12 for products

Best Practices:

  • Use concrete examples over abstractions
  • Include "why" not just "what"
  • Make requirements testable
  • Link to supporting materials
  • Update as decisions are made

What Makes a Good PRD

✅ Do:

  • Write from the user's perspective
  • Include specific success metrics
  • Address edge cases
  • Link to research and data
  • Make trade-offs explicit

❌ Don't:

  • Write implementation details (that's tech spec)
  • Assume everyone has context
  • Leave requirements ambiguous
  • Skip the "why"
  • Forget about accessibility

Scoring Rubric (0–40)

Score any output of this skill before handing it over; 32+ is ship-quality.

Dimension0510
Problem groundingProblem stated from the company's perspective, or asserted with no evidenceUser-framed problem, but the supporting data is vague ("users are frustrated") and research isn't citedProblem is the user's, quantified with current-state data, and Why Now explains what changed; claims trace to cited research
Requirement testabilityRequirements are vague qualities ("fast", "intuitive") a reviewer couldn't verifyMost requirements are concrete, but acceptance criteria are thin and non-functional requirements are boilerplateEvery P0/P1/P2 item and NFR is verifiable (thresholds, percentiles, standards), and each traces to a user story or research finding
Metric rigorSuccess metrics missing, or percentages with no baselineBaselines and targets present, but metrics only measure adoption — nothing would catch the feature succeeding while the business losesEvery metric has baseline → target, the set covers outcome as well as adoption, and at least one guardrail protects against winning the metric while harming the user
Scope & risk honestyMVP and future phases blur together; no open questions listedPhases are separated, but the reasons for the cut-lines are absent and disagreements are smoothed overEach phase boundary has a stated reason, out-of-scope asks are recorded with re-entry conditions, and open questions carry an owner, a deadline, and the cost of each answer

Quality Checks

  • Problem statement is written from the user's perspective (not the company's)
  • Success metrics are specific and measurable
  • User stories include acceptance criteria
  • Requirements are testable (not vague)
  • Open questions are listed explicitly
  • Implementation plan distinguishes MVP from future phases

Anti-Patterns

  • Do not write requirements from the company's perspective — every requirement must trace back to a user need
  • Do not include vague requirements like "the system should be fast" — every requirement must be testable
  • Do not conflate MVP with future phases — be explicit about what is and is not in scope for the first release
  • Do not leave success metrics as percentages without baselines — specify the current state and the target
  • Do not skip open questions — unresolved assumptions are risks; surfacing them is the PM's job

Example PRD Opening

# PRD: Multi-Channel Customer Support Dashboard

## Overview

**Problem Statement**: Support teams are currently managing customer inquiries across email, chat, and social media using three separate tools, leading to delayed responses, duplicated work, and inconsistent customer experiences. On average, support agents waste 2.3 hours per day switching between tools and manually tracking conversation history.

**Proposed Solution**: Build a unified dashboard that aggregates customer inquiries from all channels into a single interface, maintains conversation history across channels, and provides intelligent routing based on agent expertise and availability.

**Success Metrics**:
- Reduce average response time from 4 hours to 1 hour
- Decrease tool-switching time by 80% (from 2.3 to <0.5 hours)
- Improve customer satisfaction score from 3.8 to 4.5 (out of 5)
- Increase support agent productivity by 35%

## Context & Background

**Why Now**: Customer satisfaction has declined 15% over the past 6 months, primarily due to slow response times. Our top competitor launched a unified support dashboard last quarter, and we're hearing about it in sales calls. Support team turnover is at 45% annually, with "tool complexity" cited as a top frustration.

**Strategic Alignment**: This aligns with our Q1 company objective to "Improve customer retention by 10%" and our support team's OKR to "Reduce average handle time by 25%."

**User Research Summary**: We conducted interviews with 12 support agents and observed 20 hours of support sessions. Key findings:
- Agents spend 35% of their time finding context from previous interactions
- 65% of escalations are due to lack of conversation history
- Agents rated tool-switching as their #1 daily frustration (9.2/10 pain)
- Current NPS for support experience is -12

## User Stories & Use Cases

**US1: Unified Inbox**
As a support agent, I want to see all customer inquiries in one place so that I don't miss urgent requests and can prioritize effectively.

Acceptance Criteria:
- Inbox shows inquiries from email, chat, and social media
- Inquiries are sorted by priority (urgent, high, normal, low)
- Agent can filter by channel, customer, or status
- Real-time updates when new inquiries arrive

**US2: Cross-Channel Context**
As a support agent, I want to see the full conversation history regardless of channel so that I can provide consistent, informed responses without asking customers to repeat themselves.

Acceptance Criteria:
- Timeline view shows all interactions chronologically
- Each interaction displays channel, timestamp, and content
- Customer profile shows demographics and account information
- Previous issues and resolutions are accessible

[Continue with 5-7 total user stories...]

Example Trigger Phrases

  • "Write a PRD."
  • "Write a product spec for this feature."
  • "Write the feature specification."
  • "Write a requirements document for a new feature."

© mohitagw15856, 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 3 other files (references) in skills/prd-template of mohitagw15856/pm-claude-skills.

  • SKILL.md
  • references/success-metrics-guide.md
  • references/worked-example.md
  • templates/prd-skeleton.md

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Prd Template 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 Template compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prd Template this skillmohitagw15856/pm-claude-skills1.4k—~3kAutomated 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
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated safety check: PassMIT
Ralph Tui Create JSONsubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT

Similar skills

  • 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
  • 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
  • Ralph Tui Create JSON

    subsy/ralph-tui

    Convert PRDs to prd.json format 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
  • Prd Generator

    jamesrochabrun/skills

    Generate comprehensive Product Requirements Documents (PRDs) for product managers.

    216 GitHub starsUsed in 2 repos~3.8k tokens
    Product & Project ManagementAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Prd Template

What does Prd Template do?

Create a Product Requirements Document following proven PM template structure. Prd Template is an agent skill from mohitagw15856/pm-claude-skills. Create a Product Requirements Document following proven PM template structure.

When should I use Prd Template?

Prd Template fits situations like: asked to write a PRD; feature specification; requirements document for a new feature.

How do I install Prd Template in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill prd-template -a claude-code`. Or copy the skill folder (skills/prd-template in mohitagw15856/pm-claude-skills) into .claude/skills/prd-template in your project. Claude Code loads it when a task matches its description.

How do I install Prd Template in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill prd-template -a codex`. Or copy the skill folder (skills/prd-template in mohitagw15856/pm-claude-skills) into .agents/skills/prd-template in your project. Codex loads it when a task matches its description.

Can I use Prd Template 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 mohitagw15856/pm-claude-skills --skill prd-template -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-template, .gemini/skills/prd-template, .github/skills/prd-template and .opencode/skills/prd-template in your project.

What does Prd Template need to run?

Going by SKILL.md and its folder, Prd Template needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Prd Template 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 Template 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 Template use?

Prd Template 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 Template use?

About 3k tokens (SKILL.md is roughly 12k 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 4k tokens, read only when the agent opens those files.

What are the alternatives to Prd Template?

Skills that share tags, products or a category with Prd Template: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Ralph Tui Create Beads Rust (subsy/ralph-tui, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prd Template?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.