create-prd

A product requirements document, or PRD, is a written plan for a software feature, architecture choice, or complex bug fix. This guide defines where to save it and which sections it should contain.

In plain words
What is it for?
Use it before building a multi-file feature, making an architectural decision, or fixing a complex bug.
Why use it?
It records the problem, proposed solution, affected files, edge cases, and checks before implementation begins. That gives the work a shared reference across multiple files or layers.

Skill for Claude CodeCodexCursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/waynesutton/markdown-site/create-prd
Any agent
npx skills add waynesutton/markdown-site --skill create-prd
Clone the repo
git clone --depth 1 https://github.com/waynesutton/markdown-site

Made for: Claude Code, Codex, Cursor.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 450 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00450
Opus 5 $0.00000 $0.00225
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 2d ago against content hash ddb54eef2335, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-prd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/create-prd/SKILL.md · 77 lines

What it actually says

Create a PRD

Use this skill before any multi-file feature, architectural decision, or complex bug fix.

Activate with: @create-prd

Location and naming

  • All PRDs live in prds/ folder
  • File name: prds/<feature-or-problem-slug>.md
  • Extension is always .md, not .prd
  • Use kebab-case for the filename (e.g., prds/adding-email-auth.md)

Template

Copy and fill in this template:

# [Feature or problem name]

## Summary

1-2 sentence description of what this is and why it matters.

## Problem

What is broken or missing. Include symptoms, error messages, or user-facing impact.

## Root cause (for bugs)

What actually caused it. Do not skip this for bugs.

## Proposed solution

How to fix or build it. Be specific about the approach chosen and why.

## Files to change

- `path/to/file.ts` - what changes and why
- `convex/schema.ts` - if schema changes are needed

## Edge cases and gotchas

Anything non-obvious that came up during analysis. This section saves the next session.

## Verification

How to confirm the fix or feature works:

- [ ] Step 1
- [ ] Step 2

## Related

Links to related PRDs, issues, or external docs if any.

When to create a PRD

  • 3+ files will change
  • Schema changes are involved
  • Architectural decisions are being made (auth, hosting, data model)
  • A bug required significant investigation to diagnose
  • A feature needs to be referenced later as a migration guide or implementation reference

When to skip a PRD

  • Single file bug fix obvious from logs or types
  • Typo, CSS tweak, or label change
  • Copy change to markdown content

After creating the PRD

  1. Add the feature tasks to TASK.md under ## To Do as checkable items
  2. Reference the PRD path in the TASK.md entry if useful
  3. Begin implementation only after the plan is clear
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 77 lines · 0 tokens per session scan A ddb54eef2335

Subscribe to this mod's changes

create-prd is a skill published in the GitHub repository waynesutton/markdown-site (631 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 450 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

mb-start

Main Branch business router. Detects repo facts, save/sync state, updates, readiness, and live operator intent, then routes to the right skill or CLI contract. Use when the user starts/returns, asks what to do, needs setup, bookkeeping/books, provider setup, save/checkpoint/sync help, repair/update guidance, launch…

noontide-co/mainbranch · 76 tokens

mb-bet

Open, update, close, list, and narrate Main Branch business bets from repo truth. Use when the operator wants to frame an operating bet, track progress, capture a verdict, or draft public-safe narration.

noontide-co/mainbranch · 47 tokens

mb-status

Thin Main Branch status wrapper. Use when the operator asks what changed, what is healthy, what is stale, what to do next, or wants a daily briefing inside Claude Code.

noontide-co/mainbranch · 39 tokens

Jeff Bezos - Operations Flywheel

Jeff Bezos's operational excellence framework: flywheel effect design, input vs output metrics, high-velocity decision making, disagree and commit, and two-pizza team structure — from Amazon shareholder letters and internal operating principles.

OpenLabor/openlabor · 49 tokens

Ray Dalio - Principles Machine

Ray Dalio's systematic management framework: radical transparency, idea meritocracy, believability-weighted decisions, the 5-step process, and pain + reflection = progress — from Principles (2017) and Bridgewater's operating principles.

OpenLabor/openlabor · 54 tokens

Meeting Action Extractor

Extract decisions, action items, owners, deadlines, and follow-ups from meeting transcripts — structured output for project tracking.

OpenLabor/openlabor · 27 tokens