prd-writer

prd-writer is a skill for Claude Code from rtazima/claude-proj-blueprint. It costs 56 tokens per session (1,099 once invoked), scanned A, original, MIT.

A workflow for writing product requirement documents (PRDs), which describe what a feature should do, why it is needed, and how to verify it.

In plain words
What is it for?
Use it to draft or refine feature requirements, define what is out of scope, search earlier product decisions, and save the PRD in the project’s product-documents folder.
Why use it?
It turns rough ideas into a scoped document with clear user needs and testable acceptance criteria, while checking for related existing plans.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to draft or refine feature requirements, define what is out of scope, search earlier product decisions, and save the PRD in the project’s product-documents folder.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rtazima/claude-proj-blueprint/prd-writer
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.

Any agent
npx skills add rtazima/claude-proj-blueprint --skill prd-writer
Clone the repo
git clone --depth 1 https://github.com/rtazima/claude-proj-blueprint

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prd-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/prd-writer/github.svg)](https://agentmods.dev/skills/rtazima/claude-proj-blueprint/prd-writer)
Your own site
<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/prd-writer"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/prd-writer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prd-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/prd-writer"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/prd-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,099 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00056 $0.01099
Opus 5 $0.00028 $0.00549
Sonnet 5 $0.00011 $0.00220
Haiku 4.5 $0.00006 $0.00110

Measured 10d ago against content hash a9a05211f3cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prd-writer 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 10d 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.

.claude/skills/prd-writer/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Writer

Turn rough ideas into structured PRDs following the project's template. The PRD is the single source of truth for what to build and why.

Rules

  1. Always use the template — read docs/product/_template-prd.md first
  2. Clarify before writing — ask questions if the idea is ambiguous (max 5 questions)
  3. Scope aggressively — define what is OUT of scope as clearly as what is IN scope. The "Not Doing" list is arguably the most valuable part of the PRD
  4. User stories over descriptions — "As a [user], I want [action], so that [benefit]"
  5. Acceptance criteria are testable — each criterion must be verifiable by running code
  6. Check memory first — search for past features that might overlap or inform this one
  7. Reference, don't duplicate — link to ADRs, specs, and existing PRDs with [[wiki-links]]
  8. Output to docs/product/ — never create PRDs elsewhere

Workflow

Phase 1: Understand the idea

  1. Read the user's description / rough idea
  2. Search memory for related past features: python memory/query.py "[topic]"
  3. Check existing PRDs in docs/product/ for overlap
  4. If the idea is vague, ask up to 5 clarifying questions:
    • Who is the target user?
    • What problem does this solve?
    • What does "done" look like?
    • Are there constraints (timeline, tech, regulatory)?
    • What is explicitly out of scope?

Phase 2: Draft the PRD

Read the template and fill in every section:

  1. Context — why now? What triggered this feature?
  2. Objective — one sentence: what this feature will accomplish
  3. Scope
    • Includes: specific deliverables
    • Excludes: what this PRD does NOT cover (critical for preventing scope creep)
  4. "Not Doing" list — explicitly document what you chose NOT to build and why. This is arguably the most valuable section: it prevents scope creep and aligns expectations.
    ## Not Doing (and why)
    - **Multi-language support** — not needed for MVP; all users are PT-BR
    - **Admin dashboard** — managed via database until user count justifies UI
    - **Email notifications** — WhatsApp is the primary channel; email adds complexity without value
    
  5. User stories — 3-7 stories in As a... I want... So that... format
  6. Design — reference Figma link OR note "use design tokens" for agent flow
  7. Acceptance criteria — numbered, testable statements:
    • AC-1: When [condition], then [expected result]
    • Each must be verifiable by running a test or checking behavior
  8. Technical decisions — link to existing ADRs or note that new ones are needed
  9. Impact on specs — check each active spec module:
    • Compliance: personal data? Legal basis needed?
    • Security: new attack surface? Auth changes?
    • Observability: new metrics/alerts needed?
    • Scalability: performance impact?
    • Accessibility: WCAG compliance needed?
    • i18n: new strings to translate?
    • Skip modules that don't apply
  10. Rollout — feature flags, migration plan, rollback strategy

Read the full file on GitHub · 93 lines

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. 10d ago First seen · 93 lines · 56 tokens per session scan A a9a05211f3cc

Subscribe to this mod's changes

prd-writer is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,099 once invoked, about $0.0003 per session on Opus 5. 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.