prd-writer

prd-writer is a skill for Claude Code, Codex from stark-ai-de/agent-skills. It costs 56 tokens per session (643 once invoked), scanned A, original, Apache-2.0.

A tool for turning conversation notes, existing documents, and decisions into a product requirements document (PRD) or implementation brief. It organizes the problem, proposed solution, user stories, tests, rollout, and items left out.

In plain words
What is it for?
Use it to prepare a product spec, implementation brief, or handoff document before development begins.
Why use it?
It keeps product and engineering decisions in one durable document instead of scattered across chats and tickets. It also makes scope, open questions, and validation expectations easier to share.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare a product spec, implementation brief, or handoff document before development begins.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stark-ai-de/agent-skills/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 stark-ai-de/agent-skills --skill prd-writer
Clone the repo
git clone --depth 1 https://github.com/stark-ai-de/agent-skills

Made for: Claude Code, Codex.

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/stark-ai-de/agent-skills/prd-writer/github.svg)](https://agentmods.dev/skills/stark-ai-de/agent-skills/prd-writer)
Your own site
<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/prd-writer"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/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/stark-ai-de/agent-skills/prd-writer"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/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 643 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 $0.00643
Opus 5 $0.00028 $0.00321
Sonnet 5 $0.00011 $0.00129
Haiku 4.5 $0.00006 $0.00064

Measured 12d ago against content hash 100e8f4d4da7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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.

incubator/skills/engineering-workflows/prd-writer/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Writer

Goal

Create a clear product or implementation brief that preserves decisions, unresolved questions, scope, validation, and non-goals.

When to use

  • The user asks for a PRD, implementation brief, product spec, or handoff spec.
  • Current conversation context needs to become a durable planning artifact.
  • Engineering, product, validation, and rollout expectations need one shared document.

When not to use

  • The user only needs an ADR for a narrow repo-level decision.
  • The task is ready for implementation and does not need a planning artifact.
  • The user asks for a marketing document rather than product or engineering scope.

Inputs to inspect

  • Current conversation, existing specs, issues, roadmap items, ADRs, and domain docs.
  • User goals, constraints, target users, non-goals, and known decisions.
  • Existing validation commands and release process when relevant.

Workflow

  1. Identify the audience and artifact type: PRD, implementation brief, or handoff spec.
  2. Separate problem, goals, non-goals, proposed solution, decisions, and open questions.
  3. Write user stories or use cases only when they clarify behavior.
  4. Include acceptance criteria and validation commands.
  5. Add rollout, migration, observability, docs, or support notes only when relevant.
  6. Keep unresolved questions explicit instead of pretending decisions are final.
  7. Ask before writing files unless the user requested a file update.

Safety rules

  • Do not invent product decisions to make the brief look complete.
  • Do not bury out-of-scope items in footnotes.
  • Do not include private customer data, internal hostnames, or secrets.
  • Do not turn implementation details into requirements unless the user decided them.

References

No bundled references. Use local domain docs and ADRs when present so terminology and decisions match the repository.

Scripts

No bundled scripts.

Output format

Return or write:

  1. Problem
  2. Goals
  3. Non-goals
  4. Users or stakeholders
  5. Proposed solution
  6. User stories or workflows
  7. Decisions
  8. Open questions
  9. Acceptance criteria
  10. Validation and rollout

Read the full file on GitHub · 88 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. 12d ago First seen · 88 lines · 56 tokens per session scan A 100e8f4d4da7

Subscribe to this mod's changes

prd-writer is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 643 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 2026-08-31.