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.
npx skills add assimovt/productskills --skill prd-writinggit clone --depth 1 https://github.com/assimovt/productskillsWrote 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.
[](https://agentmods.dev/skills/assimovt/productskills/prd-writing)<a href="https://agentmods.dev/skills/assimovt/productskills/prd-writing"><img src="https://agentmods.dev/badge/skills/assimovt/productskills/prd-writing/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.
<a href="https://agentmods.dev/skills/assimovt/productskills/prd-writing"><img src="https://agentmods.dev/badge/skills/assimovt/productskills/prd-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00773 |
| Opus 5 | $0.00025 | $0.00387 |
| Sonnet 5 | $0.00010 | $0.00155 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
prd-writing 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write PRDs that are evidence-first, concise, and scannable. A PRD is a thinking tool — if it's longer than 1200 words, the author hasn't thought hard enough. Brief specs are more likely to be read, more likely to be followed, and more likely to ship on time.
Structure
Follow this structure. Every section is mandatory unless marked optional.
1. Problem
Lead with customer evidence. Quotes, data, support tickets, observed behavior. If you have no evidence, say so explicitly — that's an opinion-driven PRD and should be flagged.
Example:
"3 of 5 interviewed customers abandon onboarding at the team invite step. Average time spent: 47 seconds before closing the tab."
NOT: "Users find onboarding confusing."
2. Goals
Measurable outcomes, not outputs. Each goal has a number attached.
- "Reduce onboarding drop-off from 60% to under 30%"
- NOT "Improve the onboarding experience"
3. Target Users
Who specifically benefits. Be narrow. "Series A startup founders doing PM work before their first PM hire" — not "product managers."
4. Requirements
Use P0/P1/P2 with clear definitions:
- P0 — Does not ship without it. The feature is broken or useless without this.
- P1 — Ships without it, but significantly degraded. Do in same cycle if possible.
- P2 — Nice to have. Candidate for fast follow.
Each requirement is one sentence. If a requirement needs a paragraph to explain, it's too big — break it down.
5. Success Metrics
Numbers. Always numbers. "Reduce X from Y to Z within W weeks."
ALWAYS pair each metric with a counter-metric to prevent gaming:
- Metric: "Increase activation rate to 70%"
- Counter-metric: "Without decreasing 30-day retention below 45%"
6. Out of Scope
What you are deliberately NOT building and why. This section prevents scope creep and signals that you've thought about boundaries.
7. Open Questions (optional)
Unresolved decisions that need input. Each question names who should answer it and by when.
Guidelines
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.
- 11d ago First seen · 77 lines · 50 tokens per session scan A 3c4e46938207
prd-writing is a skill published in the GitHub repository assimovt/productskills (68 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 773 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.
Other skills, from other repositories
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…
handoff
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…
generate
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…
discover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…
execute-fleet
Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher worktrees with inbox-based result collection, verified CDD cards, sequential integration merges, and one final PR.
customise-workflow
Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…