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 Panix22/prd-writer-skill --skill prd-writergit clone --depth 1 https://github.com/Panix22/prd-writer-skillWrote 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/panix22/prd-writer-skill/prd-writer)<a href="https://agentmods.dev/skills/panix22/prd-writer-skill/prd-writer"><img src="https://agentmods.dev/badge/skills/panix22/prd-writer-skill/prd-writer.svg" alt="Measured on agentmods" 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 | $0.00119 | $0.01347 |
| Opus 5 | $0.00060 | $0.00674 |
| Sonnet 5 | $0.00024 | $0.00269 |
| Haiku 4.5 | $0.00012 | $0.00135 |
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 8d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Writer
Core Rule
Do not output a full PRD, feature list, or structured requirements document before completing Phase 1 diagnosis, page-structure confirmation, and Phase 2 concept alignment. Keep the interaction conversational until the concept PRD is confirmed.
Use Chinese by default unless the user requests another language.
Trigger Confirmation
After receiving the user's initial description, restate the core requirement in one sentence, then explain that you will ask a few rounds of questions to align on scope before starting Phase 1.
Workflow
Phase 1: Discovery and Page Structure
Collect the required facts from user, business, technical, and page-structure perspectives before drafting. Ask no more than 3 questions per turn, then wait for the user. If the user already provided an answer, do not ask it again.
User perspective:
- Who is the target user? Include age range, role/background, and usage context when possible.
- How do they solve this problem today?
- What single concrete job should the product help them complete?
- How often will they use it: daily, weekly, occasional, or another cadence?
Business perspective:
- Is the product free or paid?
- If paid, what model: one-time purchase, subscription, freemium, or another model?
- Is this a validation project or a long-term product?
Technical perspective:
- What product form: mini program, iOS, Android, H5, Web App, or another platform?
- Does it need accounts and login?
- Where does data live: local storage or cloud database?
- Does it depend on third-party services such as maps, payment, AI APIs, notifications, or analytics?
- How many weeks should this version take to build?
Page-structure perspective:
- What are the main pages or tabs? For example: 首页, 日历页, 记录页, 统计页, 个人中心.
- What does each MVP function map to: which page is the entry, and where does the result appear?
- What navigation pattern should the product use: bottom tabs, side nav, top nav, single-page flow, or wizard?
- Does it need supporting pages such as onboarding, login, settings, detail pages, edit pages, subscription/payment pages, or help pages?
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 127 lines · 119 tokens per session scan A 91871f06da5f
prd-writer is a skill published in the GitHub repository Panix22/prd-writer-skill (19 stars, last pushed 3mo ago), licensed MIT. It adds 119 tokens to every session and 1,347 once invoked, about $0.0006 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-discuss
A conversation guide for turning an unclear product idea or feature request into a structured product decision. It emphasizes confirming the target market, checking real user need, and looking for contrary evidence.
prd-review
Use when the user asks for deep business review of PRDs, requirement documents, product specs, feature proposals, or business process docs. Focus on understanding business model, modules, data relationships, flows, permissions, states, rules, omissions, contradictions, ambiguities, implementation risk, and…
命理解读师
A Chinese-language Zi Wei Dou Shu birth-chart interpretation guide, a form of traditional Chinese astrology based on birth details. It presents results as possible patterns rather than certain predictions and can include a chosen year's outlook.
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…
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…
os-done-or-not
ALWAYS invoke this skill when work wraps up or the user asks how it went - "done or not", "are we done", "what happened", "report" - in any language, and when a Stop hook asks for a session report. Produces a ten-line plain- language report: a lead, a checkmark table, and a verdict - fully done, anything needed from…