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 shawnpang/startup-founder-skills --skill prd-writinggit clone --depth 1 https://github.com/shawnpang/startup-founder-skillsWrote 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/shawnpang/startup-founder-skills/prd-writing)<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/prd-writing"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/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/shawnpang/startup-founder-skills/prd-writing"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/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 | $0.00028 | $0.01642 |
| Opus 5 | $0.00014 | $0.00821 |
| Sonnet 5 | $0.00006 | $0.00328 |
| Haiku 4.5 | $0.00003 | $0.00164 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- prd-writing — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Writing
When to Use
Activate when a founder or PM needs to turn a product idea, feature request, or strategic initiative into a structured Product Requirements Document. This includes situations where the user says things like "write a PRD," "spec out this feature," "define requirements for X," or "I need to document what we're building."
Context Required
- From startup-context: company stage, target customer segments, current product state, team size, technical constraints.
- From the user: the feature or initiative to spec, known user problems it addresses, any prior research or customer feedback, desired timeline, and scope preference (lightweight vs. full PRD).
Workflow
- Clarify scope level -- Ask whether this needs a lightweight PRD (early-stage exploration, 2-3 pages) or a full PRD (committed initiative, 5-8 pages). Default to lightweight if the company is pre-product-market-fit.
- Gather inputs -- Collect the problem statement, target users, any existing research, success criteria, and known constraints. Identify key contacts and their roles.
- Draft the 8-section PRD -- Write each section sequentially using the template below. Use accessible language suitable for a broad audience including engineering, design, and leadership.
- Flag assumptions -- Explicitly list key assumptions underlying each section. For each, state what evidence supports it and what would invalidate it.
- Review and refine -- Present the draft, invite feedback, and iterate on specific sections. State the PRD version and last-updated date.
Output Format
A structured PRD document with 8 sections:
Section Template
- Summary -- 2-3 sentence overview of what is being built and why it matters. Write for a broad audience.
- Contacts -- Key stakeholders with their roles and relevant context about their involvement.
- Background -- Context on the problem space: why now, what changed, what enables this initiative. Include competitive context on how others handle the same problem.
- Objective -- Goals, business and customer benefits, and strategic alignment. Define SMART success metrics tied to OKRs. Use the format: "Enable [user segment] to [action] resulting in [measurable outcome]."
- Market Segment(s) -- Define target users by problems and needs, not demographics. Describe primary and secondary segments with size estimates.
- Value Proposition(s) -- Map customer jobs addressed, gains provided, and pain points eliminated. Show competitive differentiation using frameworks like Value Curve analysis.
- Solution -- Feature descriptions, UX/prototypes, wireframes, user flows, and technology details when relevant. Include out-of-scope items explicitly. Document assumptions. Enumerate at least 5 edge cases.
- Release -- Phased rollout plan using relative timeframes (not exact dates). Define MVP vs. future iterations, feature flags, rollback criteria, and review checkpoints.
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.
- 12d ago First seen · 86 lines · 28 tokens per session scan A 8fbf54160c1c
prd-writing is a skill published in the GitHub repository shawnpang/startup-founder-skills (321 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,642 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…