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 britt/agent-skills --skill writing-product-specsgit clone --depth 1 https://github.com/britt/agent-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/britt/agent-skills/writing-product-specs)<a href="https://agentmods.dev/skills/britt/agent-skills/writing-product-specs"><img src="https://agentmods.dev/badge/skills/britt/agent-skills/writing-product-specs/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/britt/agent-skills/writing-product-specs"><img src="https://agentmods.dev/badge/skills/britt/agent-skills/writing-product-specs.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 | $0.00052 | $0.00814 |
| Opus 5 | $0.00026 | $0.00407 |
| Sonnet 5 | $0.00010 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
writing-product-specs 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Product Specifications
Overview
Write comprehensive product specification documents that clearly communicate what we're building, why we're building it, and how we'll know it's successful. Document everything stakeholders need to understand: the problem context, target audience, requirements, success criteria, and tradeoffs. Give them a complete picture of the feature or project.
Assume the reader is a skilled product person or engineer, but knows nothing about this specific feature or the problem domain. Assume they need clear context to understand the "why" behind the work.
Announce at start: "I'm using the writing-product-specs skill to create the product specification."
Core principle: Product specifications are detailed descriptions of the features and functionality of a product. They are used to communicate the requirements of the product to the development team.
When to Use This Skill
Use this skill when:
- You are explicitly asked to write a product specification, product spec, or PRD (Product Requirements Document)
- You are asked to design a new feature and need to document requirements before implementation
- You are planning a project and need to define what will be built and why
- You need to communicate product requirements to stakeholders, engineers, or designers
- A feature request needs to be expanded into a detailed specification with context, requirements, and success criteria
- You are asked to document the "what" and "why" of a product decision before moving to implementation
Do NOT use this skill for implementation plans — specs describe what to build and why, not the step-by-step engineering work.
Process for Writing a Product Spec
Follow this process to elicit the necessary information and compose a comprehensive product specification.
Step 1: Understand the Requested Feature or Project
Ask questions to understand the feature or project. Gather information about:
- What is it? What feature or project are we building? What does it do?
- Who is the audience? Who are we solving this problem for? What are their roles, personas, or characteristics?
- What are their problems? What specific pain points or challenges does the audience face? What is broken or missing?
- How will this feature/project solve them? What is the proposed solution? How does it address the problems?
- How will they benefit? What specifically is the benefit? What value does this deliver? What outcomes or improvements will users experience?
- How will we know if we've succeeded? What are the success metrics, validation criteria, or observable outcomes?
- How will we know if we've failed? What would indicate failure? What are the failure modes or negative indicators?
- What are we NOT doing? What is explicitly out of scope? What related features or capabilities are we excluding?
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.
- 11d ago First seen · 66 lines · 52 tokens per session scan A 055538dc631e
writing-product-specs is a skill published in the GitHub repository britt/agent-skills (5 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 814 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.
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…