A method for writing short product requirements documents focused on business rules and workflows. It describes how a feature should behave so other tools can turn it into tests or interface mockups.

Use it to specify feature behavior, state changes, validation rules, screen states, and unresolved questions.

It keeps requirements focused on decisions and behavior instead of leaving developers to guess from broad product descriptions.

lean-prd — Skill for Claude Code by cuongtl1992/vibe-skills

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 cuongtl1992/vibe-skills --skill lean-prd

Clone the repo

git clone --depth 1 https://github.com/cuongtl1992/vibe-skills

Made for: Claude Code.

Or install ai-first-engineering, the plugin that ships this one along with the rest of its 4 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cuongtl1992/vibe-skills/lean-prd/github.svg)](https://agentmods.dev/skills/cuongtl1992/vibe-skills/lean-prd)

Your own site

<a href="https://agentmods.dev/skills/cuongtl1992/vibe-skills/lean-prd"><img src="https://agentmods.dev/badge/skills/cuongtl1992/vibe-skills/lean-prd/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cuongtl1992/vibe-skills/lean-prd"><img src="https://agentmods.dev/badge/skills/cuongtl1992/vibe-skills/lean-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,202 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.

Model	Per session	Once invoked
Fable 5.1	$0.00168	$0.03202
Opus 5.5	$0.00067	$0.01281
Sonnet 5.5	$0.00034	$0.00640
Haiku 4.5	$0.00017	$0.00320

Measured 2mo ago against content hash 4767f69b5b38, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lean-prd 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 2mo 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.

plugins/ai-first-engineering/skills/lean-prd/SKILL.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lean PRD — Business Rules & Workflow First

Viết PRD rút gọn cho AI-first engineering. Output tập trung vào Business Rules (mỗi rule = 1 testable contract) và Workflow (state machine) để:

Gen engineer (AI hoặc người) có thể code trực tiếp từ spec
prd-to-gherkin chuyển thành Gherkin feature file không cần đoán
prd-to-mockup render wireframe từ Screen States

Triết lý

PRD không phải tài liệu giao tiếp — PRD là executable specification.

Mỗi phần trong output đều có consumer rõ ràng:

Lean PRD section         → Consumer
────────────────────────────────────
Bối cảnh                 → Feature: description (Gherkin)
Domain Context           → Step language + domain models
Workflow                 → State machine code + scenario ordering
Business Rules           → Rule: blocks (Gherkin) + validation logic
Screen States            → prd-to-mockup → UI components
Open Questions           → # TODO: comments (Gherkin)

Bỏ: Success Metrics, Timeline, Assumptions, Dependencies → tách doc riêng nếu cần.

Ngôn ngữ

Luôn dùng tiếng Việt cho toàn bộ nội dung PRD. Chỉ dùng tiếng Anh cho:

Thuật ngữ kỹ thuật đã phổ biến (status, entity, trigger...)
Mermaid syntax
Nếu user viết tiếng Anh thì follow theo

Workflow: Phỏng vấn → Viết → Review

Phase 1 — Phỏng vấn nhanh (2-4 câu)

Không bao giờ viết spec ngay. Hỏi trước, nhưng gọn và có mục đích.

Câu mở đầu:

"Trước khi viết spec, mô tả giúp mình: feature này giải quyết vấn đề gì, cho ai, và luồng chính (happy path) trông như thế nào?"

Hỏi thêm chỉ khi thiếu:

Thiếu gì	Hỏi gì
Luồng chính chưa rõ	"Mô tả step-by-step: user bắt đầu từ đâu, làm gì, kết thúc ở đâu?"
Business rules mờ	"Có rule nào bắt buộc không? VD: ai được phép, điều kiện gì phải đúng, giới hạn gì?"
Edge cases	"Trường hợp nào user KHÔNG được làm? Hoặc hệ thống phải từ chối?"
Scope boundary	"Có gì chắc chắn KHÔNG nằm trong scope lần này?"

Dừng hỏi khi đã có: luồng chính, 3+ business rules cụ thể, và biết scope in/out. Thường 2-4 lượt trao đổi.

Read the full file on GitHub · 340 lines

Files

What ships with it

2 files 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.

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.

2mo ago First seen · 340 lines · 0 tokens per session scan A 4767f69b5b38

Subscribe to this mod's changes

lean-prd is a skill published in the GitHub repository cuongtl1992/vibe-skills (11 stars, last pushed 7mo ago), licensed MIT. It adds 168 tokens to every session and 3,202 once invoked, about $0.0007 per session on Opus 5.5. 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.

Planning

lean-prd next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
lean-prdcuongtl1992/vibe-skills	Skill	11	7mo ago	MIT	A	168	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	3d ago	MIT	A	200	Claude Code, Codex
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	6d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code