spec-from-brief

spec-from-brief is a skill for Claude Code from Ludovic33Fr/product-ai-toolbox. It costs 58 tokens per session (1,142 once invoked), scanned A, original, MIT.

A requirements-writing tool that turns a vague feature brief into a detailed, testable specification. It checks the user story against INVEST, a checklist for making requirements independent, useful, estimable, small, and testable, and writes Given/When/Then scenarios.

In plain words
What is it for?
Use it to turn an email, chat message, or roadmap paragraph into a user story, a main usage scenario, additional cases, and unanswered business questions.
Why use it?
It exposes missing users, expected benefits, edge cases, and unresolved business decisions before development starts. This reduces ambiguity in feature requests.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pm-augmente plugin — 12 skills, 6 agents shipped together

Good fit Use it to turn an email, chat message, or roadmap paragraph into a user story, a main usage scenario, additional cases, and unanswered business questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ludovic33fr/product-ai-toolbox/spec-from-brief
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 Ludovic33Fr/product-ai-toolbox --skill spec-from-brief
Clone the repo
git clone --depth 1 https://github.com/Ludovic33Fr/product-ai-toolbox

Made for: Claude Code.

Or install pm-augmente, the plugin that ships this one along with the rest of its 12 skills, 6 agents.

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.

agentmods badge for spec-from-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/spec-from-brief/github.svg)](https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/spec-from-brief)
Your own site
<a href="https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/spec-from-brief"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/spec-from-brief/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.

agentmods 80×15 button for spec-from-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/ludovic33fr/product-ai-toolbox/spec-from-brief"><img src="https://agentmods.dev/badge/skills/ludovic33fr/product-ai-toolbox/spec-from-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,142 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.01142
Opus 5 $0.00029 $0.00571
Sonnet 5 $0.00012 $0.00228
Haiku 4.5 $0.00006 $0.00114

Measured 11d ago against content hash d877a09a31e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

spec-from-brief 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.

skills/spec-from-brief/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

spec-from-brief

Fiche éditoriale

Objectif. Transformer un brief flou en spec testable et exhaustive.

Entrées. Brief initial, base documentaire produit.

Sorties. User story INVEST, scénario nominal Given/When/Then, scénarios annexes, questions business non tranchées.

Cadence d'usage. À chaque nouvelle fonctionnalité spécifiée.

Mode opératoire

Quand m'invoquer

L'utilisateur me fournit un brief texte (mail, slack, paragraphe de roadmap) et demande de le transformer en spec, ou évoque un besoin de "passer du brief à la story", ou demande une spec INVEST.

Procédure

  1. Lire le brief en entier sans interpréter.
  2. Identifier l'utilisateur cible (rôle, contexte d'usage) ; si absent, l'inscrire en question business non tranchée.
  3. Identifier le bénéfice attendu ; si absent, idem.
  4. Reformuler en user story au format En tant que <rôle>, je veux <action> afin de <bénéfice>.
  5. Tester la story contre INVEST (Independent, Negotiable, Valuable, Estimable, Small, Testable). Pour chaque lettre, dire si elle est tenue ; sinon dire pourquoi.
  6. Construire le scénario nominal au format Given/When/Then.
  7. Lister les scénarios annexes : cas limites, états système particuliers, erreurs prévisibles. Chacun en Given/When/Then.
  8. Lister les questions business non tranchées : ambiguïtés du brief, choix de produit qui doivent être arbitrés avant la mise en chantier.
  9. Produire la sortie au format ci-dessous.

Format de sortie

# Spec — {titre court de la fonctionnalité}

## User story (INVEST)

> En tant que {rôle}, je veux {action} afin de {bénéfice}.

**Test INVEST**
- Independent : {oui / non — explication}
- Negotiable : {oui / non — explication}
- Valuable : {oui / non — explication}
- Estimable : {oui / non — explication}
- Small : {oui / non — explication}
- Testable : {oui / non — explication}

## Scénario nominal

Given {prérequis} When {action utilisateur} Then {résultat observable}


## Scénarios annexes

### {nom du scénario annexe 1}

Given ... When ... Then ...


### {nom du scénario annexe 2}
...

## Questions business non tranchées

1. {question}
2. {question}

Read the full file on GitHub · 132 lines

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.

  1. 11d ago First seen · 132 lines · 58 tokens per session scan A d877a09a31e0

Subscribe to this mod's changes

spec-from-brief is a skill published in the GitHub repository Ludovic33Fr/product-ai-toolbox (1 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 1,142 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.