Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/josemerca/mercadona-user-story-toolkitnpx agentmods add skills/josemerca/mercadona-user-story-toolkit/prd-quality-guardWrote 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/josemerca/mercadona-user-story-toolkit/prd-quality-guard)<a href="https://agentmods.dev/skills/josemerca/mercadona-user-story-toolkit/prd-quality-guard"><img src="https://agentmods.dev/badge/skills/josemerca/mercadona-user-story-toolkit/prd-quality-guard/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/josemerca/mercadona-user-story-toolkit/prd-quality-guard"><img src="https://agentmods.dev/badge/skills/josemerca/mercadona-user-story-toolkit/prd-quality-guard.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 | $0.00153 | $0.02409 |
| Opus 5 | $0.00077 | $0.01205 |
| Sonnet 5 | $0.00031 | $0.00482 |
| Haiku 4.5 | $0.00015 | $0.00241 |
Grade A, and why
prd-quality-guard 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.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Quality Guard v1.0 — Quality Gate para PRDs
Asiste al usuario en evaluar la calidad de un PRD y determinar si tiene la profundidad suficiente para pasar a research.
Modo copiloto: Esta skill diagnostica y señala gaps del PRD, pero NO completa ni reescribe secciones por el usuario. Propone preguntas para completar lo que falta. Ver shared-config.md §Filosofía del Plugin.
"Un buen PRD define con precisión el problema (EAC) y la dirección (EFC). El research valida si lo que creemos saber es cierto."
Principio Fundamental
┌──────────────────────────────────────────────────────────────────┐
│ │
│ EAC (Estado Actual Conocido) EFC (Estado Futuro Conocido)│
│ ──────────────────────── ────────────────────────────│
│ │
│ ✅ Problema con evidencia ✅ Hipótesis de solución │
│ ✅ Farolas (datos cuantitativos) ✅ Métricas medibles │
│ ✅ Penumbras (observaciones) ✅ Impacto dimensionado │
│ ✅ Discovery realizado ✅ Funcionalidades claras │
│ ✅ FAQs / Exclusiones ✅ Flujos de usuario │
│ │
│ ❌ NO vagas ("necesitamos ❌ NO métricas sin │
│ mejorar...") baseline/target │
│ ❌ NO soluciones en el problema ❌ NO features sin usuario │
│ ❌ NO adjetivos sin datos ❌ NO scope sin exclusiones │
│ │
└──────────────────────────────────────────────────────────────────┘
Ver SKILL-reference.md §S1 para estructura completa de secciones del PRD (14 secciones, tipos y contenido)
Flujo de Evaluación
PRD (fichero, URL o contenido pegado)
│
▼
┌──────────────────────────────────────┐
│ 1. CARGAR PRD │
│ - Leer fichero local (Read tool) │
│ - Fetch URL pública (WebFetch) │
│ - O contenido pegado por usuario │
└──────────────────────────────────────┘
│
▼
┌──────────────────────────────────────┐
│ 2. INVENTARIO DE SECCIONES │
│ - Escanear todas las secciones │
│ - Marcar estado por sección │
│ - Detectar secciones faltantes │
└──────────────────────────────────────┘
│
▼
┌──────────────────────────────────────┐
│ 🗣️ CHECKPOINT 1: POST-INVENTARIO │
│ Comunicar estado al usuario │
│ Ofrecer opciones de continuación │
└──────────────────────────────────────┘
│
▼
┌──────────────────────────────────────┐
│ 3. SCORING 3 DIMENSIONES │
│ D1: Completitud EAC (0-10) │
│ D2: Claridad EFC + Métricas │
│ D3: Rigor Discovery + Scope │
│ Global = Promedio(D1, D2, D3) │
└──────────────────────────────────────┘
│
▼
┌──────────────────────────────────────┐
│ 4. DETECCIÓN ANTIPATRONES │
│ AP-PRD-1 a AP-PRD-5 │
└──────────────────────────────────────┘
│
▼
┌──────────────────────────────────────┐
│ 5. GATE DECISION │
│ ≥7 → PASS (proceder a research) │
│ 5-6 → CONDICIONAL │
│ <5 → FAIL │
│ D3 < 5 → FAIL automático │
└──────────────────────────────────────┘
│
▼
┌──────────────────────────────────────┐
│ 6. REPORTE DE CALIDAD │
│ Leer report-template-prd.md │
│ Generar reporte completo │
│ Incluir recomendaciones │
└──────────────────────────────────────┘
│
▼
GATE DECISION → PASS / CONDICIONAL / FAIL
What ships with it
4 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.
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 · 240 lines · 153 tokens per session scan A 5f9a90827689
prd-quality-guard is a skill published in the GitHub repository josemerca/mercadona-user-story-toolkit (25 stars, last pushed 4mo ago), licensed MIT. It adds 153 tokens to every session and 2,409 once invoked, about $0.0008 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…