KS
Killer-Skills

bmad-validate-prd — how to use bmad-validate-prd how to use bmad-validate-prd, bmad-validate-prd setup guide, bmad-validate-prd alternative, bmad-validate-prd vs BMAD standards, what is bmad-validate-prd, bmad-validate-prd install, PRD validation workflow, BMAD standards compliance, comprehensive quality assessment

v1.0.0
GitHub

About this Skill

Perfect for Development Agents working with BMAD standards, needing comprehensive PRD validation and quality assessment capabilities. bmad-validate-prd is a repository-based skill that activates the BMAD PRD Validation workflow, utilizing a step-file architecture and configuration loading from config.yaml

Features

Triggers the BMAD PRD Validation workflow through a step-file architecture
Loads configuration from _bmad/bmm/config.yaml
Utilizes steps in the steps-v/ directory for comprehensive quality assessment
Follows the workflow defined in _bmad/bmm/workflows/2-plan-workflows/create-prd/workflow-validate-prd.md
Reviews existing PRDs against BMAD standards for improved validation

# Core Topics

KatTate KatTate
[0]
[0]
Updated: 3/7/2026

Quality Score

Top 5%
35
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add KatTate/Bmad-for-Replit/bmad-validate-prd

Agent Capability Analysis

The bmad-validate-prd MCP Server by KatTate is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use bmad-validate-prd, bmad-validate-prd setup guide, bmad-validate-prd alternative.

Ideal Agent Persona

Perfect for Development Agents working with BMAD standards, needing comprehensive PRD validation and quality assessment capabilities.

Core Value

Empowers agents to review existing PRDs against BMAD standards through step-file architecture and configuration loading from config.yaml, ensuring adherence to quality standards and best practices, utilizing MD file workflows for validation.

Capabilities Granted for bmad-validate-prd MCP Server

Validating PRDs against BMAD standards
Automating quality assessment for development projects
Reviewing workflow configurations in config.yaml

! Prerequisites & Limits

  • Requires access to _bmad/bmm/workflows and config.yaml files
  • Limited to BMAD standards and workflow validation
Project
SKILL.md
3.9 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

BMAD Validate PRD Workflow

This skill activates the BMAD PRD Validation workflow. It reviews an existing PRD against BMAD standards through comprehensive quality assessment.

Activation

When this skill is triggered, load and follow the workflow directly:

Read fully and follow: _bmad/bmm/workflows/2-plan-workflows/create-prd/workflow-validate-prd.md

The workflow uses step-file architecture with steps in steps-v/ directory.

  • Configuration loading from _bmad/bmm/config.yaml
  • PRD file discovery and loading
  • Output: validation report

Workflow Steps (13 Steps + 1 Conditional Branch)

  1. step-v-01-discovery — Discover and load the PRD to validate, detect format
  2. step-v-02-format-detection — Format classification and structure analysis
    • step-v-02b-parity-check — Parity check handler (conditional: auto-loaded for variant/legacy formats)
  3. step-v-03-density-validation — Information density validation (wordiness, filler, conciseness)
  4. step-v-04-brief-coverage-validation — Product brief coverage validation
  5. step-v-05-measurability-validation — Measurability validation (quantified success criteria)
  6. step-v-06-traceability-validation — Traceability validation (requirements linkage)
  7. step-v-07-implementation-leakage-validation — Implementation leakage detection (technology in requirements)
  8. step-v-08-domain-compliance-validation — Domain compliance validation
  9. step-v-09-project-type-validation — Project-type compliance validation
  10. step-v-10-smart-validation — SMART requirements validation
  11. step-v-11-holistic-quality-validation — Holistic quality assessment and rating
  12. step-v-12-completeness-validation — Completeness validation
  13. step-v-13-report-complete — Final report compilation, summary, and next steps

Commonly Missed Steps

  • ⚠️ step-v-07-implementation-leakage — Agents may skip leakage detection since it requires checking FRs/NFRs for technology-specific language. This is a critical quality gate.
  • ⚠️ step-v-11-holistic-quality — The holistic assessment provides the overall quality rating. Skipping it means no overall score.
  • ⚠️ step-v-13-report-complete — Final report step that compiles all findings and presents actionable options (edit, review, fix). Must not be skipped.
  • ⚠️ Each validation step must be executed sequentially — agents may try to batch multiple validations together. Each step must complete fully before the next begins.

Replit Task List Integration

MANDATORY on activation: Before beginning Step 1, create a Replit task list using the write_task_list tool with one task per workflow step listed above (13 sequential steps; if step-v-02b parity check is triggered, add it as a task dynamically). Each task should include the step number and name (e.g., "Step 1: Discovery — Discover and load the PRD to validate"). Mark the first task as in_progress. As you complete each step, immediately mark its task as completed (architect_reviewed: "not_applicable", reason: "BMAD workflow step — planning/facilitation, not code") and mark the next task as in_progress. This gives the user visible progress tracking throughout the workflow.

Critical Rules

  • NEVER skip steps or optimize the sequence
  • NEVER auto-proceed past WAIT points — stop and wait for user input
  • ALWAYS read each step file completely before taking action
  • ALWAYS follow step-file architecture: load one step at a time, never look ahead
  • ALWAYS halt at menus and wait for user selection
  • Recommend using a different high-quality LLM for validation if available
  • Each validation step must produce findings independently — do not batch

What's Next

After validating a PRD, the typical next steps are:

  • If issues found: Edit PRD (EP) — fix the identified problems
  • If passed: Create Architecture (CA) or Create UX (CU)

Related Skills

Looking for an alternative to bmad-validate-prd or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication