bmad-help

Analyzes BMad workflow state and recommends the next skill to invoke.

Updated Jul 2, 2026
One-click install
npx skills add https://github.com/tuanpa-nhg-eng/nhg-ipms --skill bmad-help-tuanpa-nhg-eng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-help
Source: https://github.com/tuanpa-nhg-eng/nhg-ipms/tree/main/.claude/skills/bmad-help
Command: npx skills add https://github.com/tuanpa-nhg-eng/nhg-ipms --skill bmad-help-tuanpa-nhg-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Users working with the BMad framework often lose track of which module and phase they are in, what steps are already complete, and which skill to run next. This Skill reads the installed skill catalog, resolved configuration, and existing output artifacts to orient the user and answer BMad-related questions. ## Core Features & Use Cases - Workflow Position Detection: Scans resolved output locations for artifact files matching catalog patterns to infer which steps are already completed. - Next-Step Recommendation: Uses phase, preceded-by, followed-by, and required fields from the bmad-help.csv catalog to suggest optional and required next skills, including menu codes, skill names, and args. - Grounded Q&A: Fetches module documentation sources (e.g., llms.txt) registered in the catalog to answer general questions about a module without fabricating project details. - Use Case: A user asks "what should I do next in BMad?" The Skill resolves config via the resolve_config.py script, detects a completed PRD artifact, and recommends the next required skill with its invocation command, offering to run it immediately. ## Quick Start Ask the assistant where you are in your BMad workflow and what skill to run next.

Frequently Asked Questions about bmad-help

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I know what to do next in a BMad workflow?

Ask for BMad help and the Skill reads the bmad-help.csv catalog, checks which output artifacts already exist, and recommends the next optional and required skills with their menu codes and invocation commands.

How does BMad help detect which steps are already completed?

It resolves output-location paths from the merged configuration and searches them for files matching the outputs patterns in the catalog. Found files are fuzzy-matched to catalog rows to infer completion.

Can BMad help answer general questions about a module?

Yes. Catalog rows with _meta in the skill column point to module documentation sources such as llms.txt, which the Skill fetches to ground answers about that module rather than guessing.

What configuration files does BMad help read?

It runs the resolve_config.py script, which merges _bmad/config.toml, _bmad/config.user.toml, _bmad/custom/config.toml, and _bmad/custom/config.user.toml in that order to resolve output locations and language settings.

Does BMad help force a strict order of skills?

No. The preceded-by and followed-by fields are soft sequencing suggestions. Only rows marked required=true act as gates that must complete before later phases become meaningful.