skills.rest
HordRicJr
HordRicJrCOMMUNITY
Explore all skills by this author →
GitHub

bmad-workflow-builder

Builds, edits, and analyzes AI skills and workflows through a goal-driven loop.

6|Updated Aug 29, 2026
Search Tags:#prompt engineering#skill builder#quality analysis#bmad#workflow authoring#skill scaffolding#frontmatter validation
One-click install
npx skills add https://github.com/HordRicJr/Akomagni --skill bmad-workflow-builder-hordricjr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-workflow-builder
Source: https://github.com/HordRicJr/Akomagni/tree/main/bmad-core/.agents/skills/bmad-workflow-builder
Command: npx skills add https://github.com/HordRicJr/Akomagni --skill bmad-workflow-builder-hordricjr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tiktoken, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve? Turning a half-formed idea into a lean, outcome-driven AI skill is hard: most generated skills ship bloated instructions, generic procedure, and no evidence they beat the bare model. This Skill guides the full lifecycle of building, editing, and quality-analyzing skills so every line earns its place. ## Core Features & Use Cases - Build and Edit flow: Scaffolds new skills from a template via init_skill.py, hardens vague ideas through questioning, captures decisions in a memlog, and runs the result on real input before shipping. - Analyze flow: Runs deterministic pre-pass scanners (token metrics, workflow integrity, frontmatter lint) plus LLM lenses, then renders a self-contained HTML and Markdown report with severity-graded findings. - Quality gates: Enforces SKILL.md token budgets, org build standards, optional eval requirements, and lint gates before handoff. - Use Case: Ask it to "build a skill that triages support tickets" and it will pressure-test the idea, scaffold the directory, draft a minimal SKILL.md, offer baseline evals, and deliver a lint-clean skill with an audit trail. ## Quick Start Ask the assistant to build a new skill from your idea, or point it at an existing skill directory and ask it to analyze or edit that skill.

Frequently Asked Questions about bmad-workflow-builder

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

FAQPage Schema
How do I build a new AI skill with a SKILL.md file?▼

Invoke the build intent with a description of your idea. The builder hardens the concept, scaffolds the directory with init_skill.py, drafts a minimal outcome-driven SKILL.md, and validates it with lint gates before handoff.

How do I quality-check an existing skill or workflow?▼

Point the skill at the target directory and ask to analyze it. The Analyze intent runs deterministic pre-pass scanners for token metrics and workflow integrity, applies LLM lenses, and renders a self-contained HTML report with severity-graded findings.

What makes a good SKILL.md description field?▼

The description must be present, under the length limit, free of angle brackets, and include a "Use when..." trigger phrase so routing can match user intent. The quick_validate.py script enforces these frontmatter rules.

Does the builder support non-interactive or headless runs?▼

Yes, pass --headless or -H to skip interactive questioning. Headless runs resume automatically from the memlog, default customization to no, and emit a JSON status object on completion or blockage.

What are the SKILL.md token budget limits?▼

The default desired budget is 2000 tokens and the hard budget is 3000 tokens, measured with tiktoken cl100k_base. Over-budget skills must lift sections into references/ until they return under budget.

When should a skill include a customize.toml file?▼

Only when the author explicitly accepts end-user customization during the build; the default is no. Accepted skills get activation hooks, persistent facts, and template or output-path knobs merged across base, team, and personal override files.

Related Skills

Explore More Software Engineering Skills→
apavanelloapavanello

researchers-journalism

Research and analyze journalistic sources for comprehensive reporting.

Community
Advanced
jacob-balslevjacob-balslev
1

skill-scaffold

Scaffold SKILL.md files conforming to Skill Metadata Protocol v7.

Community
Intermediate
ivanshamaevivanshamaev
14

soda-core

Run SodaCL data quality checks against configured data sources.

Community
Intermediate
ActiveMemoryActiveMemory
74

skill-creator

Create and refine reusable agent skills using a frontmatter-driven template.

Official
Intermediate