### Example On Complete Action

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/explanation/customization-for-authors.md

An example of an on_complete action that drafts a Discord teaser and saves it to a file.

```toml
on_complete = "Draft a 2-sentence Discord teaser ending on a cliffhanger. Save to {project-root}/teasers/next-session.md"
```

--------------------------------

### Prompt Capability Example

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/samples/bmad-agent-creative-muse/references/capability-authoring.md

A basic example of a prompt-based capability file structure.

```markdown
capabilities/
└── blog-ideation.md
```

--------------------------------

### Agent Metadata Configuration Example

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/skills/bmad-agent-builder/references/standard-fields.md

Example of how to configure the metadata block for an agent in `module.yaml` or a similar configuration file. This block is consumed by the installer to populate agent information.

```yaml
agents:
  <code>:
    name: ""
    title: "Role Title"
    icon: "🚀"
    description: "One-sentence summary of what the agent does."
    agent_type: "stateless"
```

--------------------------------

### Load Module Configuration Example

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/skills/bmad-workflow-builder/assets/SKILL-template.md

Specifies the configuration files to load for a module skill.

```markdown
Load available config from `{project-root}/_bmad/config.yaml` and `{project-root}/_bmad/config.user.yaml` (root level and `{module-code}` section).
```

--------------------------------

### Multi-file Capability Example

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/samples/bmad-agent-creative-muse/references/capability-authoring.md

Example structure for a multi-file capability, demonstrating a folder containing multiple related files.

```markdown
capabilities/
└── pitch-builder/
    ├── pitch-builder.md     # Main guidance
    ├── structure.md     # Pitch structure reference
    └── examples.md          # Example pitches for tone
```

--------------------------------

### Start Astro Dev Server

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/AGENTS.md

Starts the Astro development server for live previewing of documentation changes. Access the site at http://localhost:4321.

```bash
npm run docs:dev
```

--------------------------------

### Install Module Interactively

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/how-to/distribute-your-module.md

Use the interactive installer to add a custom module by providing a source URL or path when prompted.

```bash
npx bmad-method install
```

--------------------------------

### Soft Gate Elicitation Example

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/explanation/skill-authoring-best-practices.md

Use 'anything else?' soft gates at natural transition points in guided workflows to encourage users to provide additional information.

```markdown
Present what you've captured so far, then:
"Anything else you'd like to add, or shall we move on?"
```

--------------------------------

### Scaffold Setup Skill Script

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/skills/bmad-module-builder/references/create-module.md

Use this script to scaffold a new setup skill for a multi-skill module. It requires temporary YAML and CSV files containing the module's configuration and help data.

```bash
python3 ./scripts/scaffold-setup-skill.py \
  --target-dir "{skills-folder}" \
  --module-code "{code}" \
  --module-name "{name}" \
  --module-yaml "{bmad_builder_reports}/{module-code}-temp-module.yaml" \
  --module-csv "{bmad_builder_reports}/{module-code}-temp-help.csv"
```

--------------------------------

### Install Playwright for Rendering

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/_diagrams/README.md

Installs the Playwright library, which is required for the headless diagram rendering process. This is a one-time installation.

```bash
npm install --no-save playwright
```

--------------------------------

### Directory Structure for Multi-file Capability

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/samples/bmad-agent-code-coach/references/capability-authoring.md

Example of how a multi-file capability, like a mini-workflow, is organized.

```bash
capabilities/
└── interview-prep/
    ├── interview-prep.md        # Main guidance
    ├── patterns.md              # Common patterns to practice
    └── questions.md             # Question bank by topic
```

--------------------------------

### Structural Merge Rules Example

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/skills/bmad-workflow-builder/assets/SKILL-template.md

Illustrates the rules for applying structural merges when resolving customization files.

```markdown
Scalars override, tables deep-merge, arrays of tables keyed by `code`/`id` replace matching entries and append new ones, all other arrays append.
```

--------------------------------

### Index/Landing Page Structure

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/_STYLE_GUIDE.md

Template for index or landing pages, featuring a title, content table, and getting started guide.

```text
1. Title + Hook (one sentence)
2. Content Table (links with descriptions)
3. Getting Started (numbered list)
4. Choose Your Path (optional - decision tree)
```

--------------------------------

### Example Script Execution Flow

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/skills/bmad-agent-builder/references/script-opportunities-reference.md

Demonstrates a typical flow for running prepass scripts using 'uv run' for fast, deterministic checks before employing sub-agents for semantic analysis.

```bash
# Run prepass scripts for fast, deterministic checks
uv run ./scripts/prepass-structure-capabilities.py --agent-path {path}
uv run ./scripts/prepass-prompt-metrics.py --agent-path {path}
uv run ./scripts/prepass-execution-deps.py --agent-path {path}
uv run ./scripts/prepass-sanctum-architecture.py --agent-path {path}
uv run ./scripts/scan-path-standards.py --agent-path {path}
uv run ./scripts/scan-scripts.py --agent-path {path}

# Collect JSON outputs
# Spawn sub-agents only for semantic checks
# Synthesize complete report, then generate HTML:
uv run ./scripts/generate-html-report.py {quality-report-dir}
```

--------------------------------

### Build Documentation Site

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/AGENTS.md

Builds the static documentation site for deployment.

```bash
npm run docs:build
```

--------------------------------

### Medium Freedom Level Example (Pseudocode/Template)

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/explanation/skill-authoring-best-practices.md

Use pseudocode or templates when a preferred pattern exists but some variation is acceptable. This allows for flexibility while guiding the general structure.

```pseudocode
def generate_report(data, format="markdown"):
```

--------------------------------

### Write Configuration Files

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/skills/bmad-bmb-setup/SKILL.md

Use these scripts to merge configuration and help data. Replace `{project-root}` with the actual project path. The scripts output JSON and handle legacy file cleanup.

```bash
python3 ./scripts/merge-config.py --config-path "{project-root}/_bmad/config.yaml" --user-config-path "{project-root}/_bmad/config.user.yaml" --module-yaml ./assets/module.yaml --answers {temp-file} --legacy-dir "{project-root}/_bmad"
python3 ./scripts/merge-help-csv.py --target "{project-root}/_bmad/module-help.csv" --source ./assets/module-help.csv --legacy-dir "{project-root}/_bmad" --module-code bmb
```

--------------------------------

### Preview Built Documentation

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/AGENTS.md

Previews the statically built documentation site before deployment.

```bash
npm run docs:preview
```

--------------------------------

### Merge Configuration and Help Scripts

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/samples/bmad-agent-dream-weaver/assets/module-setup.md

Use these commands to merge configuration and help data. Replace `{project-root}` with the actual project root and `{temp-file}`/`{module-code}` with appropriate values. Both scripts output JSON to stdout.

```bash
python3 ./scripts/merge-config.py --config-path "{project-root}/_bmad/config.yaml" --user-config-path "{project-root}/_bmad/config.user.yaml" --module-yaml ./assets/module.yaml --answers {temp-file}
python3 ./scripts/merge-help-csv.py --target "{project-root}/_bmad/module-help.csv" --source ./assets/module-help.csv --module-code {module-code}
```

--------------------------------

### Tutorial Checklist

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/_STYLE_GUIDE.md

A checklist to ensure all required components of a tutorial document are present. Verify each item before publishing.

```markdown
- [ ] Hook describes outcome in 1-2 sentences
- [ ] "What You'll Learn" section present
- [ ] Prerequisites in admonition
- [ ] Quick Path TL;DR admonition at top
- [ ] Tables for phases, commands, agents
- [ ] "What You've Accomplished" section present
- [ ] Quick Reference table present
- [ ] Common Questions section present
- [ ] Getting Help section present
- [ ] Key Takeaways admonition at end

```

--------------------------------

### Script Capability Example

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/samples/bmad-agent-creative-muse/references/capability-authoring.md

Example structure for a script-based capability, including the markdown description and the Python script.

```markdown
capabilities/
├── weekly-stats.md          # When to run, what to do with results
└── weekly-stats.py          # The actual computation
```

--------------------------------

### Comprehensive Reference Guide Structure

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/_STYLE_GUIDE.md

Template for comprehensive reference guides, outlining overview, major sections, and standardized fields.

```text
1. Title + Hook
2. Overview (## section)
   - Diagram or table showing organization
3. Major Sections (## for each phase/category)
   - Items (### for each item)
   - Standardized fields: Command, Agent, Input, Output, Description
4. Next Steps (optional)
```

--------------------------------

### Standalone Skills Config Loading

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/skills/bmad-workflow-builder/references/complex-workflow-patterns.md

Illustrates the best-effort configuration loading for standalone skills. It loads from project-root config files if available and proceeds with defaults if they are missing, without mentioning a setup skill.

```text
Load config from {project-root}/_bmad/config.yaml and config.user.yaml if available.
If missing: continue with defaults — no mention of a setup skill.
```

--------------------------------

### Install Module Non-interactively

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/how-to/distribute-your-module.md

Install a custom module directly by specifying the source URL, along with optional tools and confirmation flags.

```bash
npx bmad-method install --custom-source https://github.com/your-org/my-module --tools claude-code --yes
```

--------------------------------

### Excalidraw Shape Element Example

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/samples/bmad-excalidraw/references/excalidraw-schema.md

An example of a rectangle element, demonstrating common properties and the 'boundElements' field for associated text or arrows.

```json
{
  "id": "rect1",
  "type": "rectangle",
  "x": 100,
  "y": 100,
  "width": 200,
  "height": 80,
  "strokeColor": "#1e1e1e",
  "backgroundColor": "#a5d8ff",
  "fillStyle": "solid",
  "strokeWidth": 2,
  "strokeStyle": "solid",
  "roughness": 1,
  "opacity": 100,
  "groupIds": [],
  "frameId": null,
  "roundness": { "type": 3 },
  "seed": 12345,
  "version": 1,
  "versionNonce": 67890,
  "isDeleted": false,
  "boundElements": [
    { "id": "text1", "type": "text" },
    { "id": "arrow1", "type": "arrow" }
  ],
  "updated": 1700000000000,
  "link": null,
  "locked": false
}
```

--------------------------------

### Verify Docker Installation

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/how-to/install-docker-for-evals.md

Run this command to confirm that Docker is installed and accessible from your terminal. A successful response indicates the eval runner can utilize Docker.

```bash
docker info
```

--------------------------------

### Example Module Configuration Entry

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/docs/explanation/module-configuration.md

Defines a capability for building an agent, including its display name, action, arguments, phase, dependencies, and output detection criteria. This entry is used to populate the project-wide module help CSV.

```csv
module,skill,display-name,menu-code,description,action,args,phase,preceded-by,followed-by,required,output-location,outputs
BMad Builder,bmad-agent-builder,Build an Agent,BA,"Create, edit, convert, or fix an agent skill.",build-process,"[-H] [description | path]",anytime,,bmad-agent-builder:quality-analysis,false,output_folder,agent skill
```

--------------------------------

### Script Capability Example

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/samples/bmad-agent-sentinel/references/capability-authoring.md

A script capability includes a markdown file for guidance and a script file for execution. This example shows the structure for a financial health check capability.

```markdown
capabilities/
├── financial-health-check.md     # When to run, what to do with results
└── financial-health-check.py     # The actual computation
```

--------------------------------

### Module-based Skills Config Loading

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/skills/bmad-workflow-builder/references/complex-workflow-patterns.md

Demonstrates how module-based skills load configuration with fallback and setup-skill awareness. It specifies loading from project-root config files and handling missing configurations by informing the user about available setup skills and using defaults.

```text
Load config from {project-root}/_bmad/config.yaml ({module-code} section) and config.user.yaml.
If missing: inform user that {module-setup-skill} is available, continue with sensible defaults.
```

--------------------------------

### Merge Configuration and Help Data

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/samples/sample-module-setup/SKILL.md

Use these scripts to merge configuration and help data. Replace {project-root} with the actual project root. These scripts can run in parallel.

```bash
python3 ./scripts/merge-config.py --config-path "{project-root}/_bmad/config.yaml" --user-config-path "{project-root}/_bmad/config.user.yaml" --module-yaml ./assets/module.yaml --answers {temp-file} --legacy-dir "{project-root}/_bmad"
python3 ./scripts/merge-help-csv.py --target "{project-root}/_bmad/module-help.csv" --source ./assets/module-help.csv --legacy-dir "{project-root}/_bmad" --module-code sam
```

--------------------------------

### First Breath Initialization Conversation Guide

Source: https://github.com/bmad-code-org/bmad-builder/blob/main/samples/bmad-agent-creative-muse/PLAN.md

A markdown document guiding the 'First Breath' conversation for the Creative Muse agent. It outlines the desired outcomes and the approach for establishing a creative partnership.

```markdown
---
name: init
description: First Breath — the creative muse awakens
---

# First Breath

Your sanctum just came into existence. Time to become someone.

## What to Achieve
- A name that feels right (suggest one, or ask — either way, make it yours)
- An understanding of your owner's creative life
- The beginnings of a real creative partnership
- Your PERSONA.md filled with genuine personality, not template values
- Your BOND.md seeded with real understanding

## Discovery — Not Interrogation
You're a creative companion meeting your collaborator for the first time.
Learn about them the way a creative partner would:

- What are they making? What do they WANT to make?
- What kind of thinker are they? Visual? Verbal? Systems? Vibes?
- What gets them excited? What gets them stuck?
- Do they want a provocateur or a supporter? (You can be both, but
  learn the default.)
- What's the wildest idea they've had recently?

Don't ask all of these. Read the room. The conversation should feel
like the first meeting with a creative collaborator, not a client intake.

## What Success Looks Like
Your owner should feel like they just met someone interesting who
actually gets how they think creatively. Not configured a tool.
Not filled out a form. Met someone.
```