mastergo

Retrieve and analyze MasterGo design DSL data. Use when users provide MasterGo links (https://mastergo.com/file/xxx or /goto/xxx) to fetch design structure, component documentation, and DSL metadata.

16 stars

Best use case

mastergo is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Retrieve and analyze MasterGo design DSL data. Use when users provide MasterGo links (https://mastergo.com/file/xxx or /goto/xxx) to fetch design structure, component documentation, and DSL metadata.

Teams using mastergo should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/mastergo/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/design/mastergo/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/mastergo/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How mastergo Compares

Feature / AgentmastergoStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Retrieve and analyze MasterGo design DSL data. Use when users provide MasterGo links (https://mastergo.com/file/xxx or /goto/xxx) to fetch design structure, component documentation, and DSL metadata.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# MasterGo Skill

Retrieve and analyze design data from MasterGo files using self-contained Python scripts.

## Prerequisites

**Environment variable required:**

```bash
export MASTERGO_TOKEN="mg_your_token_here"
```

Get token: MasterGo Settings > Security > Personal Access Token

**Requirements**: Team Edition account, files in Team Projects (not Drafts).

### CRITICAL: Secure Token Handling

**NEVER do this:**
- `echo $MASTERGO_TOKEN` - exposes secret in output
- `echo "Token: $MASTERGO_TOKEN"` - exposes secret
- `printenv MASTERGO_TOKEN` - exposes secret
- Any command that prints the token value

**Secure verification method:**

```bash
test -n "$MASTERGO_TOKEN" && echo "Token is set" || echo "Token is NOT set"
```

This only prints whether the token exists, never its value.

## Script Location

Scripts are in `scripts/` relative to this SKILL.md file. Use absolute path when executing:

```
{this_skill_directory}/scripts/mastergo_*.py
```

## Workflow

### Step 1: Analyze DSL Structure

**Always analyze first** to understand the page structure:

```bash
python scripts/mastergo_analyze.py "https://mastergo.com/goto/xxx"
```

Output shows:
- Node tree (type, name, size)
- Text contents
- Component doc links
- Navigation targets

### Step 2: Get Full DSL (if needed)

For detailed DSL data:

```bash
python scripts/mastergo_get_dsl.py "https://mastergo.com/goto/xxx"
```

Output: JSON with `{ dsl, componentDocumentLinks, rules }`

### Step 3: Fetch Component Docs

If `componentDocumentLinks` is non-empty, fetch relevant docs:

```bash
python scripts/mastergo_get_dsl.py URL | python scripts/mastergo_fetch_docs.py --from-dsl
```

Or fetch individually:

```bash
python scripts/mastergo_fetch_docs.py "https://example.com/button.mdx"
```

## Scripts Reference

| Script | Purpose | Output |
|--------|---------|--------|
| `mastergo_analyze.py` | Structure summary | Human-readable tree to stdout |
| `mastergo_get_dsl.py` | Full DSL data | JSON to stdout |
| `mastergo_fetch_docs.py` | Component docs | Doc content to stdout |
| `mastergo_utils.py` | Utility functions | Import as module |

## DSL Key Concepts

- **`token` fields**: Design tokens for colors, shadows, fonts (convert to CSS variables when generating code)
- **`componentInfo`**: Component metadata including documentation links
- **`interactive` fields**: User interactions including page navigation targets
- **`rules` array**: Guidelines returned with DSL response

## CRITICAL: Do NOT Pollute User Projects

**FORBIDDEN actions:**
- Creating `.temp_dsl.json` or any DSL cache file in user project
- Creating `analyze_dsl.py` or any analysis script in user project
- Creating any temporary files in user project directory
- Writing any skill-related files outside of skill directory

**ALLOWED:**
- Running scripts and capturing stdout output
- Using output directly in memory
- Reading user's existing project files for context

All script output goes to **stdout only**. Use the output directly; do not save intermediate files to user's project.

## References

- [references/dsl-types.md](references/dsl-types.md) - Complete DSL type definitions
- [references/dsl-structure.md](references/dsl-structure.md) - Key fields and patterns
- [references/multi-page-workflow.md](references/multi-page-workflow.md) - Multi-page workflow

Related Skills

bgo

10
from diegosouzapw/awesome-omni-skill

Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.

Coding & Development

analyze-rust-optimizations

16
from diegosouzapw/awesome-omni-skill

This skill performs thorough analysis of Rust libraries to find optimization opportunities. It should be used when reviewing Rust code for performance improvements, memory efficiency, or when profiling indicates bottlenecks. Focuses on runtime performance and memory usage through dynamic profiling tools and static code analysis.

analyze-project-architecture

16
from diegosouzapw/awesome-omni-skill

LLM-based architectural analysis that transforms raw project data into meaningful structure

analyze-pr-performance

16
from diegosouzapw/awesome-omni-skill

Analyze code review pipeline performance for a specific PR. Use when investigating slow PRs, identifying bottlenecks, or debugging performance issues in code reviews.

analyze

16
from diegosouzapw/awesome-omni-skill

Deep analysis and investigation

analyze-m1-module-for-migration

16
from diegosouzapw/awesome-omni-skill

Systematically analyze a Magento 1 module to determine its purpose, usage, and migration requirements for Magento 2. Use when you need to decide whether to migrate a M1 module, find alternatives, or skip it.

analyze-function

16
from diegosouzapw/awesome-omni-skill

Deep line-by-line analysis of a function or method. Explains what each line does, why it's written that way, performance implications, edge cases, and design patterns. Use when user says "analyze-function", "analyze {function}", "deep dive on {function}", or "explain {function} line by line".

analyze-friction

16
from diegosouzapw/awesome-omni-skill

Orchestrate 3-stage friction analysis workflow across conversations. Extracts raw friction, abstracts patterns, and presents for approval. Use when user wants to analyze conversation history for improvement opportunities.

analyze-codebase

16
from diegosouzapw/awesome-omni-skill

Analyze a codebase to generate a comprehensive architecture and structure report. Use when user wants to understand a codebase, explore project structure, or generate analysis.

analyze-code

16
from diegosouzapw/awesome-omni-skill

Deep code analysis using consultant agent. Identifies technical debt, risks, and improvement opportunities.

analyze-code-structure

16
from diegosouzapw/awesome-omni-skill

Examine code organization and identify structural patterns. Use when reviewing module design.

analyze-architecture

16
from diegosouzapw/awesome-omni-skill

Comprehensive brownfield architecture analysis for existing codebases. Discovers structure, identifies patterns, assesses quality, calculates production readiness, and provides actionable recommendations. Use when analyzing existing codebases to understand architecture, assess quality, or prepare for modernization.