bmad-gds
AI-driven Game Development Studio using BMAD methodology. Routes game projects through Pre-production, Design, Architecture, Production, and Game Testing phases with 6 specialized agents. Supports Unity, Unreal Engine, Godot, and custom engines.
Install with Tessl CLI
npx tessl i github:supercent-io/skills-template --skill bmad-gds66
Quality
48%
Does it follow best practices?
Impact
96%
2.08xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/bmad-gds/SKILL.mdDiscovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description establishes a distinctive niche in game development with specific engine support, but lacks explicit trigger guidance ('Use when...') which is critical for skill selection. The capabilities are described at a high level (phases and agents) rather than concrete actions, and the technical term 'BMAD methodology' may not match natural user language.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'when the user wants to create a game', 'build a video game', 'game development project', or 'game prototype'.
Replace or supplement 'BMAD methodology' with plain language describing what it enables, such as 'structured game development workflow' or 'phased game creation process'.
Add concrete actions the skill performs, such as 'generates game design documents', 'creates technical architecture', 'produces asset specifications', or 'manages development milestones'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (game development) and lists phases (Pre-production, Design, Architecture, Production, Game Testing) and mentions engine support, but doesn't describe concrete actions like 'creates game design documents' or 'generates architecture diagrams'. | 2 / 3 |
Completeness | Describes what it does (routes game projects through phases with agents) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Unity', 'Unreal Engine', 'Godot', and 'Game Development', but missing common user terms like 'make a game', 'game project', 'indie game', or 'game design'. 'BMAD methodology' is technical jargon most users wouldn't naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of game development, specific engines (Unity, Unreal, Godot), BMAD methodology, and 6 specialized agents creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive command reference for a game development workflow system with good organization and clear phase-based structure. However, it lacks concrete examples of command usage, expected outputs, and validation checkpoints between workflow phases. The content describes what commands exist rather than demonstrating how to use them effectively.
Suggestions
Add a concrete example showing one command's input and expected output (e.g., what bmad-gds-game-brief prompts for and what file it generates)
Include validation checkpoints in the Typical Workflow section (e.g., 'Verify GDD completeness before proceeding to architecture')
Remove the Quick Reference section as it duplicates information already in the phase tables, or consolidate into a single reference
Add example file paths or directory structure showing where generated artifacts are stored
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient with table-based command references, but includes some redundancy (Quick Reference duplicates earlier tables) and the 'When to use' section explains obvious use cases Claude could infer. | 2 / 3 |
Actionability | Commands are clearly listed with descriptions, but there's no concrete example of actually running a command, expected inputs/outputs, or what files get generated. The workflow is described abstractly rather than with executable examples. | 2 / 3 |
Workflow Clarity | The 'Typical Workflow' section provides a clear 8-step sequence, but lacks validation checkpoints between phases. No guidance on what to verify before proceeding (e.g., 'ensure GDD is approved before architecture') or error recovery paths. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections (phases, agents, workflow, quick reference). Tables provide scannable overviews. The skill appropriately serves as an overview document pointing to commands without deeply nested references. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.