adb-skill-generator
Meta-tool for rapid adb-* skill creation from templates
76
Quality
41%
Does it follow best practices?
Impact
100%
1.88xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/adb-meta-automation/adb-skill-generator/SKILL.mdQuality
Discovery
17%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too terse and technical, failing to explain what the skill actually does in concrete terms or when it should be used. The 'adb-*' terminology assumes context that may not be available, and the lack of trigger guidance makes it difficult for Claude to know when to select this skill from a larger pool.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'create new adb skill', 'scaffold skill', 'generate skill from template'
Expand the capabilities section to list specific actions (e.g., 'generates boilerplate, creates file structure, populates frontmatter')
Define what 'adb-*' means or replace with more descriptive language that users would naturally use
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (adb-* skill creation) and one action (rapid creation from templates), but lacks comprehensive detail about what specific actions are performed or what templates are involved. | 2 / 3 |
Completeness | Only partially addresses 'what' (skill creation from templates) and completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Uses technical jargon ('Meta-tool', 'adb-*') that users would not naturally say. Missing natural keywords like 'create skill', 'new skill', 'skill template', or 'generate skill'. | 1 / 3 |
Distinctiveness Conflict Risk | The 'adb-*' prefix provides some specificity to a particular skill family, but 'skill creation' and 'templates' could overlap with other meta or scaffolding tools. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides highly actionable, executable guidance for generating ADB skills with clear examples and parameter documentation. However, it suffers from verbosity - explaining concepts like 'Convention over Configuration' and TOON format that Claude already knows, and including redundant sections that inflate token usage without adding value. The workflow lacks explicit validation steps after generation.
Suggestions
Remove 'Design Philosophy' section entirely - these are general software principles Claude already knows
Consolidate the TOON explanation into a single line reference (e.g., 'See adb-workflow-orchestrator for TOON format') rather than re-explaining it
Add explicit validation step after generation: 'Verify: python -c "import yaml; yaml.safe_load(open('SKILL.md'))"' or similar
Move 'Common Customization Patterns' and 'Troubleshooting' to a separate ADVANCED.md file, keeping only quick-start content in main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant redundancy - the workflow section repeats TOON explanations, there's excessive emoji usage, and sections like 'Design Philosophy' and 'Common Customization Patterns' explain concepts Claude already understands. The core content is useful but could be 40% shorter. | 2 / 3 |
Actionability | Excellent executable examples throughout - complete bash commands with all parameters, concrete JSON output examples, and specific file paths. The generated structure is clearly documented and commands are copy-paste ready. | 3 / 3 |
Workflow Clarity | The 4-step integration workflow is clear, but lacks validation checkpoints. There's no explicit verification step after generation (e.g., 'validate generated SKILL.md syntax') and no feedback loop for handling generation failures beyond exit codes. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but the document is monolithic at ~300 lines. The 'Related Skills' and 'Workflows' sections could be separate files. References to workflow/ directory exist but inline content is excessive. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- majiayu000/claude-skill-registry
- Commit
6213d1a
- 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.