adb-skill-generator
Meta-tool for rapid adb-* skill creation from templates
70
26%
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 ./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.
The description is too terse and jargon-heavy to serve as an effective skill selector. It lacks a 'Use when...' clause, concrete action verbs, and natural trigger terms that a user would employ. While the domain (adb-* skill creation) provides some distinctiveness, the description needs significant expansion to be useful for skill selection among many options.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to create a new adb-* skill, scaffold skill files, or generate skill boilerplate from templates.'
Include natural trigger terms users would say, such as 'create new skill', 'scaffold', 'new adb skill', 'skill template', 'generate skill file'.
List specific concrete actions, e.g., 'Generates skill markdown files, configures YAML frontmatter, creates directory structure, and populates boilerplate content from predefined templates.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (adb-* skill creation) and a general action (rapid creation from templates), but doesn't list specific concrete actions like 'generates boilerplate', 'configures YAML frontmatter', 'scaffolds test files', etc. | 2 / 3 |
Completeness | It partially addresses 'what' (rapid skill creation from templates) but has no 'Use when...' clause or equivalent explicit trigger guidance, and the 'what' itself is vague. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | The terms 'meta-tool', 'adb-* skill creation', and 'templates' are technical jargon unlikely to match natural user queries. Users would more likely say 'create a new skill', 'scaffold a skill', or 'add a new adb skill'. | 1 / 3 |
Distinctiveness Conflict Risk | The 'adb-* skill creation' niche is fairly specific and unlikely to conflict with most other skills, but the term 'meta-tool' and 'templates' could overlap with other scaffolding or template-generation skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is significantly over-engineered for what is essentially a scaffolding CLI tool. It suffers from severe verbosity—explaining design philosophy, TOON format basics, and ecosystem context that Claude doesn't need. The actionability is moderate since CLI invocations are clear but the actual template content and error recovery workflows are missing. The content would benefit greatly from being cut to roughly 1/3 its current size.
Suggestions
Cut the content by 60-70%: remove Design Philosophy, 'What is TOON?', Common Customization Patterns, and Troubleshooting sections entirely—these explain things Claude already knows or can infer
Add explicit validation steps after generation: e.g., 'Verify generated SKILL.md has valid frontmatter' and 'Run generated launch script with --help to confirm it's functional'
Consolidate the three nearly-identical examples into one comprehensive example showing the most common flags, with a brief table for other flag combinations
Move the detailed template structure description and workflow documentation to separate reference files, keeping only the Quick Reference and Scripts sections in SKILL.md
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Contains extensive unnecessary explanation (Design Philosophy section, TOON explanation, ecosystem integration walkthrough, template structure breakdown). The 'What is TOON?' section explains concepts Claude doesn't need. Multiple redundant examples show the same basic command pattern. The 'Common Customization Patterns' and 'Troubleshooting' sections add bulk with minimal unique value. | 1 / 3 |
Actionability | Provides concrete CLI commands with specific flags and parameters, plus JSON output examples. However, the actual generator script is referenced but not provided—we see how to invoke it but not the implementation. The generated script templates are described structurally (9-section list) rather than showing executable template content. Customization patterns show snippets but lack full context. | 2 / 3 |
Workflow Clarity | The 4-step 'Integration with Ecosystem' section provides a reasonable sequence, and the generated directory structure is clear. However, there are no validation checkpoints—no step to verify the generated skill is correct, no feedback loop if generation partially fails. The exit codes are listed but there's no guidance on what to do when encountering codes 1 or 2 (partial/failed creation). | 2 / 3 |
Progressive Disclosure | References workflow/ directory and related skills, but the main SKILL.md is monolithic with too much inline content that could be split out (Design Philosophy, TOON explanation, template structure details, customization patterns). The 'Related Skills' and workflow sections hint at external references but the bulk of content is crammed into one file. | 2 / 3 |
Total | 7 / 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-data
- Commit
3dd3ac0
- 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.