Meta-tool for rapid adb-* skill creation from templates
Install with Tessl CLI
npx tessl i github:majiayu000/claude-skill-registry-data --skill adb-skill-generator80
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 100%
↑ 1.88xAgent success when using this skill
Validation for skill structure
Discovery
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 identifies a clear niche (adb-* skill creation) but is too terse to be effective for skill selection. It lacks explicit trigger guidance and natural user keywords, making it difficult for Claude to know when to select this skill. The technical terminology may not match how users naturally request this functionality.
Suggestions
Add a 'Use when...' clause with trigger terms like 'create new skill', 'scaffold skill', 'add adb skill', 'generate skill template'
Expand the capabilities list to include specific actions like 'generates YAML frontmatter', 'creates skill file structure', 'sets up skill boilerplate'
Include natural language variations users might say such as 'new skill', 'make a skill', 'skill generator'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (adb-* skill creation) and one action (rapid creation from templates), but lacks detail on what specific actions are involved in skill creation or what templates are available. | 2 / 3 |
Completeness | Describes what it does (creates skills from templates) 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 'adb-*' and 'skill creation' which are relevant but technical. Missing natural variations users might say like 'create new skill', 'add skill', 'scaffold', or 'generate skill file'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'adb-* skill creation' niche is very specific and unlikely to conflict with other skills. The meta-tool framing and template focus create a clear, distinct purpose. | 3 / 3 |
Total | 8 / 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 strong actionability with executable commands and concrete examples, but suffers from verbosity and redundant explanations (TOON format explained twice, design philosophy that states obvious principles). The workflow lacks explicit validation steps between generation and usage, and the document would benefit from splitting reference material into separate files.
Suggestions
Remove the 'Design Philosophy' section entirely - these are obvious principles Claude already understands
Consolidate TOON explanations into a single reference or link to external TOON documentation instead of repeating inline
Add explicit validation step after skill generation: 'Step 2: Validate generated skill structure with --dry-run or similar'
Move 'Common Customization Patterns' and 'Script Template Structure' to separate reference files (e.g., CUSTOMIZATION.md, TEMPLATES.md) with clear links from main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant redundancy - the workflow section repeats TOON explanations that appear elsewhere, the 'Design Philosophy' section explains concepts Claude already knows, and the template structure sections are verbose. However, the core command examples are reasonably efficient. | 2 / 3 |
Actionability | Provides fully executable bash commands with clear parameter documentation, concrete examples showing exact output structure, and copy-paste ready code. The generated directory structure and JSON output examples are specific and actionable. | 3 / 3 |
Workflow Clarity | The 'Integration with Ecosystem' section provides a 4-step workflow, but lacks explicit validation checkpoints. There's no 'validate generated skill works' step between generation and implementation. The troubleshooting section partially addresses errors but doesn't integrate into the main workflow. | 2 / 3 |
Progressive Disclosure | References to related skills and workflow directory are present, but the document is monolithic with ~300 lines of inline content. The TOON explanation section, design philosophy, and common customization patterns could be split into separate reference files. Navigation between sections is implicit rather than clearly signaled. | 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 | |
Table of Contents
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.