adb-skill-generator
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
Evaluation results
100%
92%New App Automation Skill Scaffolding
Skill directory structure and naming conventions
Root directory name
0%
100%
scripts/ subdirectory
0%
100%
workflows/ subdirectory
0%
100%
templates/ subdirectory
0%
100%
analysis/ subdirectory
0%
100%
SKILL.md present
0%
100%
SKILL.md frontmatter
0%
100%
Launcher script name
0%
100%
Checker script name
0%
100%
No extra scripts
100%
100%
Script names follow pattern
0%
100%
Skill placed under .claude/skills/
0%
100%
Without context: $0.5223 · 1m 43s · 29 turns · 2,946 in / 5,541 out tokens
With context: $0.7273 · 2m 32s · 31 turns · 709 in / 9,736 out tokens
100%
34%Write an App Launch Automation Script
9-section IndieDevDan script template
Section 1: Docstring
100%
100%
Section 2: Imports
100%
100%
Section 3: Constants
100%
100%
Section 4: Project root
0%
100%
Section 5: Data models
0%
100%
Section 6: Helpers
62%
100%
Section 7: Core logic
100%
100%
Section 8: Formatters
100%
100%
Section 9: CLI interface
70%
100%
Section 10: Entry point
100%
100%
Section ordering
42%
100%
uv run invocation
0%
100%
Without context: $0.4041 · 1m 45s · 19 turns · 25 in / 6,302 out tokens
With context: $0.6544 · 2m 21s · 26 turns · 32 in / 8,571 out tokens
100%
15%Create Automation Workflows for a Fitness App Skill
TOON workflow format and TOON+MD pairing
TOON file: name field
100%
100%
TOON file: description field
100%
100%
TOON file: parameters block
100%
100%
TOON file: phases block
100%
100%
Phase structure
44%
100%
Parameter templating syntax
90%
100%
Recovery rules
55%
100%
Workflow name matches filename
100%
100%
MD: purpose section
100%
100%
MD: parameters documented
100%
100%
MD: example command
37%
100%
MD: error handling section
100%
100%
Advanced workflow uses checker
100%
100%
Without context: $1.1432 · 2m 51s · 40 turns · 219 in / 9,569 out tokens
With context: $0.6377 · 2m 7s · 31 turns · 327 in / 7,500 out tokens
- Evaluated
- Agent
- Claude Code
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.