grug-brained-dev
Use when reviewing PRs, simplifying over-engineered code, judging architecture, or renaming unclear concepts — inline fake helpers, delete meatless ceremony, rename lying names, merge over-split files, reject premature abstraction, say no to speculative config/modes/layers, then end with the smallest safe next change. Triggers when code is too fancy, too abstract, too clever, too many files/helpers/layers, or too well-factored but painful to change. Embody Grug brain: complexity very bad, small words, no consultant speak, no hard pivot to opposite dogma.
72
63%
Does it follow best practices?
Impact
81%
1.65xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./grug-brained-dev/SKILL.mdEvaluation results
98%
54%Notification Service Code Review
Code review of over-engineered notification module
Grug output sections
0%
100%
No preamble
0%
100%
Grug voice maintained
0%
100%
Meat identified
75%
100%
Concrete smash verdict
66%
100%
Identifies fake helpers
80%
100%
Names scrutiny
75%
100%
No balance ritual
50%
100%
No hard pivot
50%
100%
Travel cost mentioned
100%
100%
Next bonk is small
25%
75%
Check mentioned in bonk
0%
100%
60%
8%Report Utilities Refactor
Refactor plan for helper-heavy utility module
Grug voice in plan
0%
0%
Grug output format
0%
0%
Fake helpers identified
100%
100%
Real helper kept
100%
100%
DRY nuance
0%
0%
No hard pivot
100%
100%
Plan as bonks
16%
75%
Stop signal in plan
66%
83%
Check mentioned in bonk
100%
100%
No balance ritual
100%
100%
Log helpers flagged
0%
0%
87%
34%Architecture Review: Order Processing System
Architecture review of over-engineered greenfield design
Grug voice maintained
0%
87%
Grug output sections
0%
70%
No cathedral for hut
91%
91%
Suspicious names flagged
50%
100%
Demon trapped check
30%
80%
Microservice demon named
80%
90%
Concurrency danger flagged
100%
100%
DDD/CQRS no sermon
87%
62%
No balance ritual
83%
100%
Next bonk is small
25%
100%
Greenfield warning
33%
66%
Fake cut points identified
50%
100%
- Repository
- joshuadavidthomas/agent-skills
- Commit
d20109a
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
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.