Find and fix technical debt including duplicated code, dead code, outdated patterns, and code smells. Run at the end of sessions to clean up.
SkillScore86Maintained
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆Coding pack
Last verified 8/9/2026
What it changes
Passed 17 of 20 test cases with the skill, and 12 of 20 without it.
Without skill59%
With skill86%
Checks it passed that the model alone missed
Flags functions longer than 50 lines as code smells.
Specifies ruff check . as the linter verification command.
Flags functions with more than 5 parameters as code smells.
and 4 more in the full report
7 fixed12 passed either way2 still failing1 broke
Pass-rate lift
+27 pp
Tokens
-19%
Agent turns
0%
Response time
-42%
Model gemini-3.6-flashMeasured 8/9/2026v119 of 22 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
In `src/core/engine.py`, public functions like `def calculate_metrics():` lack docstrings detailing arguments and return values. Which category does this belong to?
What was checked, without and with the skill
Checked
Without skill
With skill
Categorizes missing docstrings on public functions under Missing Best Practices.
Missed
Passed
case-14 · gemini-3.6-flash · 8/9/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md72 linessingle file
Technical Debt Finder
Identify and fix technical debt in the codebase.
What to Look For
Code Duplication
Functions with similar logic that could be consolidated
Copy-pasted code blocks
Repeated patterns that should be abstracted
Dead Code
Unused imports
Unused functions or classes
Commented-out code blocks
Unreachable code paths
Outdated Patterns
Deprecated API usage
Old-style string formatting (% or .format) vs f-strings