Install any skill in seconds. Free to start, no credit card required.
Get Started Free →oliver-kriska/boundaries
Analyze Phoenix context boundaries and module coupling via mix xref.
Passed 20 of 23 test cases with the skill, and 14 of 23 without it.
and 3 more in the full report
6 fixed14 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
When scoring context boundary health on a 0 to 100 scale, what weight is assigned to the 'Modules per context' metric?
| Checked | Without skill | With skill |
|---|---|---|
| Metric weight for modules per context is 20 percent | Missed | Passed |
The instructions your model reads when the skill loads.
Analyze module dependencies to ensure clean context separation and proper architectural boundaries.
/phx:boundaries # Check for violations
/phx:boundaries --assess # Score context health (0-100)
/phx:boundaries --fix # Suggest fixes for violations
--assess Mode: Context Health ScoreEvaluate overall boundary health with a quantified score.
| Metric | Healthy Range | Red Flag | Weight |
|---|---|---|---|
| Modules per context | 3-15 | >20 or <2 | 20% |
| Public API surface | 5-30 funcs | >40 funcs | 15% |
| Fan-out (contexts called) | 1-4 | >6 | 20% |
| Fan-in (called by contexts) | 1-6 | >10 | 15% |
| Circular dependencies | 0 | >0 | 15% |
| Boundary violations | 0 | >0 | 15% |
Use Glob to count .ex files per context directory under lib/my_app/*/.
Use Grep to count public function definitions per context file under lib/my_app/*.ex.
Run mix xref graph --format stats for dependency analysis.
Run mix xref graph --format cycles --label compile for compile-time circular dependencies.
## Context Health Assessment
### Overall Score: 82/100 (Good)
test cases passed, vs 14 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.