Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sipyourdrink-ltd/bernstein-quality
Show quality metrics for Bernstein runs - success rates per model, lint/test pass rates, completion time distributions.
Passed 3 of 10 test cases with the skill, and 4 of 10 without it.
1 fixed6 passed either way13 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
What exact command in our repository displays overall task success counts and fail counts for our coding agents?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies the command scripts/quality.sh metrics | Missed | Passed |
The instructions your model reads when the skill loads.
Analyze quality and reliability of agent-generated code.
Run scripts/quality.sh metrics for overall quality metrics.
Run scripts/quality.sh pass-rates for lint/typecheck/test pass rates by model.
Run scripts/quality.sh times for completion time distributions.
Present a quality dashboard:
## Quality Dashboard
### Success Rate by Model
| Model | Tasks | Success | Fail | Rate |
|-------|-------|---------|------|------|
| claude-sonnet-4 | 24 | 22 | 2 | 91.7% |
| gpt-4.1 | 12 | 10 | 2 | 83.3% |
### Pass Rates
| Check | Overall | claude-sonnet-4 | gpt-4.1 |
|-------|---------|-----------------|---------|
| Lint | 96% | 98% | 92% |
| Type-check | 88% | 91% | 83% |
| Tests | 85% | 89% | 75% |
### Completion Times
| Percentile | Time |
|------------|------|
| p50 | 3m 20s |
| p90 | 8m 45s |
test cases passed, vs 4 / 10 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.