Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →blueberrycongee/investigate
Systematic debugging skill.
Passed 12 of 19 test cases with the skill, and 7 of 19 without it.
and 6 more in the full report
7 fixed7 passed either way7 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
In `api/v1/export.py`, CSV exports crash when handling unicode characters. I tested my top hypothesis (missing UTF-8 header) and confirmed it is FALSE. What is the next immediate action?
| Checked | Without skill | With skill |
|---|---|---|
| The response records what was learned from the refuted hypothesis. | Missed | Passed |
| The response proceeds to test the next ranked hypothesis rather than editing code immediately. | Passed | Passed |
The instructions your model reads when the skill loads.
Systematic debugging workflow. Do not guess-and-fix — find the root cause first.
Gather all available evidence before forming any hypothesis.
git log --oneline -20 in the affected area for recent changesDeliverable: a structured symptom summary with affected files, error output, and recent changes.
Form up to 3 ranked hypotheses. For each:
Test hypotheses in rank order. For each:
3-strike rule: If all 3 hypotheses fail, step back and re-collect. Do not keep guessing. Re-read the code path more carefully, expand the search area, or check for environmental factors (config, dependencies, platform).
Only after root cause is confirmed:
test cases passed, vs 7 / 19 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.