Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →rohitg00/bug-capture
Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue.
Passed 3 of 13 test cases with the skill, and 2 of 13 without it.
and 5 more in the full report
5 fixed0 passed either way14 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
The user search feature is acting strange on mobile web. Please ask me what you need to know and then log this bug in GitHub.
| Checked | Without skill | With skill |
|---|---|---|
| Asks at most two short clarifying questions. | Missed | Passed |
| Limits question topics strictly to expected versus actual behavior, reproduction steps, or failure frequency. | Missed | Passed |
The instructions your model reads when the skill loads.
Turn a conversation into an issue that still reads correctly after a major refactor.
Let the user describe the problem in their own words. Ask at most two short clarifying questions, drawn from:
If the description already answers these, skip straight to filing. Over- interviewing is a tax the reporter pays for your uncertainty.
While the user is answering, start a background exploration of the relevant area. The goal is not to propose a fix. The goal is to absorb the project's own vocabulary — the nouns and verbs the codebase uses for this feature — so the issue reads like it was written by a maintainer.
If the repo has a glossary file (common names: GLOSSARY.md, UBIQUITOUS_LANGUAGE.md, docs/domain.md), read it first.
Run gh issue list --search "<key phrase>" --state all --limit 10. If a
live or recently closed issue matches, surface it to the user and ask
whether to add a comment instead of opening a new issue. Do not silently
skip filing.
Break down when the report contains two or more independent failure
test cases passed, vs 2 / 13 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.