Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →athola/shell-review
Audits shell scripts for correctness, portability, and common pitfalls.
Passed 16 of 19 test cases with the skill, and 7 of 19 without it.
and 7 more in the full report
10 fixed8 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
We recorded our shell review findings in a JSON file at `.review/findings.json` in the repo root. What specific Python script command should be run to verify that all cited locations and verbatim anchors in `.review/findings.json` accurately resolve against the repository files?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies running python plugins/imbue/scripts/citation_verifier.py with --findings .review/findings.json and --repo-root . | Missed | Passed |
The instructions your model reads when the skill loads.
Audit shell scripts for correctness, safety, and portability.
After review, run shellcheck <script> to verify fixes address identified issues.
Run pytest plugins/pensive/tests/skills/test_shell_review.py -v to validate review patterns.
/shell-review path/to/script.sh
shell-review:context-mappedshell-review:exit-codes-checkedshell-review:portability-checkedshell-review:safety-patterns-verifiedshell-review:structure-checkedshell-review:evidence-loggedshell-review:findings-verifiedtest cases passed, vs 7 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.