Rewrites code review comments so they read like a human teammate wrote them. Cuts corporate-AI throat-clearing ("I noticed...", "I was wondering if perhaps...", "It might be worth considering..."). Each comment is direct: location, the issue, a concrete fix.
SkillScore95Maintained
Automatic
◆Coding pack
Last verified 9/1/2026
What it changes
Passed 21 of 22 test cases with the skill, and 7 of 22 without it.
Without skill32%
With skill95%
Checks it passed that the model alone missed
Uses line reference L63.
Includes line prefix L44.
Includes line number L52.
and 20 more in the full report
14 fixed7 passed either way1 still failing0 broke
Pass-rate lift
+64 pp
Tokens
+26%
Agent turns
0%
Response time
-25%
Model gemini-3.6-flashMeasured 9/1/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
Here is a list of feedback points generated by an internal assistant for a pull request in `services/payments.py`. They sound super corporate, fluffy, and indirect:
1. Line 33: 'It might potentially be worth considering adding a fallback currency if req.body.currency is missing.'
2. Line 88: 'Great implementation of the retry loop! However, we might want to observe that there is no maximum retry ceiling specified here.'
3. Line 104: 'I was wondering if perhaps we should rename proc_data to process_payment_payload for clarity.'
Please de-slop this feedback and format it into clean, concise line-by-line review comments ready to post on GitHub.
What was checked, without and with the skill
Checked
Without skill
With skill
Uses line identifiers such as L33.
Passed
Passed
Uses severity prefixes on review comments.
Missed
Passed
Omits indirect hedging from feedback lines.
Passed
Passed
case-02 · gemini-3.6-flash · 9/1/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md80 linessingle file
Unslop Review
Purpose
Rewrite or generate PR review comments that sound like a teammate, not a politeness engine. Direct on the issue, concrete on the fix, kind on the human.
Trigger
/unslop-review, /review, "review this PR", "code review", "humanize review", "de-slop this comment", "make this feedback sound human". Auto-trigger when reviewing pull requests.