feedback-rephraserlisted
Install: claude install-skill kalyvask/winning-writing
# Feedback rephraser
Source: `points/performance-review-rules.md` (reframing kit) and `points/core-rules.md` (say what you like + what you would like).
## Why this exists
Blunt feedback feels honest to the giver and burns trust with the receiver. The receiver hears *"you are bad at X"* even when the giver meant *"the work needs Y."* The fix is mechanical: lead with what you LIKE, then what you WOULD LIKE, anchored to the WORK, phrased as a QUESTION where possible.
The principle generalizes across every channel — annual review, Slack DM, 1:1 talking point, peer review comment, HR script. Same rewrite, same rules.
## What to detect
Catch any sentence that does one or more of:
- Addresses a personal trait, not a behavior in the work (*"you don't smile enough," "you're intellectually intimidating," "you're too blunt"*)
- Tells the person to *stop* something without naming what to do instead (*"stop interrupting," "stop being late"*)
- Uses *you are* / *you're too* / *you don't* as the load-bearing verb
- Speculates about the person's emotional state (*"you're burning out," "you don't care"*)
- Mentions personal context the writer hasn't been invited to discuss (*"because of your divorce," "since the baby was born"*)
- Phrases a complaint as a declaration when a question would land softer (*"this isn't working"*)
## The five-move reframe
Every rewrite uses some combination of these moves:
1. **Open with what you LIKE** — at least one named, specific thing.
2. **Re-aim at