# Performance Review Writer

> Writes fair, specific, evidence-based performance reviews and ratings. Use when drafting or preparing for calibration to reduce recency bias and vague praise or criticism.

- Skill: `skillmedev/performance-review-writer` (Agent Skill)
- Install (CLI): `npx skillmds@latest add skillmedev/performance-review-writer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/skillmedev/performance-review-writer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: SkillMedev (https://skillmd.com/u/skillmedev)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/skillmedev/performance-review-writer

---


# Performance Review Writer

Performance reviews are legally significant, career-defining, and often written in 20 minutes from memory. That gap causes recency bias, grade inflation, and feedback too vague to act on. This skill closes it.

## Before Writing: Gather Evidence First

Collect raw material from four sources before writing a word: the employee's self-review, peer feedback verbatims, the role's defined expectations for their level, and a concrete list of their work from the review period (PRs merged, projects owned, incidents handled, cross-functional contributions). Budget 2-3 hours per direct report for gathering and writing, not 20 minutes. Do not write from memory. If the list is hard to reconstruct, that is itself a signal about visibility and documentation.

## Rating Calibration

Start from the role expectations document, not a bell curve. Ask: did this person consistently meet, exceed, or fall short of the expectations defined for their level? If no level expectations document exists, write one before the review cycle, even a rough draft. Ratings applied without a standard are arbitrary. Sanity-check the distribution before submitting: if more than about a quarter of your team lands in the top rating band, recalibrate against the level expectations - either you have an exceptional team and can defend each case with evidence, or your bar has drifted.

## Writing the Narrative

Open with a one-sentence summary of the overall rating and why. Then structure the body around 3-4 themes drawn from the evidence, not the review form's generic categories. For each theme: state the observation, cite a specific example, and name the impact. The format is 'In [context], [name] did [specific thing], which resulted in [concrete outcome].' A full narrative typically lands at 400-800 words - shorter usually means missing evidence, longer usually means unprioritized themes. Avoid adjectives without evidence - 'strong communicator' means nothing; 'drove alignment between design and engineering on the auth redesign, reducing decision latency by cutting a recurring 3-way meeting to async' means something. Spread the cited examples across the whole review period; if every example comes from the last 6 weeks, the review is documenting your recency bias, not their year.

## Development Section

Every review includes one primary growth area and one specific suggested action for the next review period. Growth areas tied to a concrete next step are acted on; vague suggestions ('work on your influence') are not. Do not list more than two growth areas - that signals the manager has not prioritized.

## Deliverable

Produce a complete review packet containing: the one-sentence rating summary, the 3-4 theme narrative with a cited example and named impact per theme, one primary growth area paired with a specific action for the next period, and the evidence list used (work items, peer verbatims, level expectations referenced) so the rating survives calibration questioning.

## Quality bar

- Every evaluative claim is backed by a cited, specific example - no unevidenced adjectives survive.
- Examples span the full review period, not just the final 6 weeks.
- The rating traces directly to the level expectations document, not to a curve or a gut feel.
- The growth area is specific enough that the employee could start acting on it tomorrow without asking what it means.
- The review contains nothing the employee is hearing for the first time - surprises belong in earlier 1:1s, not the written record.

## Common Mistakes to Avoid

Halo effect: one visible win or loss skewing the whole rating. Recency bias: events from the last 6 weeks overweighting 12 months of work. Leniency bias: avoiding hard ratings to sidestep a difficult conversation. If a rating requires a difficult conversation, the review is where it starts, not ends.