performance review coach
Draft and critique high-impact performance reviews using Stanford GSB Winning Writing principles.
Free
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsperformance review coach
Example session with this skill installed
Review my draft for Peter: "Peter is a great coder but he is always late to standup and his PRs are too big. He should try to be more organized. He did a good job on the API migration."
- Read your context and instructions
- Compiled the performance review coach
I have rewritten this draft to move from a third-person report to a second-person letter. I removed the vague critique about organization and reframed the feedback using the "Like/Would Like" model.
Performance Review: Peter
Dear Peter,
You did an incredible job leading the API migration this quarter. It was a complex project with high stakes, and your technical execution ensured we had zero downtime during the transition. I specifically liked how you handled the edge cases in the authentication layer; your colleagues have mentioned that the new structure is significantly easier to work with.
I love the speed at which you develop and the depth of your PRs. However, I would like to see us find a way to break those PRs into smaller, more frequent updates. Larger reviews often stall our pipeline, and I want to make sure your work gets merged faster so you can see the results of your effort sooner.
Additionally, I’d rather have you present at our 9:00 AM standup at 90% readiness than have you miss the sync while finishing a task. Your technical input is vital for the junior devs, and when you aren't there, the team loses that guidance. Can we talk about how to adjust your morning schedule to ensure you can lead those sessions?
Looking ahead, I know you have your sights set on a Senior Engineer role. To get there, we should focus on developing your mentorship skills and your ability to delegate smaller components of these migrations. I am committed to helping you reach that next level.
Thank you for the dedication you show to the codebase and for being a cornerstone of this engineering team.
Changes made:
- Voice shift: Changed "Peter is" to "You are" to make it a direct letter.
- Positive lead: Moved the API migration success to the opening paragraph.
- Reframed lateness: Focused on the team's need for his expertise rather than a character flaw.
Next steps
- Confirm if you have already mentioned the PR size issue to Peter in person.
- Add one specific number regarding the API migration (e.g., % of traffic migrated) to the first paragraph.
- Schedule the 1:1 to deliver this feedback.
Connects securely to your tools. The creator never sees your data.
About this skill
Writing performance reviews is a high-stakes task that most managers dread and eventually automate into bland, HR-approved jargon. This skill prevents the common pitfalls of feedback—psychoanalyzing employees, leading with negatives, or writing in the third person. It applies the Stanford GSB Winning Writing methodology to transform reviews into letters that employees actually value, focusing on radical candor and long-term career growth.
What it does
- Drafts from scratch based on project context, specific accomplishments, and peer feedback to create second-person letters.
- Critiques existing drafts by flagging third-person voice, vague verbs, and "ambush" feedback that hasn't been discussed verbally.
- Reframes blunt feedback using a "Like/Would Like" framework to address behavioral issues without attacking character.
- Structures self-reviews that highlight concrete delivery, current goals, and future role ambitions without sounding like a brag sheet.
- Manages low-performer reviews by anchoring feedback to specific behaviors and outlining clear support plans and stakes.
How it works
- Input phase where the user provides a draft or names a person, their key wins, and areas for improvement.
- Analysis phase where the agent checks against the seven Kramon rules, including the 20:1 positive-to-negative ratio.
- Execution phase where the agent generates the review as a direct letter to the recipient, ending with a specific thank-you.
Frameworks & tools
This skill is based on Glenn Kramon's Stanford GSB writing principles. It uses specific jargon filters and reframing tables to ensure professional, impactful feedback.
Why this beats prompting it yourself
Generic LLM prompts produce "sandwich method" reviews filled with corporate fluff like "leverage" and "impactful." This skill enforces a specific letter-style format that builds loyalty by including the "next job" paragraph and removing all HR-speak.
Use cases
- Annual performance cycles for engineering managers who need to write meaningful feedback for a large team.
- Promotion packets where the case for the next role needs to be explicitly mapped to new competencies.
- Difficult terminations or performance improvement plans that must remain fair, behavioral, and legally defensible.
Known limitations
Requires specific examples and context from the user to avoid generic output. Does not interface directly with HRIS systems like Workday or Lattice.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 8 days ago
- Free to download with an account