performance-review
Skill1 starsChanged 7 months agoMITView on GitHub
Structure a performance review with self-assessment, manager template, and calibration prep. Use when review season kicks off and you need a self-assessment template, writing a manager review for a direct report, prepping rating distributions and promotion cases for calibration, or creating development plans.
27 other projects use a version of this.
Adopted by
Most recently taken up by
- XuHo-IT/Content-Agent-Kittheir own version, first seen Nov 15, 2026
- Cure-Consulting-Group/ProductEngineeringSkillstheir own version, first seen Nov 12, 2026
- Smaui94/ClaudeSkillCollectiontheir own version, first seen Nov 8, 2026
- frnkgns/Overgeared-Skillstheir own version, first seen Nov 8, 2026
- flopperj/dotfiles-coretheir own version, first seen Nov 4, 2026
- nledford/engineering-review-boardtheir own version, first seen Nov 3, 2026
Used with
Projects with it also use architecture-review, security-review and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SentrySkillarchitecture-review
Staff-level codebase health review. Finds monolithic modules, silent failures, type safety gaps, test coverage holes, and LLM-friendliness issues.
Also in 7 projects that use this
SentrySkillsecurity-review
Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.
Also in 9 projects that use this
OpenAISkillsystematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Also in 3 projects that use this
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
- anthropics/knowledge-work-plugins★ 36ksame name
- genspark-ai/genoffice★ 12ksame name
- microsoft/intelligent-terminal★ 2.2ksame name
- borgbase/vykar★ 722same name
- ShipSecAI/studio★ 380same name
- nledford/engineering-review-board★ 11same name
- bis-code/claude-toolkit★ 8same name
- XuHo-IT/Content-Agent-Kit★ 8same name
- frnkgns/Overgeared-Skills★ 7same name
- Sagargupta16/agent-recipes★ 4same name
17 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository164 other files it gives its agents.
- instrument-data-to-allotropeSkill
- literature-reviewSkill
- nextflow-developmentSkill
- scientific-problem-selectionSkill
- scvi-toolsSkill
- single-cell-rna-qcSkill
- discover-brandSkill
- enforce-voiceSkill
- generate-guidelinesSkill
- csat-reportSkill
- customer-escalationSkill
- customer-researchSkill
- draft-responseSkill
- kb-articleSkill
- sentiment-analysisSkill
- ticket-triageSkill
- analyzeSkill
- build-dashboardSkill
- create-vizSkill
- data-context-extractorSkill
- data-modelingSkill
- data-pipelineSkill
- etl-designSkill
- explore-dataSkill
- sql-queriesSkill
- statistical-analysisSkill
- validate-dataSkill
- write-querySkill
- accessibility-reviewSkill
- component-librarySkill
- design-critiqueSkill
- design-handoffSkill
- design-systemSkill
- frontend-designSkill
- research-synthesisSkill
- user-researchSkill
- ux-copySkill
- wireframingSkill
- Agent DevelopmentSkill
- CLAUDE.md ManagementSkill
- MCP Server BuilderSkill
- Plugin DevelopmentSkill
- Prompt EngineeringSkill
- Skill CreatorSkill
- curriculum-designSkill
- lesson-planningSkill
- quiz-generatorSkill
- study-guideSkill
- tutoringSkill
- api-designSkill
- architectureSkill
- ci-cd-pipelineSkill
- code-reviewSkill
- database-migrationSkill
- debugSkill
- dependency-auditSkill
- deploy-checklistSkill
- documentationSkill
- error-handlingSkill
- git-workflowSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 23 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 76
Use a consistent rating scale:
- Distinctive: line 160
Action: Create a manager review template, then guide through each report with prompts to surface specific examples and calibrate ratings …
- Distinctive: line 167
Write reviews with specific examples, not general statements.
- Distinctive: line 173
Avoid recency bias. Review the full period, not just the last month.
- Distinctive: line 175
Never surprise someone in a review.
- Distinctive: line 176
Keep calibration notes separate from the review shared with the employee.
“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Performance Review
Structure performance reviews including self-assessment templates, manager review frameworks, calibration preparation materials, and development plans. Ensure consistent, fair, and growth-oriented evaluation.
Workflow
Step 1: Select Review Framework
Based on the review type, prepare the appropriate framework:
- Self-assessment: Template for the employee to reflect on accomplishments, growth areas, and goals
- Manager review: Structured evaluation covering results, competencies, and development
- Calibration prep: Rating distribution analysis, promotion cases, and comparison matrices
- Development plan: Forward-looking growth plan with skill gaps, actions, and milestones
- 360-feedback: Multi-rater feedback collection framework with peer and cross-functional input
Collect context:
- Company values or competency framework (if available)
- Level expectations document or job ladder
- Key results or OKRs for the review period
- Prior review notes or development plan
Step 2: Build the Review Document
Self-Assessment Template:
- Key accomplishments (3-5 with impact metrics)
- Challenges faced and lessons learned
- Skills developed during the period
- Areas for growth and development
- Goals for the next period
- Feedback on team and manager support
Manager Review Template:
- Results summary: What was delivered against expectations
- Competency assessment: How work was done (collaboration, communication, technical depth)
- Strengths: 2-3 key strengths with specific examples
- Development areas: 1-2 areas with actionable recommendations
- Overall rating with justification
- Promotion readiness assessment (if applicable)
- Compensation recommendation (if part of the cycle)
Calibration Prep:
- Rating distribution across the team
- Forced ranking or stack ranking (if required)
- Promotion nominees with supporting evidence
- Retention risk flags for top performers
- Performance improvement candidates with documentation
Step 3: Apply Rating Framework
Use a consistent rating scale:
| Rating | Definition |
| Exceptional (5) | Consistently exceeds expectations, delivers outsized impact |
| Exceeds (4) | Regularly exceeds expectations in most areas |
| Meets (3) | Fully meets expectations, solid and reliable contributor |
| Developing (2) | Partially meets expectations, improvement needed in key areas |
| Below (1) | Does not meet expectations, immediate improvement required |
Target distribution (guidelines, not quotas):
- Exceptional: 5-10%
- Exceeds: 20-25%
- Meets: 50-60%
- Developing: 10-15%
- Below: 0-5%
Step 4: Generate Development Plan
For each person reviewed, create forward-looking development actions:
- Skill gaps: Specific competencies to build (tied to level expectations)
- Development actions: Concrete steps (courses, projects, mentoring, stretch assignments)
- Timeline: Quarterly milestones for each development area
- Support needed: Resources, coaching, or opportunities the manager should provide
- Success criteria: How progress will be measured
Output Format
## Performance Review: [Type]
**Employee**: [Name] | **Role**: [Title] | **Level**: [Level]
**Review Period**: [dates] | **Manager**: [Name]
---
### [Self-Assessment / Manager Review]
#### Key Accomplishments
1. **[Accomplishment]**: [Impact with metrics]
- Evidence: [specific examples]
2. **[Accomplishment]**: [Impact with metrics]
- Evidence: [specific examples]
#### Competency Assessment
| Competency | Rating (1-5) | Evidence |
|------------------------|--------------|----------------------------|
| [Technical Excellence] | X | [specific example] |
| [Collaboration] | X | [specific example] |
| [Execution] | X | [specific example] |
| [Leadership/Influence] | X | [specific example] |
#### Strengths
- [Strength with example]
- [Strength with example]
#### Development Areas
- [Area]: [Current state] -> [Target state]. Action: [specific step]
#### Overall Rating: [X/5 — Label]
**Justification**: [2-3 sentences explaining the rating]
#### Promotion Readiness
- [ ] Ready now [ ] Ready in 6 months [ ] Not yet (needs: [what])
### Development Plan
| Skill Gap | Action | Timeline | Success Metric |
|------------------|------------------------|----------|-----------------------|
| [Gap 1] | [Specific action] | Q1 | [How to measure] |
| [Gap 2] | [Specific action] | Q2 | [How to measure] |
### Calibration Notes (manager eyes only)
- Retention risk: LOW / MEDIUM / HIGH
- Comp adjustment recommended: Yes / No
- Additional context: [notes]Examples
User: "I need to write my self-assessment for annual review." Action: Provide the self-assessment template with prompts for accomplishments, growth areas, and goals. Coach on how to quantify impact.
User: "Help me write reviews for my 6 direct reports." Action: Create a manager review template, then guide through each report with prompts to surface specific examples and calibrate ratings consistently.
User: "Prep me for calibration. I have 12 people to rate." Action: Generate a calibration worksheet with rating distribution, promotion cases, and talking points for each rating decision.
Best Practices
- Write reviews with specific examples, not general statements. "Delivered Project X 2 weeks early, saving $50K" beats "good at execution."
- Separate results (what was achieved) from competencies (how it was achieved). Someone can hit targets through unsustainable methods.
- Calibrate across the team before finalizing individual ratings. Review all ratings together to ensure consistency.
- Development areas should be forward-looking and actionable, not a restatement of failures.
- Limit to 1-2 development areas. More than that dilutes focus and feels punitive.
- For self-assessments, encourage employees to quantify impact wherever possible: revenue, time saved, users impacted, bugs prevented.
- Avoid recency bias. Review the full period, not just the last month. Keep running notes throughout the cycle.
- For calibration, prepare promotion cases with evidence mapped to the next-level job description, not just "they've been here long enough."
- Never surprise someone in a review. If performance is below expectations, that feedback should have been delivered in real-time during the period.
- Keep calibration notes separate from the review shared with the employee. Retention risk and comp recommendations are manager-only data.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

