agentleFS
nisarthnisarth/claude-skills-store/skills/human-resources/performance-review/SKILL.md

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

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.
  • SentrySkill

    architecture-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

  • SentrySkill

    security-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

  • OpenAISkill

    systematic-debugging

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    Also in 3 projects that use this

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
  1. Distinctive:

    Use a consistent rating scale:

    line 76
  2. Distinctive:

    Action: Create a manager review template, then guide through each report with prompts to surface specific examples and calibrate ratings …

    line 160
  3. Distinctive:

    Write reviews with specific examples, not general statements.

    line 167
  4. Distinctive:

    Avoid recency bias. Review the full period, not just the last month.

    line 173
  5. Distinctive:

    Never surprise someone in a review.

    line 175
  6. Distinctive:

    Keep calibration notes separate from the review shared with the employee.

    line 176

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

  1. Key accomplishments (3-5 with impact metrics)
  2. Challenges faced and lessons learned
  3. Skills developed during the period
  4. Areas for growth and development
  5. Goals for the next period
  6. Feedback on team and manager support

Manager Review Template:

  1. Results summary: What was delivered against expectations
  2. Competency assessment: How work was done (collaboration, communication, technical depth)
  3. Strengths: 2-3 key strengths with specific examples
  4. Development areas: 1-2 areas with actionable recommendations
  5. Overall rating with justification
  6. Promotion readiness assessment (if applicable)
  7. Compensation recommendation (if part of the cycle)

Calibration Prep:

  1. Rating distribution across the team
  2. Forced ranking or stack ranking (if required)
  3. Promotion nominees with supporting evidence
  4. Retention risk flags for top performers
  5. Performance improvement candidates with documentation

Step 3: Apply Rating Framework

Use a consistent rating scale:

RatingDefinition
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.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.