Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot official · Anthropic

performance-review — Claude Code skill: what it does, how to install

Generates structured templates for self-assessments, manager reviews, and team calibration sessions.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add anthropics/knowledge-work-plugins --skill performance-review -a claude-code
Open on GitHub

What performance-review does

This skill builds structured performance review documents across three distinct modes: self-assessment, manager, and calibration. If you run the command without arguments, the assistant asks which format you need.

The templates include goal tracking tables, accomplishment breakdowns with measurable impact, and skill development plans. If HRIS or issue tracker connectors are active, the skill pulls prior review history and completed tickets. Without connectors, paste project context manually.

What it helps with

  • draft a structured self-assessment with measurable results
  • write a manager review with an actionable development plan
  • prepare rating distributions and promotion cases for calibration
  • translate vague feedback into specific behavioral examples

Example prompts for the agent

  • /performance-review self-assessment
  • /performance-review manager Alex
  • /performance-review calibration

How to install performance-review

1Skills CLI (Vercel)

npx skills add anthropics/knowledge-work-plugins --skill performance-review -a claude-code

2Manually: put the files in place

~/.claude/skills/performance-review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/performance-review/

From the same set89

The whole set →
data-visualization official anthropics Selects chart types based on data structure and produces Python visualization code in matplotlib, seaborn, and plotly. Useful for reports and research figures. Claude Code CX Codex Cursor +1 13,700installs documentation official anthropics A skill for technical writing that drafts READMEs, API references, runbooks, architecture docs and onboarding guides. Useful when the code exists but the description does not. Claude Code CX Codex Cursor +1 10,300installs build-dashboard official anthropics Builds a self-contained HTML dashboard with Chart.js charts, KPI cards, and filterable tables. Useful for turning raw data or queries into a standalone browser report. Claude Code CX Codex Cursor +1 9,100installs memory-management official anthropics This skill organizes workplace shorthand, names, and project details into files an agent can consult. It fits projects where requests rely on an internal vocabulary and shared context. Claude Code CX Codex Cursor +1 7,400installs task-management official anthropics Tracks commitments, active work, and follow-ups in a local TASKS.md file. Useful when managing project to-dos directly from the AI coding chat. Claude Code CX Codex Cursor +1 7,200installs architecture official anthropics Writes an Architecture Decision Record or reviews a system design: options, trade-offs, consequences. Useful when you have to pick between technologies. Claude Code CX Codex Cursor +1 6,700installs knowledge-synthesis official anthropics Merges search results across chats, emails, and documents into deduplicated answers with source attribution. Flags conflicting facts and scores source reliability. Claude Code CX Codex Cursor +1 6,400installs testing-strategy official anthropics This skill designs testing strategies and test plans for a project. Use it when you need test types, coverage goals, or gaps in existing checks. Claude Code CX Codex Cursor +1 6,400installs

Similar

prioritization-frameworks phuryn Reference guide to 9 prioritization frameworks: RICE, ICE, Opportunity Score, Kano, MoSCoW and more. Helps you pick the right method, compare approaches, and rank tasks by importance. Claude Code CX Codex Cursor +1 9,900installs cmux-keyboard-shortcuts manaflow-ai Configures cmux shortcuts in ~/.config/cmux/cmux.json. Useful for adopting tmux-style chords, auditing overrides, and validating syntax. Claude Code CX Codex Cursor +1 6,200installs mempalace-recall MemPalace Instructs the agent to query MemPalace before answering questions about past decisions, projects, or people. Prevents model hallucinations when facts are already stored. Claude Code CX Codex Cursor +1 1,300installs strategy-red-team phuryn Stress-tests PRDs, roadmaps, and strategies by attacking load-bearing assumptions before reality does, returning kill criteria and cheap tests. Claude Code CX Codex Cursor +1 9,200installs find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. Claude Code CX Codex Cursor +1 4,000,000installs grill-me Matt Pocock grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts. Claude Code 1,424,476installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs handoff Matt Pocock Creates a handoff document from the current conversation so another agent can continue the work. Use it when a task moves to a new session or agent. Claude Code 1,038,491installs

Questions about performance-review

How to install performance-review in Claude Code?

Run npx skills add anthropics/knowledge-work-plugins --skill performance-review -a claude-code. You can also save the definition directly to ~/.claude/skills/performance-review/SKILL.md.

What does performance-review do?

It generates standardized templates for employee self-evaluations, manager feedback reports, and team calibration meetings.

How does the skill work with external tools?

When linked to an HRIS connector, it retrieves employee history and roles. A project tracker connector lets it reference finished tickets and milestones directly.

Source text

SKILL.md · Apache-2.0
---
name: performance-review
description: 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 turning vague feedback into specific behavioral examples.
argument-hint: "<employee name or review cycle>"
---

# /performance-review

> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).

Generate performance review templates and help structure feedback.

## Usage

```
/performance-review $ARGUMENTS
```

## Modes

```
/performance-review self-assessment       # Generate self-assessment template
/performance-review manager [employee]    # Manager review template for a specific person
/performance-review calibration           # Calibration prep document
```

If no mode is specified, ask what type of review they need.

## Output — Self-Assessment Template

```markdown
## Self-Assessment: [Review Period]

### Key Accomplishments
[List your top 3-5 accomplishments this period. For each, describe the situation, your contribution, and the impact.]

1. **[Accomplishment]**
   - Situation: [Context]
   - Contribution: [What you did]
   - Impact: [Measurable result]

### Goals Review
| Goal | Status | Evidence |
|------|--------|----------|
| [Goal from last period] | Met / Exceeded / Missed | [How you know] |

### Growth Areas
[Where did you grow? New skills, expanded scope, leadership moments.]

### Challenges
[What was hard? What would you do differently?]

### Goals for Next Period
1. [Goal — specific and measurable]
2. [Goal]
3. [Goal]

### Feedback for Manager
[How can your manager better support you?]
```

## Output — Manager Review

```markdown
## Performance Review: [Employee Name]
**Period:** [Date range] | **Manager:** [Your name]

### Overall Rating: [Exceeds / Meets / Below Expectations]

### Performance Summary
[2-3 sentence overall assessment]

### Key Strengths
- [Strength with specific example]
- [Strength with specific example]

### Areas for Development
- [Area with specific, actionable guidance]
- [Area with specific, actionable guidance]

### Goal Achievement
| Goal | Rating | Comments |
|------|--------|----------|
| [Goal] | [Rating] | [Specific observations] |

### Impact and Contributions
[Describe their biggest contributions and impact on the team/org]

### Development Plan
| Skill | Current | Target | Actions |
|-------|---------|--------|---------|
| [Skill] | [Level] | [Level] | [How to get there] |

### Compensation Recommendation
[Promotion / Equity refresh / Adjustment / No change — with justification]
```

## Output — Calibration

```markdown
## Calibration Prep: [Review Cycle]
**Manager:** [Your name] | **Team:** [Team] | **Period:** [Date range]

### Team Overview
| Employee | Role | Level | Tenure | Proposed Rating | Notes |
|----------|------|-------|--------|-----------------|-------|
| [Name] | [Role] | [Level] | [X years] | [Rating] | [Key context] |

### Rating Distribution
| Rating | Count | % of Team | Company Target |
|--------|-------|-----------|----------------|
| Exceeds Expectations | [X] | [X]% | ~15-20% |
| Meets Expectations | [X] | [X]% | ~60-70% |
| Below Expectations | [X] | [X]% | ~10-15% |

### Calibration Discussion Points
1. **[Employee]** — [Why this rating may need discussion, e.g., borderline, first review at level, recent role change]
2. **[Employee]** — [Discussion point]

### Promotion Candidates
| Employee | Current Level | Proposed Level | Justification |
|----------|-------------|----------------|---------------|
| [Name] | [Current] | [Proposed] | [Evidence of next-level performance] |

### Compensation Actions
| Employee | Action | Justification |
|----------|--------|---------------|
| [Name] | [Promotion / Equity refresh / Market adjustment / Retention] | [Why] |

### Manager Notes
[Context the calibration group should know — team changes, org shifts, project impacts]
```

## If Connectors Available

If **~~HRIS** is connected:
- Pull prior review history and goal tracking data
- Pre-populate employee details and current role information

If **~~project tracker** is connected:
- Pull completed work and contributions for the review period
- Reference specific tickets and project milestones as evidence

## Tips

1. **Be specific** — "Great job" isn't feedback. "You reduced deploy time 40% by implementing the new CI pipeline" is.
2. **Balance positive and constructive** — Both are essential. Neither should be a surprise.
3. **Focus on behaviors, not personality** — "Your documentation has been incomplete" vs. "You're careless."
4. **Make development actionable** — "Improve communication" is vague. "Present at the next team all-hands" is actionable.

© anthropics · Apache-2.0 · anthropics/knowledge-work-plugins

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor