Claude Skills
CollectionsCompareWorkflowsNominate
Sign inSign up
© 2026 Curated Agent Skills·Learn more about Agent Skills
Back to repository

analyze-performance

verified

Evaluation framework for analyzing decision-making quality across five dimensions.

View on GitHub

Marketplace

workaholic

qmu/workaholic

Plugin

core

development

Repository

qmu/workaholic

plugins/core/skills/analyze-performance/SKILL.md

Last Verified

February 4, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/qmu/workaholic/blob/main/plugins/core/skills/analyze-performance/SKILL.md -a claude-code --skill analyze-performance

Installation paths:

Claude
.claude/skills/analyze-performance/
Powered by add-skill CLI

Instructions

# Analyze Performance

Evaluate a development branch's decision-making quality.

## Calculate Metrics

```bash
bash .claude/skills/analyze-performance/sh/calculate.sh <base-branch>
```

Returns JSON with performance metrics:

```json
{
  "commits": 5,
  "started_at": "2026-01-15T10:00:00+09:00",
  "ended_at": "2026-01-15T14:30:00+09:00",
  "duration_hours": 4.5,
  "duration_days": 1,
  "velocity": 1.1,
  "velocity_unit": "hour"
}

## Evaluation Framework

Evaluate the developer's decision-making across five dimensions. For each, provide:

- A rating: Strong / Adequate / Needs Improvement
- 1-2 sentences of evidence-based analysis

### 1. Consistency

Did decisions follow established patterns? Were similar problems solved similarly? Did pivots converge toward better solutions rather than oscillate indecisively?

### 2. Intuitivity

Were solutions obvious and easy to understand? Did decisions align with common expectations? Would another developer find the choices natural?

### 3. Describability

Did final names land well? Were naming improvements made when better options were discovered? Did terminology avoid semantic conflicts and support future extension?

### 4. Agility

How well did the developer respond to unexpected issues? Did they iterate effectively, incorporating lessons learned into subsequent work? Were course corrections made quickly when needed?

### 5. Density

Does the code express meaning economically? Is the ratio of conceptual value to textual surface area high? Does the solution achieve its purpose without verbose scaffolding, redundant abstractions, or diluted semantics?

## Output Format

Return structured markdown:

```markdown
### Decision Quality Analysis

| Dimension      | Rating                            | Notes             |
| -------------- | --------------------------------- | ----------------- |
| Consistency    | Strong/Adequate/Needs Improvement | Brief observation |
| Intuitivity    | ...                               | ...        

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
2865 chars