notque/vexjoy-agent / skills/meta/toolkit
toolkit
VerifiedToolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.
references/agent-evaluation/report-templates.md
View on GitHub# Evaluation Report Templates
Use the scorer's raw `total/max_total` and grade. Do not normalize to 100 or add qualitative points.
## Single Item
````markdown
# Evaluation Report: {name}
**Type**: Agent | Skill
**Evaluated**: {YYYY-MM-DD HH:MM}
**Structural Score**: {total}/{max_total} ({grade}; {percentage}%)
## Structural Precheck
| Check | Status | Earned | Max | Detail |
|---|---|---:|---:|---|
| {checks[*].name} | {checks[*].status} | {checks[*].earned} | {checks[*].max} | {checks[*].detail} |
**Secret penalty**: {secret_penalty}
## Qualitative Findings
### High
- **{file}:{line}**: {finding and impact}
### Medium
- **{file}:{line}**: {finding and impact}
### Low
- **{file}:{line}**: {finding and impact}
## Recommendations
1. **{Action}**: {specific guidance}
## Raw Output
```json
{score-component.py JSON result}
```
````
## Collection Summary
```markdown
# Collection Evaluation Summary
**Date**: {YYYY-MM-DD}
**Agents**: {count}
**Skills**: {count}
**Average structural percentage**: {percentage}%
## Grade Distribution
| Grade | Agents | Skills |
|---|---:|---:|
| A (90-100%) | {count} | {count} |
| B (75-89%) | {count} | {count} |
| C (60-74%) | {count} | {count} |
| D (40-59%) | {count} | {count} |
| F (0-39%) | {count} | {count} |
## Results
| Component | Type | Total | Max | Percentage | Grade | Primary issue |
|---|---|---:|---:|---:|:---:|---|
| {file} | {type} | {total} | {max_total} | {percentage}% | {grade} | {issue} |
## Common Qualitative Findings
| Finding | Count | Affected components |
|---|---:|---|
| {finding} | {count} | {files} |
```
## Quick Check
```markdown
# Quick Check: {name}
**Structural Score**: {total}/{max_total} ({grade}; {percentage}%)
| Check | Status | Earned/Max | Detail |
|---|---|---:|---|
| {name} | {status} | {earned}/{max} | {detail} |
**Top qualitative issue**: {evidence-backed issue or "None found"}
```
## Comparison
```markdown
# Comparison: {name1} vs {name2}
| Aspect | {name1} | {name2} |
|---|---:|---:|
| Structural score | {total}/{max_total} | {total}/{max_total} |
| Percentage | {percentage}% | {percentage}% |
| Grade | {grade} | {grade} |
| High qualitative findings | {count} | {count} |
## Recommendation
{Which component better fits the stated use and why.}
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |