# Workbench Analysis

## 1. Purpose

This directory stores intermediate analysis produced by CCPE Forge.

Files here are not final artifacts.

They may include:

```text
Classification reports
Audit reports
Quality reports
Refactor plans
Model mining reports
Extraction notes
Comparison reports
Upgrade plans
Creation briefs
Human decision logs
```

## 2. Typical Use

Use this directory when CCPE Forge has analyzed a raw artifact but has not yet produced final upgraded outputs.

Examples:

```text
workbench/analysis/cognitive-imaging-specialist-audit-report.md
workbench/analysis/zhangliao-red-team-refactor-plan.md
workbench/analysis/cognitive-prism-model-mining-report.md
workbench/analysis/review-committee-creation-brief.md
```

## 3. Recommended File Types

### 3.1 Classification Report

Use for identifying artifact type.

Suggested filename:

```text
{name}-classification-report.md
```

### 3.2 Audit Report

Use for detailed diagnosis.

Suggested filename:

```text
{name}-audit-report.md
```

### 3.3 Refactor Plan

Use before rewriting or splitting artifacts.

Suggested filename:

```text
{name}-refactor-plan.md
```

### 3.4 Model Mining Report

Use when extracting models from articles or agent appendices.

Suggested filename:

```text
{name}-model-mining-report.md
```

### 3.5 Creation Brief

Use before creating a new Agent, Skill, Runtime, or Model Card.

Suggested filename:

```text
{name}-creation-brief.md
```

## 4. Analysis File Metadata

Recommended front matter:

```yaml
---
artifact_type:
source_path:
created:
status: analysis
mode:
review_status:
next_action:
---
```

Possible `mode` values:

```text
creator
auditor
refactor
model-mining
classification
```

Possible `review_status` values:

```text
needs-user-review
reviewed
accepted
rejected
superseded
```

## 5. Human Decision Logs

When analysis requires user decision, record it here.

Suggested structure:

```md
# Human Decision Log: {Artifact Name}

## Decision 1

### Question

### Options

### User Decision

### Date

### Impact
```

## 6. Analysis to Upgrade Flow

Typical flow:

```text
workbench/raw/{source}.md
→ workbench/analysis/{source}-audit-report.md
→ workbench/analysis/{source}-refactor-plan.md
→ workbench/upgraded/{source}-upgraded.md
→ canonical directory
```

## 7. Rules

Do not treat analysis files as canonical artifacts.

Do not update Model Index from analysis alone unless the user confirms the extracted model status.

Do not overwrite analysis reports unless they are clearly superseded.

Prefer creating new versions when decisions change.

## 8. Versioning

For iterative analysis, use:

```text
{name}-audit-report-v1.md
{name}-audit-report-v2.md
{name}-refactor-plan-v1.md
{name}-refactor-plan-v2.md
```

Or keep one current file and maintain a change log inside it.

## 9. Final Rule

This directory is the thinking bench.

It stores diagnosis, planning, and review before anything becomes canonical.