ccpe-system/workbench/analysis/cognitive-imaging-specialis...

125 lines
3.1 KiB
Markdown

# Classification Report: Cognitive Imaging Specialist
## 1. Source
```text
source_path: workbench/raw/认知显影者1.1.md
source_title: 认知显影专家 / Cognitive Imaging Specialist
source_version: 1.1
source_date: 2026-03-06
audit_mode: CCPE Forge Auditor Mode
```
## 2. Primary Classification
```text
Primary Classification: Hybrid Artifact
```
This artifact is not only a prompt. It is a self-contained model-backed expert Agent that embeds a cognitive model and an executable method.
## 3. Component Breakdown
```text
CCPE-Agent:
- Cognitive Imaging Specialist role
- Expert identity
- Interaction style
- Capability boundary
- Decision authority
Model Card candidate:
- 认知显影术 / Cognitive Imaging
- Five-layer cognitive imaging model
- Scope: complex adaptive systems, unfamiliar domains, low-feedback environments
- Assumptions: anti-intuition, compression, causal intervention
CCPE-Skill candidate:
- Cognitive Imaging five-step procedure
- Capture / Darkroom / Enlarger / Exposure / Development
- Prediction-error capture
- Do-Operator causal test
- Conspiracy breaker / falsification boundary
CCPE-Lite candidate:
- Portable expert prompt version for GPT / Gemini / Claude style assistants
- Useful because the original artifact is already human-facing and chat-operable
Runtime node candidate:
- Potential member in a review committee or model-mining committee
- Not currently a full Runtime by itself
Tool / retrieval policy candidate:
- Dynamic RAW Capture
- External search data treated as raw material, not truth
```
## 4. Usage Mode
```text
Primary Usage Mode: Expert Mode
Secondary Usage Mode: Hybrid Mode
```
The artifact is primarily a single expert assistant. Because version 1.1 adds external retrieval intake and distinguishes report mode from discussion mode, it also has Hybrid Mode elements.
## 5. Depth vs Automation Orientation
```text
Orientation: Depth-Oriented with Hybrid support
```
The core work is interpretive, theoretical, and judgment-heavy. Automation should only support retrieval intake, formatting, routing, and archival.
## 6. Runtime Need
```text
Runtime Need: Optional, not required for standalone use
```
A Runtime is not required to use this as a single expert assistant. A Hybrid or Interactive Runtime becomes useful only if this Agent is placed inside a committee workflow.
## 7. Current CCPE 2.0 Layer Mapping
```text
Core Layer:
-> Role Layer
-> Objective Layer
Execution Layer:
-> Capability Layer
-> Context Layer
-> Authority Layer
-> Tool / Retrieval Policy
Constraint Layer:
-> Constraint Layer
-> Authority Layer
-> Safety Rules
Operation Layer:
-> Workflow Layer
-> State Layer
-> Output Layer
-> Evaluation Layer
-> possible Runtime notes
Appendix:
-> Model Card candidate
-> Skill candidate
```
## 8. Classification Verdict
```text
认知显影者1.1
= CCPE-Agent
+ embedded Cognitive Imaging Model
+ reusable Cognitive Imaging Skill
+ portable CCPE-Lite prompt candidate
+ retrieval/tool policy
+ possible Runtime node
```
Do not split automatically. Split only if the next phase is explicitly Refactor Mode.