ccpe-system/.codex/skills/ccpe-forge/templates/ccpe-model-card.md

artifact_type	model_name	model_id	aliases	author	version	created	updated	status	source_material	model_type	layer	related_models	related_agents	related_skills	related_runtimes	based_on
model-card								candidate								CCPE System

{Model Name}

1. Model Overview

1.1 One-Sentence Definition

1.2 Short Description

1.3 Model Type

Use one or more:

foundational
intermediate
applied
workflow-model
implicit-extracted
candidate
deprecated

1.4 Layer

Use one or more:

L0: Foundational Assumption
L1: Foundational Model
L2: Intermediate Model
L3: Applied Model
L4: Workflow / Procedure Model
L5: Output / Evaluation Lens

2. Source Material

2.1 Primary Source

title:
path:
author:
date:
source_type:

2.2 Secondary Sources

-
-
-

2.3 Extraction Notes

2.4 Confidence

Use one:

high
medium
low

3. Core Problem

3.1 Problem Statement

3.2 Why This Problem Matters

3.3 What Existing Thinking Misses

4. Scope

4.1 Applies To

-
-
-

4.2 Best Used When

-
-
-

4.3 Non-Scope

-
-
-

4.4 Boundary Conditions

5. Core Assumptions

1.
2.
3.

For each assumption, clarify:

assumption:
why it matters:
what would challenge it:

6. Core Mechanism

6.1 Mechanism Summary

6.2 Key Variables

- variable:
  meaning:
  role in model:

6.3 Causal / Generative Logic

6.4 Model Dynamics

7. Procedure / Operating Logic

7.1 Procedure

1.
2.
3.
4.
5.

7.2 If No Fixed Procedure

7.3 Decision Points

- decision point:
  criteria:
  possible outcomes:

8. Inputs

8.1 Valid Inputs

-
-
-

8.2 Poor Inputs

-
-
-

8.3 Required Context

-
-
-

9. Outputs

9.1 Output Types

-
-
-

9.2 Output Format

9.3 Good Output Criteria

-
-
-

10. Failure Modes

10.1 Common Failure Modes

1.
2.
3.

10.2 Overuse Risks

10.3 Misuse Risks

10.4 Degeneration Pattern

Example:

A causal model may degenerate into conspiracy-style explanation if it cannot define what would falsify it.

11. Falsification Boundary

11.1 What Would Challenge This Model?

-
-
-

11.2 What Should Not Happen If the Model Is Correct?

-
-
-

11.3 What Is Outside the Model's Explanatory Power?

-
-
-

11.4 Weak Falsification Warning

12. Distinctions

12.1 Different From

- nearby concept:
  distinction:

12.2 Not Equivalent To

-
-
-

12.3 Common Confusions

-
-
-

13. Related Models

13.1 Parent Models

-
-

13.2 Child Models

-
-

13.3 Sibling Models

-
-

13.4 Overlapping Models

-
-

13.5 Conflicting Models

-
-

14. Related Agents

- agent_id:
  path:
  usage:

15. Related Skills

- skill_id:
  path:
  usage:

16. Runtime Usage

- runtime_id:
  path:
  usage:

17. Examples

17.1 Example Input

17.2 Model Application

17.3 Example Output

17.4 Failure Example

18. Evaluation Criteria

Use this checklist when judging whether the model was applied well:

Core problem addressed?
Scope respected?
Assumptions made explicit?
Mechanism applied correctly?
Failure modes avoided?
Falsification boundary preserved?
Output useful?
Original conceptual force preserved?

19. Conversion Opportunities

19.1 Possible Skills

-
-

19.2 Possible Agents

-
-

19.3 Possible Runtimes

-
-

20. Version Notes

v0.1:
- Initial candidate Model Card.

21. Review Status

Use one:

needs-source-check
needs-user-confirmation
needs-scope-review
needs-falsification-boundary
needs-merge-review
reviewed

22. Open Questions

1.
2.
3.