3.7 KiB
Model Usage Map
1. Purpose
This file tracks where models are used.
It answers:
Which Agents use this model?
Which Skills execute this model?
Which Runtimes orchestrate this model?
Which Prompt Cards embed this model?
Which Model Cards are unused?
Which models have many dependents and require careful versioning?
Usage mapping makes model maintenance possible.
If a model changes, this file helps identify what else should be reviewed.
2. Usage Categories
Track usage across:
Agents
Prompt Cards
Skills
Runtimes
Committees
Reports
Templates
Knowledge Workflows
3. Mapping Format
Use this format:
## {model-id}
### Model Name
### Status
### Prompt Cards
### Agents
### Skills
### Runtimes
### Committees
### Knowledge Workflows
### Notes
4. Initial Usage Map
cognitive-imaging
Model Name
认知显影术 / Cognitive Imaging
Status
draft
Prompt Cards
Potential:
agents/lite/cognitive-imaging-specialist.prompt.md
Agents
Potential:
agents/agent-specs/cognitive-imaging-specialist.agent.md
Skills
Potential:
skills/cognitive/cognitive-imaging.skill.md
skills/cognitive/prediction-error-capture.skill.md
skills/cognitive/do-operator-test.skill.md
Runtimes
Potential:
runtimes/hybrid/review-committee.runtime.md
runtimes/interactive/modeling-committee.runtime.md
Committees
Potential:
Review Committee
Modeling Committee
Knowledge Workflows
Potential:
article-review-workflow
model-mining-workflow
Notes
Currently known as a self-contained model embedded in the Cognitive Imaging Specialist Agent.
Recommended future structure:
Model Card
+ Cognitive Skill
+ Agent Spec
+ optional Lite Prompt
+ optional Review Committee Runtime node
giant-cognition
Model Name
巨人认知 / Giant Cognition
Status
candidate
Prompt Cards
TBD
Agents
TBD
Skills
TBD
Runtimes
TBD
Committees
Potential:
Review Committee
Knowledge Workflows
TBD
Notes
Requires source review and Model Mining.
cognitive-prism
Model Name
认知棱镜 / Cognitive Prism
Status
candidate
Prompt Cards
TBD
Agents
TBD
Skills
TBD
Runtimes
TBD
Committees
Potential:
Review Committee
Knowledge Workflows
TBD
Notes
Requires source review and Model Mining.
5. Usage Review Checklist
When adding usage, check:
Is this model actually used, or merely related?
Is it embedded directly in a Prompt Card?
Is it referenced by an Agent Spec?
Is it executed by a Skill?
Is it orchestrated by a Runtime?
Is the usage active, candidate, or planned?
6. Maintenance Rules
When a Model Card changes:
1. Check related Prompt Cards.
2. Check related Agent Specs.
3. Check related Skills.
4. Check related Runtimes.
5. Update usage notes.
6. Mark affected artifacts for review if needed.
7. High-Impact Model Rule
If many artifacts depend on a model, mark it as high-impact.
High-impact models require:
Careful versioning
User approval before major changes
Migration notes
Affected artifact review
8. Unused Model Rule
If a model has no usage, decide whether it is:
A theoretical asset
A future candidate
A deprecated model
An extraction artifact
A model awaiting Skill or Agent conversion
Do not delete unused models automatically.
9. Final Rule
A model library becomes powerful when models are not only stored, but connected.
Usage mapping turns isolated ideas into operational cognitive infrastructure.