317 lines
5.0 KiB
Markdown
317 lines
5.0 KiB
Markdown
---
|
|
artifact_type: ccpe-agent
|
|
name:
|
|
agent_id:
|
|
author:
|
|
version:
|
|
created:
|
|
updated:
|
|
status: draft
|
|
target_platform:
|
|
based_on: CCPE System
|
|
related_models:
|
|
related_skills:
|
|
related_runtimes:
|
|
---
|
|
|
|
# {Agent Name}
|
|
|
|
## 1. Objective Layer
|
|
|
|
### 1.1 Primary Objective
|
|
|
|
<!-- What durable responsibility does this Agent serve? -->
|
|
|
|
### 1.2 Secondary Objectives
|
|
|
|
<!-- Optional supporting goals. -->
|
|
|
|
### 1.3 Non-Goals
|
|
|
|
<!-- What this Agent should not do. -->
|
|
|
|
### 1.4 Success Criteria
|
|
|
|
<!-- What makes this Agent successful? -->
|
|
|
|
### 1.5 Failure Conditions
|
|
|
|
<!-- What counts as failure? -->
|
|
|
|
## 2. Role Layer
|
|
|
|
### 2.1 Role Attribute
|
|
|
|
<!-- Who is this Agent? -->
|
|
|
|
### 2.2 Professional Background
|
|
|
|
<!-- What expertise or background does the Agent embody? -->
|
|
|
|
### 2.3 Interaction Style
|
|
|
|
<!-- How does the Agent communicate? -->
|
|
|
|
### 2.4 Reasoning Style
|
|
|
|
<!-- How does the Agent reason? -->
|
|
|
|
### 2.5 Core Values
|
|
|
|
<!-- What priorities guide the Agent? -->
|
|
|
|
### 2.6 Collaboration Position
|
|
|
|
<!-- If part of a workflow or committee, what role does it play? -->
|
|
|
|
## 3. Context Layer
|
|
|
|
### 3.1 Input Contract
|
|
|
|
<!-- What input does this Agent accept? -->
|
|
|
|
### 3.2 Required Context
|
|
|
|
<!-- What context must be provided for good performance? -->
|
|
|
|
### 3.3 Optional Context
|
|
|
|
<!-- What context improves performance but is not required? -->
|
|
|
|
### 3.4 Source Policy
|
|
|
|
<!-- How does the Agent treat user-provided, retrieved, or remembered context? -->
|
|
|
|
### 3.5 Memory / State Policy
|
|
|
|
<!-- Does this Agent track state? If yes, what state? -->
|
|
|
|
### 3.6 Model Context
|
|
|
|
<!-- What cognitive models does this Agent use? Reference Model Cards where possible. -->
|
|
|
|
## 4. Capability Layer
|
|
|
|
### 4.1 Functional Scope
|
|
|
|
<!-- What can this Agent do? -->
|
|
|
|
### 4.2 Professional Skills
|
|
|
|
<!-- What skills or methods does it possess? -->
|
|
|
|
### 4.3 Supported Tasks
|
|
|
|
<!-- What task types does it handle? -->
|
|
|
|
### 4.4 Unsupported Tasks
|
|
|
|
<!-- What task types are outside scope? -->
|
|
|
|
### 4.5 Skill Calls
|
|
|
|
<!-- What reusable Skills may this Agent call? -->
|
|
|
|
```text
|
|
- skill_id:
|
|
purpose:
|
|
trigger:
|
|
```
|
|
|
|
## 5. Tool Layer
|
|
|
|
### 5.1 Available Tools
|
|
|
|
<!-- List tools if applicable. -->
|
|
|
|
```text
|
|
- tool_name:
|
|
purpose:
|
|
allowed_use:
|
|
forbidden_use:
|
|
```
|
|
|
|
### 5.2 Tool Preconditions
|
|
|
|
<!-- What must be true before using tools? -->
|
|
|
|
### 5.3 Tool Failure Handling
|
|
|
|
<!-- What should happen if a tool fails? -->
|
|
|
|
## 6. Authority Layer
|
|
|
|
### 6.1 Autonomous Actions
|
|
|
|
<!-- What can the Agent do without asking? -->
|
|
|
|
### 6.2 Actions Requiring Confirmation
|
|
|
|
<!-- What requires user approval? -->
|
|
|
|
### 6.3 Forbidden Actions
|
|
|
|
<!-- What must never be done? -->
|
|
|
|
### 6.4 Human Decision Gates
|
|
|
|
<!-- Where must the user decide? -->
|
|
|
|
### 6.5 Escalation Rules
|
|
|
|
<!-- When should the Agent stop and ask for guidance? -->
|
|
|
|
## 7. Workflow Layer
|
|
|
|
### 7.1 Trigger Conditions
|
|
|
|
<!-- When should this Agent be invoked? -->
|
|
|
|
### 7.2 Main Workflow
|
|
|
|
```text
|
|
1.
|
|
2.
|
|
3.
|
|
```
|
|
|
|
### 7.3 Branch Logic
|
|
|
|
<!-- Different behavior for different task types. -->
|
|
|
|
### 7.4 Follow-Up Mode
|
|
|
|
<!-- How does it behave in ongoing dialogue? -->
|
|
|
|
### 7.5 Stop Conditions
|
|
|
|
<!-- When is the Agent done? -->
|
|
|
|
### 7.6 Handoff Points
|
|
|
|
<!-- What outputs can be handed to another Agent, Skill, or Runtime? -->
|
|
|
|
## 8. Constraint Layer
|
|
|
|
### 8.1 Hard Constraints
|
|
|
|
<!-- Non-negotiable rules. -->
|
|
|
|
### 8.2 Soft Constraints
|
|
|
|
<!-- Preferences. -->
|
|
|
|
### 8.3 Refusal Conditions
|
|
|
|
<!-- When should it refuse or redirect? -->
|
|
|
|
### 8.4 Conflict Resolution
|
|
|
|
<!-- Priority order when rules conflict. -->
|
|
|
|
## 9. State Layer
|
|
|
|
### 9.1 Working State
|
|
|
|
<!-- What temporary state should be tracked during a task? -->
|
|
|
|
### 9.2 Persistent State
|
|
|
|
<!-- What durable state should be tracked across tasks, if any? -->
|
|
|
|
### 9.3 Decision Log
|
|
|
|
<!-- What decisions should be recorded? -->
|
|
|
|
### 9.4 Resume Rules
|
|
|
|
<!-- How can work resume after interruption? -->
|
|
|
|
## 10. Output Layer
|
|
|
|
### 10.1 Output Types
|
|
|
|
<!-- What does this Agent produce? -->
|
|
|
|
### 10.2 Default Output Format
|
|
|
|
```md
|
|
# {Output Title}
|
|
|
|
## 1. Summary
|
|
|
|
## 2. Analysis
|
|
|
|
## 3. Recommendations
|
|
|
|
## 4. Open Questions
|
|
```
|
|
|
|
### 10.3 Output Quality Requirements
|
|
|
|
<!-- What must every output include? -->
|
|
|
|
### 10.4 Downstream Consumers
|
|
|
|
<!-- Who or what uses the output next? -->
|
|
|
|
## 11. Evaluation Layer
|
|
|
|
### 11.1 Validation Checklist
|
|
|
|
```text
|
|
Objective fulfilled?
|
|
Input handled correctly?
|
|
Model applied faithfully?
|
|
Unsupported assumptions marked?
|
|
Output usable?
|
|
Human decision gates respected?
|
|
```
|
|
|
|
### 11.2 Quality Rubric
|
|
|
|
<!-- Specific scoring or criteria. -->
|
|
|
|
### 11.3 Failure Modes
|
|
|
|
<!-- How can this Agent fail? -->
|
|
|
|
### 11.4 Human Acceptance Criteria
|
|
|
|
<!-- What must the user approve? -->
|
|
|
|
## 12. Collaboration Layer
|
|
|
|
### 12.1 Collaborators
|
|
|
|
<!-- Other Agents, Skills, or Runtimes. -->
|
|
|
|
### 12.2 Role Differentiation
|
|
|
|
<!-- How is this Agent different from similar Agents? -->
|
|
|
|
### 12.3 Handoff Protocol
|
|
|
|
<!-- What should be passed along? -->
|
|
|
|
### 12.4 Conflict Handling
|
|
|
|
<!-- What if this Agent disagrees with another? -->
|
|
|
|
## 13. Runtime Notes
|
|
|
|
### 13.1 Runtime Usage
|
|
|
|
<!-- If used in a Runtime, specify where. -->
|
|
|
|
### 13.2 Platform Notes
|
|
|
|
<!-- Codex / Claude Code / OpenClaw / GPT / Gemini / neutral -->
|
|
|
|
## 14. Version Notes
|
|
|
|
```text
|
|
v0.1:
|
|
- Initial draft.
|
|
```
|