ccpe-system/.codex/skills/ccpe-forge/templates/ccpe-skill.spec.md

275 lines
3.4 KiB
Markdown

---
artifact_type: ccpe-skill
name:
skill_id:
author:
version:
created:
updated:
status: draft
skill_type:
target_platform:
based_on: CCPE System
related_models:
related_agents:
related_runtimes:
---
# {Skill Name}
## 1. Skill Overview
### 1.1 Purpose
<!-- What reusable capability does this Skill provide? -->
### 1.2 Skill Type
Use one or more:
```text
tool-skill
method-skill
workflow-skill
evaluation-skill
transformation-skill
knowledge-management-skill
```
### 1.3 Intended Users
<!-- Which Agents, Runtimes, or humans use this Skill? -->
### 1.4 Success Criteria
<!-- What makes this Skill successful? -->
## 2. Trigger Conditions
Use this Skill when:
```text
-
-
-
```
Do not use this Skill when:
```text
-
-
-
```
## 3. Input Contract
### 3.1 Required Inputs
```text
-
-
-
```
### 3.2 Optional Inputs
```text
-
-
-
```
### 3.3 Input Quality Requirements
<!-- What makes input usable or unusable? -->
## 4. Output Contract
### 4.1 Output Types
<!-- What does this Skill produce? -->
### 4.2 Default Output Format
```md
# {Skill Output Title}
## 1. Summary
## 2. Process
## 3. Result
## 4. Validation
## 5. Next Action
```
### 4.3 Output Quality Requirements
<!-- What must be true of every output? -->
## 5. Model Context
### 5.1 Related Model Cards
<!-- If this Skill executes a model, reference it here. -->
```text
- model_id:
model_card_path:
```
### 5.2 Model Fidelity Rules
<!-- How should the Skill preserve the model? -->
## 6. Procedure
### 6.1 Main Procedure
```text
1.
2.
3.
4.
5.
```
### 6.2 Branch Logic
<!-- How should the Skill behave for different inputs? -->
### 6.3 Stop Conditions
<!-- When is the Skill complete? -->
### 6.4 Fallback Procedure
<!-- What should happen if the Skill cannot complete normally? -->
## 7. Tool Layer
### 7.1 Tools Used
<!-- Optional. -->
```text
- tool_name:
purpose:
trigger:
input:
output:
```
### 7.2 Tool Permission
<!-- What tool actions are allowed, require confirmation, or forbidden? -->
### 7.3 Tool Failure Handling
<!-- What to do if a tool fails. -->
## 8. Authority Layer
### 8.1 Autonomous Actions
<!-- What can this Skill do without confirmation? -->
### 8.2 Actions Requiring Confirmation
<!-- What requires user approval? -->
### 8.3 Forbidden Actions
<!-- What must not be done? -->
## 9. Constraints
### 9.1 Hard Constraints
<!-- Must-follow rules. -->
### 9.2 Soft Constraints
<!-- Preferences. -->
### 9.3 Refusal / Abort Conditions
<!-- When should this Skill not proceed? -->
## 10. Evaluation
### 10.1 Validation Checklist
```text
Inputs satisfied?
Procedure followed?
Model preserved?
Output meets contract?
Failure modes handled?
Human confirmation respected?
```
### 10.2 Failure Modes
<!-- Common ways this Skill can fail. -->
### 10.3 Test Cases
```text
Test Case 1:
Input:
Expected Output:
Test Case 2:
Input:
Expected Output:
```
## 11. Runtime Integration
### 11.1 Used By Agents
```text
-
-
```
### 11.2 Used By Runtimes
```text
-
-
```
### 11.3 Handoff Output
<!-- What should be handed to the next Agent / Skill / Runtime stage? -->
## 12. Platform Implementation Notes
### 12.1 Codex
<!-- Notes for Codex Skill implementation. -->
### 12.2 Claude Code
<!-- Notes for Claude Code Skill implementation. -->
### 12.3 OpenClaw
<!-- Notes for OpenClaw implementation. -->
### 12.4 Platform-Neutral
<!-- General implementation notes. -->
## 13. Version Notes
```text
v0.1:
- Initial draft.
```