# Skills

## 1. Purpose

This directory stores reusable CCPE Skills.

A Skill is a reusable capability module.

It may encode:

```text
A tool procedure
A cognitive method
A workflow procedure
An evaluation checklist
A transformation process
A knowledge-management operation
```

A Skill is not merely a tool wrapper.

## 2. Directory Structure

Recommended subdirectories:

```text
skills/
├── cognitive/
├── tool/
├── workflow/
└── evaluation/
```

## 3. Skill Types

### 3.1 cognitive/

Use for cognitive or reasoning methods.

Examples:

```text
cognitive-imaging.skill.md
prediction-error-capture.skill.md
do-operator-test.skill.md
assumption-stress-test.skill.md
argument-chain-inspection.skill.md
```

### 3.2 tool/

Use for tool-use procedures.

Examples:

```text
voice-to-text-preprocessing.skill.md
pdf-extraction.skill.md
web-retrieval-cleaning.skill.md
```

### 3.3 workflow/

Use for reusable workflow procedures.

Examples:

```text
model-mining.skill.md
review-report-synthesis.skill.md
article-to-model-extraction.skill.md
knowledge-archival.skill.md
```

### 3.4 evaluation/

Use for validation or review procedures.

Examples:

```text
ccpe-quality-audit.skill.md
model-card-validation.skill.md
agent-spec-validation.skill.md
runtime-safety-check.skill.md
```

## 4. Skill Requirements

Each Skill should define:

```text
Purpose
Skill Type
Trigger Conditions
Input Contract
Output Contract
Procedure
Branch Logic
Stop Conditions
Failure Handling
Validation Checklist
Related Models
Related Agents
Related Runtimes
```

If the Skill uses tools, also define:

```text
Tool Scope
Allowed Uses
Actions Requiring Confirmation
Forbidden Actions
Tool Failure Handling
```

## 5. Skill vs Agent

A Skill does not need a persona.

A Skill should focus on repeatable capability.

If the artifact has a role, personality, and user-facing interaction contract, it may be an Agent instead.

## 6. Skill vs Model Card

A Skill executes a model or method.

A Model Card defines the model itself.

Example:

```text
cognitive-imaging-model.md
= the model

cognitive-imaging.skill.md
= the procedure that applies the model
```

## 7. Naming Convention

Use lowercase kebab-case.

Recommended pattern:

```text
{name}.skill.md
```

Examples:

```text
cognitive-imaging.skill.md
model-mining.skill.md
review-report-synthesis.skill.md
```

## 8. Skill Metadata

Recommended front matter:

```yaml
---
artifact_type: ccpe-skill
name:
skill_id:
author:
version:
created:
updated:
status:
skill_type:
target_platform:
related_models:
related_agents:
related_runtimes:
based_on: CCPE System
---
```

## 9. Status Values

Use:

```text
draft
experimental
active
deprecated
archived
```

## 10. Final Rule

Extract a Skill when a method should travel across Agents.

Do not extract a Skill when separation makes the system harder to use without improving reuse.