Best use case
devkit-create-skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Enable interactive design mode
Teams using devkit-create-skill should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/devkit-create-skill/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How devkit-create-skill Compares
| Feature / Agent | devkit-create-skill | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Enable interactive design mode
Which AI agents support this skill?
This skill is designed for Codex.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# Create AIWG Skill
Create a new skill that can be triggered by natural language patterns.
## Understanding Skills
Skills differ from commands:
- **Commands**: Triggered by explicit `/command-name` invocation
- **Skills**: Triggered by natural language patterns (e.g., "apply voice", "validate writing")
Skills are ideal for:
- Capabilities users invoke conversationally
- Features that should "just work" without explicit commands
- Cross-cutting concerns that apply in many contexts
## Process
### 1. Validate Parameters
Verify `$ARGUMENTS` contains:
- Skill name (kebab-case)
- `--to` target (addon or framework, NOT extension)
**Note**: Skills cannot be added to extensions because skills need standalone functionality.
Check target exists:
```bash
ls ~/.local/share/ai-writing-guide/agentic/code/addons/<target>/
# or
ls ~/.local/share/ai-writing-guide/agentic/code/frameworks/<target>/
```
### 2. Interactive Design (if --interactive)
Guide the user through skill design:
**Skill Purpose**:
> What does this skill do? (e.g., "applies voice profiles to content", "validates code quality")
**Trigger Phrases**:
> What natural language phrases should activate this skill?
> Examples:
> - "apply voice", "use voice", "write in <voice> voice"
> - "validate code", "check quality", "review code"
> - "format document", "clean up", "prettify"
**Input Requirements**:
> What input does this skill need?
> - Content to process
> - Configuration parameters
> - File paths
**Output Format**:
> What does this skill produce?
> - Transformed content
> - Validation report
> - Recommendations
**Reference Materials**:
> Does this skill need supporting documentation?
> - Style guides
> - Validation rules
> - Example outputs
### 3. Execute Scaffolding
Run the CLI scaffolding tool:
```bash
node ~/.local/share/ai-writing-guide/tools/scaffolding/add-skill.mjs \
<name> \
--to <target>
```
### 4. Generated Structure
```
<target>/skills/<name>/
├── SKILL.md # Main skill definition
└── references/ # Supporting documentation
```
### 5. Customize SKILL.md
The generated SKILL.md needs customization.
**REQUIRED frontmatter fields:**
- `name:` — skill slug (kebab-case)
- `description:` — **Mandatory.** Used by Claude Code for NL matching and required by Codex (Codex rejects any SKILL.md without a non-empty description). Never leave this blank.
- `version:` — semver string (e.g., `1.0.0`)
- `priority:` — **Mandatory.** Importance level: `critical`, `high`, `medium`, or `low`. Used by corpus gap reports and backlog tooling to surface work items. Never omit.
```yaml
---
name: <skill-name>
description: <what this skill does — REQUIRED, non-empty>
version: 1.0.0
priority: medium
---
# <Skill Name>
## Trigger Phrases
Activate this skill when the user says:
- "<phrase 1>"
- "<phrase 2>"
- "<phrase 3>"
## Input
This skill expects:
- <input requirement 1>
- <input requirement 2>
## Execution Process
1. <Step 1>
2. <Step 2>
3. <Step 3>
## Output
This skill produces:
- <output 1>
- <output 2>
## Examples
### Example 1: <scenario>
**User**: "<example trigger>"
**Result**: <what happens>
### Example 2: <scenario>
**User**: "<example trigger>"
**Result**: <what happens>
```
### 6. Add Reference Materials
If the skill needs supporting documentation:
```bash
# Create reference files
touch <target>/skills/<name>/references/style-guide.md
touch <target>/skills/<name>/references/validation-rules.md
```
### 7. Update Manifest
The CLI tool automatically updates the manifest. Verify:
```json
{
"skills": ["existing-skill", "<new-skill>"]
}
```
## Output Format
```
Skill Created: <name>
─────────────────────
Location: <target>/skills/<name>/
Created:
✓ SKILL.md
✓ references/
Manifest updated: <target>/manifest.json
Next Steps:
1. Edit SKILL.md to define trigger phrases
2. Add execution process details
3. Create reference materials (if needed)
4. Test with natural language triggers
```
## Examples
```bash
# Create skill in addon
/devkit-create-skill code-formatter --to aiwg-utils
# Create skill with interactive guidance
/devkit-create-skill voice-apply --to voice-framework --interactive
# Create skill in framework
/devkit-create-skill requirement-tracer --to sdlc-complete
```
## Best Practices
1. **Clear trigger phrases**: Use natural, conversational language
2. **Multiple triggers**: Provide several ways to invoke the skill
3. **Specific execution**: Document exactly what happens when triggered
4. **Good examples**: Show realistic usage scenarios
5. **Reference materials**: Include supporting docs when needed
## References
- @$AIWG_ROOT/agentic/code/addons/aiwg-dev/README.md — aiwg-dev addon overview
- @$AIWG_ROOT/docs/extensions/extension-types.md — Extension types including skill type
- @$AIWG_ROOT/docs/cli-reference.md — CLI reference including add-skill command
- @$AIWG_ROOT/docs/extensions/creating-extensions.md — Guide to building custom extensions
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/vague-discretion.md — Concrete trigger phrase and loop termination requirementsRelated Skills
voice-create
Generate custom voice profiles from natural language descriptions by mapping tone, formality, and domain to voice dimensions
soul-create
Generate a SOUL.md identity file from source material, interactive prompts, or an existing voice profile
provenance-create
Create a W3C PROV-compliant provenance record for an artifact
issue-create
Create a new ticket/issue with configurable backend (Gitea, GitHub, Jira, Linear, or local files)
devkit-validate
Validate addon, framework, or extension structure and manifest
devkit-test
Auto-fix discoverable issues
devkit-create-framework
Comma-separated phase names
devkit-create-extension
Create a new AIWG extension (framework expansion pack) with AI-guided setup
devkit-create-command
Create a new slash command with AI-guided behavior definition
devkit-create-agent
Create a new agent with AI-guided expertise definition following the Agent Design Bible
devkit-create-addon
Create a new AIWG addon with AI-guided setup
create-prd
Create a Product Requirements Document (PRD) for a product feature