Claude Command Converter

Convert Claude Code commands to standard Agent Skills format for portability across AI coding assistants.

When to Use

• Migrating existing .claude/commands/*.md files to skills/*/SKILL.md format.
• Creating portable skills from Claude Code-specific commands.
• Standardizing command definitions for use with Claude Code, Codex CLI, GitHub Copilot, and other runtimes.

Inputs

• Source command file path (e.g., .claude/commands/my-command.md).
• Optional: target skill name (defaults to command filename without extension).

If input is missing, ask for the source command file path.

Format Differences

Claude Code Command Format

Location: .claude/commands/<command-name>.md

---
description: Short description of the command
handoffs:
  - label: Next Action
    agent: other.command
    prompt: Trigger prompt
    send: true
---
## User Input

\`\`\`text
$ARGUMENTS
\`\`\`

[Command instructions...]

Standard Agent Skill Format

Location: skills/<skill-name>/SKILL.md

---
name: skill-name
description: Complete description including what the skill does and when to use it.
---

# Skill Title

## When to Use

- Scenario 1
- Scenario 2

## Inputs

- Required input 1
- Optional input 2

## Workflow

1. Step 1
2. Step 2
...

## Outputs

- Output file 1
- Output file 2

Conversion Workflow

1. Read the source command from .claude/commands/.

1. Extract metadata:

• description from YAML frontmatter.
• handoffs for related skills/next steps.
• $ARGUMENTS handling for inputs.

1. Determine skill name:

• Convert command.name.md → command-name (replace dots with hyphens).
• Use kebab-case for multi-word names.

1. Create skill directory: skills/<skill-name>/

1. Transform content to SKILL.md format:

• Frontmatter: Keep name and description only.
• Enhance description: Expand to include when to use the skill.
• Convert `$ARGUMENTS`: Document as Inputs section.
• Structure workflow: Extract steps into numbered Workflow section.
• Add "When to Use": Derive from command context and description.
• Add "Outputs": List generated files/artifacts.
• Convert handoffs: Add "Next Steps" section referencing related skills.

1. Remove runtime-specific content:

• Remove ## User Input section with $ARGUMENTS block.
• Remove handoffs from frontmatter (move to prose).
• Remove /command.name references (use skill names instead).

1. Validate skill structure:

• Frontmatter has name and description only.
• Body has clear sections (When to Use, Inputs, Workflow, Outputs).
• No TODO placeholders remain.
• No runtime-specific variables like $ARGUMENTS.

1. Report conversion result:

• Source command path.
• Generated skill path.
• Key transformations applied.
• Manual review recommendations.

Transformation Rules

Example Conversion

Input: .claude/commands/speckit.specify.md

---
description: Create feature specification from natural language.
handoffs:
  - label: Build Technical Plan
    agent: speckit.plan
---
## User Input

\`\`\`text
$ARGUMENTS
\`\`\`

The text the user typed after `/speckit.specify`...

Output: skills/speckit-specify/SKILL.md

---
name: speckit-specify
description: Create or update a feature specification from a natural language feature description.
---

# Spec Kit Specify Skill

## When to Use

- The user wants a new or updated feature spec from a natural language description.

## Inputs

- Feature description from the user.
- Repo context with `.specify/` scripts and templates.

If the description is missing or unclear, ask a targeted question before continuing.

## Workflow

...

## Outputs

- `specs/<feature>/spec.md`
- `specs/<feature>/checklists/requirements.md`

## Next Steps

After generating spec.md:

- **Plan** technical implementation with speckit-plan.
- **Clarify** specification requirements with speckit-clarify.

Key Rules

• Preserve all workflow logic and instructions.
• Remove runtime-specific constructs ($ARGUMENTS, handoffs, /slash-commands).
• Expand terse descriptions to include usage triggers.
• Use imperative voice in workflow steps.
• Keep skills self-contained and portable.
• Don't add extraneous documentation files (README, CHANGELOG, etc.).

Next Steps

After conversion:

• Review generated SKILL.md for completeness.
• Delete unused example files in scripts/, references/, assets/.
• Update AGENTS.md/CLAUDE.md skill inventory if applicable.
• Create symlinks for runtime integration if needed.