claude-command-converter — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited claude-command-converter (Agent Skill) and scored it 83/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 4 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 4 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Convert Claude Code commands to standard Agent Skills format for portability across AI coding assistants.
.claude/commands/*.md files to skills/*/SKILL.md format..claude/commands/my-command.md).If input is missing, ask for the source command file path.
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
$ARGUMENTS
\`\`\`
[Command instructions...]Location: skills/<skill-name>/SKILL.md
---
name: skill-name
description: Complete description including what the skill does and when to use it.
---
# Skill Title
## When to Use
- Scenario 1
- Scenario 2
## Inputs
- Required input 1
- Optional input 2
## Workflow
1. Step 1
2. Step 2
...
## Outputs
- Output file 1
- Output file 2.claude/commands/.description from YAML frontmatter.handoffs for related skills/next steps.$ARGUMENTS handling for inputs.command.name.md → command-name (replace dots with hyphens).skills/<skill-name>/name and description only.## User Input section with $ARGUMENTS block.handoffs from frontmatter (move to prose)./command.name references (use skill names instead).name and description only.$ARGUMENTS.| Claude Command | Agent Skill |
|---|---|
$ARGUMENTS | Inputs section describing expected user input |
handoffs: | Next Steps section with skill references |
/command.name | skill-name (kebab-case) |
agent: foo.bar | foo-bar skill reference |
description: in frontmatter | description: expanded with triggers |
Inline ## User Input | Removed; documented in Inputs |
Input: .claude/commands/speckit.specify.md
---
description: Create feature specification from natural language.
handoffs:
- label: Build Technical Plan
agent: speckit.plan
---
## User Input
\`\`\`text
$ARGUMENTS
\`\`\`
The text the user typed after `/speckit.specify`...Output: skills/speckit-specify/SKILL.md
---
name: speckit-specify
description: Create or update a feature specification from a natural language feature description.
---
# Spec Kit Specify Skill
## When to Use
- The user wants a new or updated feature spec from a natural language description.
## Inputs
- Feature description from the user.
- Repo context with `.specify/` scripts and templates.
If the description is missing or unclear, ask a targeted question before continuing.
## Workflow
...
## Outputs
- `specs/<feature>/spec.md`
- `specs/<feature>/checklists/requirements.md`
## Next Steps
After generating spec.md:
- **Plan** technical implementation with speckit-plan.
- **Clarify** specification requirements with speckit-clarify.$ARGUMENTS, handoffs, /slash-commands).After conversion:
scripts/, references/, assets/.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.