ClawHub

Doro Command Creator

v1.0.0

WHAT: Create Claude Code slash commands - reusable markdown workflows invoked with /command-name. WHEN: User wants to create, make, or add a slash command. U...

⭐ 0· 436·1 current·1 all-time
byMus Titou@a2mus
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The skill declares no env vars, no installs, and is instruction-only. Its guidance to check git state and write files to .claude/commands or ~/.claude/commands is consistent with a tool that creates slash-command markdown files.
ℹ
Instruction Scope
The SKILL.md stays on-topic (how to design and write slash-command files) but includes templates and examples that instruct agents to run and automate repository-changing operations (git add/commit, make all-ci, gt submit, Edit tool, TodoWrite, Task tool). This is expected for commands that themselves will perform CI/git actions, but users should be aware generated commands may execute or propose file edits and CI runs — review them before invocation.
✓
Install Mechanism
No install spec and no code files with executable installs are present (instruction-only). This minimizes disk/installation risk.
✓
Credentials
The skill requests no environment variables or credentials. References to tools (git, make, gt, Bash tool, Edit/Read tools, TodoWrite, Task tool) are plausible for creating/testing commands; no unrelated secrets are requested.
✓
Persistence & Privilege
always:false and no instructions to modify other skills or system-wide agent settings. The skill instructs creating files under project or user-level .claude directories only, which is appropriate for its purpose.
Assessment
This skill appears to do what it says: help you author slash-command markdown files. It asks for no secrets and installs nothing, which is good. Important cautions: the examples and templates show commands that run shell tools (git, make, gt), edit files, and can create commits/PRs — those are powerful actions. Before you (or an agent) invoke any generated command, review the command file content and confirm you want it to run the listed operations. Prefer creating/testing commands in a disposable repository or using the project-scoped location (.claude/commands/) rather than a global location (~/.claude/commands/) until you're confident. If you are concerned about autonomous agents running repository-changing commands, restrict the agent's tool permissions or require explicit user approval before executing any generated command.

Like a lobster shell, security has layers — review code before you run it.

latestvk979z622mpdpbht38brdc38wbx81t3e2

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments