Command Development
Reference for authoring Claude Code slash commands: frontmatter, arguments, bash and file refs
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 21, 2026
- Environment
- Claude Code 2.x (agent harness)
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (SKILL.md not found in repo tree). The test below is what we measured on Jul 21, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Fetched SKILL.md via raw GitHub; frontmatter parses with name+description and version 0.2.0. Spot-checked 3 linked files (references/plugin-features-reference.md, references/frontmatter-reference.md, examples/simple-commands.md) — all HTTP 200. No security smells. For the output test I built the same command ("fix a GitHub issue by number") twice: a naive baseline and one following the skill body. Baseline had zero frontmatter, was written as messages TO the user ("Thanks for using this command!") — the exact anti-pattern the skill warns against — and used no argument tokens (0 occurrences of $1/$ARGUMENTS), so the issue number was never injected. The skill version added scoped frontmatter (argument-hint, allowed-tools: Bash(gh:*)), injected $1 in 3 places, used !`gh issue view $1` for context, and handled the missing-argument case. Trigger judgment: 3 command-authoring phrasings load it, 2 adjacent ones ("create a new PDF-parsing skill", "write a git commit message") correctly do not.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Command Development does
A reference skill that guides authoring Claude Code slash commands: YAML frontmatter fields (description, argument-hint, allowed-tools, model), dynamic arguments ($1/$ARGUMENTS), @ file references, inline bash execution, namespacing, and plugin-specific patterns. Triggers when the user asks to create a slash command, define command arguments, use command frontmatter, or organize commands. Covers both project/personal commands and plugin-bundled commands.
How to install Command Development
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Command Development
-
/command-developmentReference for authoring Claude Code slash commands: frontmatter, arguments, bash and file refs
It also activates on plain-language prompts like these:
-
Create a slash command with custom arguments -
Add file references to this command -
Use AskUserQuestion inside my new command
Frequently asked questions
- Is the Command Development skill free?
- Yes. The skill itself is free from tzachbon/smart-ralph. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Command Development work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md via raw GitHub; frontmatter parses with name+description and version 0.2.0. Spot-checked 3 linked files (references/plugin-features-reference.md, references/frontmatter-reference.md, examples/simple-commands.md) — all HTTP 200. No security smells. For the output test I built the same command ("fix a GitHub issue by number") twice: a naive baseline and one following the skill body. Baseline had zero frontmatter, was written as messages TO the user ("Thanks for using this command!") — the exact anti-pattern the skill warns against — and used no argument tokens (0 occurrences of $1/$ARGUMENTS), so the issue number was never injected. The skill version added scoped frontmatter (argument-hint, allowed-tools: Bash(gh:*)), injected $1 in 3 places, used !`gh issue view $1` for context, and handled the missing-argument case. Trigger judgment: 3 command-authoring phrasings load it, 2 adjacent ones ("create a new PDF-parsing skill", "write a git commit message") correctly do not.
- What is the Command Development SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Command Development?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Command Development with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.