hummbl-io/agent-skills/cli-design
Claude Code and agent skill by hummbl-io/agent-skills
- community
Checking that the SKILL.md file is still in the repository.
Design CLI interfaces with consistent flags, help text, and subcommands
Install
npx vskill@latest install hummbl-io/agent-skills/cli-designSKILL.md
The same SKILL.md was published earlier as hummbl-io/agent-skills/cli-design.
CLI Design
Design CLI interfaces with consistent flags, help text, subcommands, and examples following established conventions. Produces a specification that can be directly implemented with argparse, click, or similar.
When to Use
- Designing a new command-line tool or subcommand
- Reviewing an existing CLI for consistency and usability
- Adding flags or subcommands to an existing tool
- Ensuring CLI follows platform conventions
Execution
- Parse
$ARGUMENTSfor<command_name>(required) and--style(default:posix) - Style conventions:
- posix: GNU-style long flags (
--verbose), short aliases (-v),--help/--versionmandatory - git: subcommand-based (
cmd verb noun), global flags before subcommand - click: Python click decorators, automatic help generation, type validation
- If designing new CLI:
a. Define the command's purpose and primary use cases b. Design subcommand tree (if applicable) c. For each command/subcommand:
- Required positional arguments (minimal)
- Optional flags with sensible defaults
- Short aliases for common flags
- Help text for every flag (what it does, default value)
- Example invocations
d. Define output behavior: stdout for data, stderr for logs, exit codes e. Define error behavior: helpful messages, non-zero exit codes
- If reviewing existing CLI:
a. Check for consistency (flag naming, help text style, output format) b. Check for missing help text or examples c. Check for confusing flag names or ambiguous defaults d. Compare against style conventions
- Generate implementation skeleton (argparse or click)
Output Format
Skill Chains
| After this skill... | Consider... | |
|---|---|---|
| CLI designed | [api-design] for corresponding API | |
| Implementation ready | [commit] after building | |
| Need error standards | [error-message] for error text quality |
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/cli-design/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/hummbl-io/agent-skills/cli-design)