dexter-cnx/agent-engineering-toolkit/cli-creator
Claude Code and agent skill by dexter-cnx/agent-engineering-toolkit
- community
Checking that the SKILL.md file is still in the repository.
Build or refine a reusable agent-friendly CLI with compact output, structured modes where practical, setup checks, read-first flow, and companion skill support.
Install
npx vskill@latest install dexter-cnx/agent-engineering-toolkit/cli-creatorSKILL.md
The same SKILL.md was published earlier as dexter-cnx/agent-engineering-toolkit/cli-creator.
Purpose
Use this skill when repeated repository work should be turned into a reusable CLI instead of being solved with ad hoc shell commands.
Best-fit cases
- CI or build investigation
- report export
- API-backed search and read
- architecture validation
- localization generation
- changelog drafting
- local archive inspection
Principles
Design for repeated agent use.
The CLI should be:
- non-interactive by default
- compact by default
- machine-readable where practical
- explicit about setup and auth
- clear about discovery versus exact read
- able to export large results to files
- safe by default
- separated into read versus write paths
Recommended command shape
Use this structure unless the repository clearly needs something else:
<cli> doctor<cli> auth status<cli> search ...<cli> list ...<cli> read <id><cli> export ...<cli> download ...<cli> draft ...<cli> write ...
Recommended flags:
--json--limit--output--dry-run
Required workflow
- inspect repository conventions
- propose the command surface before implementation
- keep defaults small
- implement discovery output compactly
- require stable IDs for exact reads
- route large outputs to files
- keep live writes separate
- add or update a companion skill
- verify the CLI from outside the source directory
Deliverable format
Return:
- assumptions
- proposed command surface
- files to create or update
- implementation summary
- verification proof
- companion skill content
- shortest future invocation prompt
Anti-patterns
Avoid:
- interactive prompts
- giant stdout dumps
- mixed read and write behavior
- hidden state with no way to inspect it
- vague setup failures
- undocumented install paths
Security
- Security scanPassed, 95 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 repositoryCheckingoverlays/agent-friendly-cli/skills/cli-creator/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/dexter-cnx/agent-engineering-toolkit/cli-creator)