Agent skill
agent-friendly-cli
Use when writing command-line scripts agents will control
Install this agent skill to your Project
npx add-skill https://github.com/sanand0/scripts/tree/main/agents/agent-friendly-cli
Metadata
Additional technical details for this skill
- sources
-
[ "https://justin.poehnelt.com/posts/rewrite-your-cli-for-ai-agents/", "https://chatgpt.com/c/69aa737d-c6d8-839b-b573-90732dbdd3f0" ]
SKILL.md
- Support JSON input via
--jsonor--paramsand output via--output jsonor--format json. Prefer structured output as default for non-TTY. - Validate all inputs aggressively. Humans and agents make mistakes or can be adversarial. Support
--dry-runfor writes. Confirm before destructive actions - Add a schema or
--describecapability that returns machine-readable method signatures: params, request body, response types, ... - Design for context-window efficiency. Document and support filters, field masks, NDJSON pagination, etc. so agents can request only needed data.
- Support environment-variable-driven, headless execution for unattended use (tokens, credential file paths)
- Fail fast showing reason and correct invocation.
- Document with compact, explicit instructions and examples.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
llm
Call LLM via CLI for transcription, vision, speech/image generation, piping prompts, sub-agents, ...
data-story
Write data findings as a compelling narrative story, Malcolm Gladwell prose, NYT graphics-team visuals, engaging & memorable even for a non-technical audience.
design
ALWAYS follow this design guide for any front-end work
demos
Use when creating demos or POCs
uv-uvx
Tips on using uv and uvx (Python build tools) effectively with GitHub, Torch, etc.
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or explicit GPT-5.4 upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.
Didn't find tool you were looking for?