skills.rest
khulnasoft-bot
khulnasoft-botCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-dx-cli-scale

Scores CLI tools against seven agent-first design principles on a 0-21 scale.

1|Updated Jun 30, 2026
Search Tags:#developer tools#cli#evaluation#json output#scoring rubric#cli design#agent dx
One-click install
npx skills add https://github.com/khulnasoft-bot/design.md --skill agent-dx-cli-scale-khulnasoft-bot
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-dx-cli-scale
Source: https://github.com/khulnasoft-bot/design.md/tree/main/.agents/skills/agent-dx-cli-scale
Command: npx skills add https://github.com/khulnasoft-bot/design.md --skill agent-dx-cli-scale-khulnasoft-bot

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? CLI tools are traditionally designed for humans, which makes them hard for AI agents to parse, prone to hallucinated inputs, and lacking safety rails. This Skill provides a structured rubric to evaluate how well any CLI supports agent-driven usage. ## Core Features & Use Cases - Seven-Axis Scoring: Rates machine-readable output, raw payload input, schema introspection, context window discipline, input hardening, safety rails, and agent knowledge packaging from 0 to 3 each. - Rating Bands: Maps total scores (0-21) to Human-only, Agent-tolerant, Agent-ready, or Agent-first classifications. - Multi-Surface Checklist: Notes MCP support, plugin installation, and headless authentication as bonus readiness signals. - Use Case: A platform team evaluating whether to adopt a new internal CLI for agent workflows can score it against the rubric and identify which axes need improvement before rollout. ## Quick Start Use the agent-dx-cli-scale skill to evaluate the design of our internal deployment CLI and produce a score for each of the seven axes.

Frequently Asked Questions about agent-dx-cli-scale

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate whether a CLI is designed for AI agents?▼

Score the CLI on seven axes: machine-readable output, raw payload input, schema introspection, context window discipline, input hardening, safety rails, and agent knowledge packaging. Each axis scores 0-3, and the total maps to a rating from Human-only to Agent-first.

What makes a CLI agent-first instead of human-first?▼

Agent-first CLIs default to structured JSON output, accept raw API payloads, expose runtime schema introspection, harden inputs against hallucination patterns like path traversal, and offer dry-run modes. Human-first CLIs optimize for discoverability and forgiveness instead.

What score range indicates a CLI is agent-ready?▼

A total score of 11-15 out of 21 indicates an agent-ready CLI with structured I/O, input validation, and some introspection. Scores of 16-21 indicate agent-first design with full schema introspection, comprehensive hardening, and packaged agent knowledge.

Does the scale cover MCP and headless authentication support?▼

Yes, but as an unscored bonus checklist rather than part of the 0-21 total. It notes whether the CLI exposes MCP over stdio JSON-RPC, supports extension or plugin installation, and allows headless authentication via environment variables.

What input hardening patterns should a CLI defend against for agents?▼

The rubric expects rejection of control characters, path traversals like ../, percent-encoded segments like %2e, and embedded query params in resource IDs. Top scores also require output path sandboxing to the working directory and HTTP-layer percent-encoding.

Related Skills

Explore More Software Engineering Skills→
DevMHOneDevMHOne

cli-eval

Automates the creation and execution of LLM benchmark evaluation suites via CLI.

Community
Advanced
albanistrefialbanistrefi
4

umbraco-cli

Inspect and mutate Umbraco Management API resources with JSON and dry-run options.

Community
Intermediate
Asygnuz-S-A-SAsygnuz-S-A-S

agent-dx-cli-scale

Scores CLI tools against seven agent-first design principles on a 0-21 scale.

Official
Basic
loveoplay2023-hueloveoplay2023-hue

mcporter

Manage MCP servers and invoke their tools via a command-line interface.

Community
Intermediate