cli-agent-readiness

What problem does it solve?

It helps you measure how reliably an AI agent can use your CLI without getting stuck, mis-parsed options, or requiring trial-and-error.

Core Features & Use Cases

• Documentation Quality Scoring: checks whether agents can learn correct usage from AGENTS.md/CODING_AGENTS.md/README and whether key flags/env vars match <binary> --help.
• Machine-Readable Self-Description: verifies whether the CLI exposes a structured manifest/schema (or at least parseable --help) so agents can plan calls safely.
• Integration Readiness & Reproducible Setup: assesses presence/co-versioning of artifacts (e.g., MCP/OpenAPI/skills/tooling), whether installation is non-interactive and idempotent, and whether examples support realistic workflows.
• Use Case: You maintain an internal deployment CLI and want agents to run it safely; run this skill to pinpoint whether missing docs, poor schema support, drift-prone integrations, or weak examples are blocking reliable use.

Quick Start

Run the readiness evaluation for your CLI binary, then review evaluations/<cli-name>/readiness.md to see which dimensions are preventing agent-ready operation.