Implement, scaffold, or modify an agent-ready CLI in a repository. Use when user says '/agent-ready-cli-build' or asks to build or implement a CLI from an existing spec, an OpenAPI file, or requirements. Produces a git-initialized repo on disk with source, tests, docs, and distribution instructions. For the full idea-to-delivery pipeline (story, spec, build, audit) prefer agent-ready-cli-end-to-end. Does not push, publish, or submit unless explicitly requested.
Deliver a complete agent-ready CLI end to end: gather inputs once, then run story → spec → build → audit/eval unattended. Use when user says '/agent-ready-cli-end-to-end' or asks to build an agent-ready CLI from an idea, requirements, or a bare OpenAPI file — prefer this over agent-ready-cli-build when no spec or repo exists yet. Produces a git-initialized repo with tests, docs, and distribution instructions. Claims no checklist score. Does not push, publish, or submit unless explicitly requested.
Audit an existing CLI against the Agent-Ready CLI Checklist. Evidence-first: identifies the target command, runs it with --help and safe read-only commands, finds install instructions and the docs page, scores the checklist, and produces prioritized fixes. Use when user says '/agent-ready-cli-audit' or asks to audit a CLI, check whether a CLI is agent-ready, or review a CLI/repo/docs for agent readiness — including questions like 'is our CLI good for agents?' or 'why do coding agents get stuck with our tool?'. Does not design new commands.
Turn CLI workflow stories, requirements, or an OpenAPI spec into an exact agent-ready command contract: command tree, grammar, flags, config precedence, auth, JSON schemas, stdin/stdout/stderr, dry-run/confirm behavior, verification commands, errors, exit codes, tests, and docs. Asks for requirements if none are given; OpenAPI file is the preferred input when the CLI wraps an API. Use when user says '/agent-ready-cli-spec' or asks to design a CLI command contract or write a CLI spec. Design only — not implementation.
Define what an agent-ready CLI should expose before writing commands: actors, environments, jobs-to-be-done, product-surface fit, workflow stories, success evidence, and non-goals. Accepts requirements and/or an OpenAPI spec as input and asks for requirements if missing. Use when user says '/agent-ready-cli-story' or asks what CLI to build, which workflows a CLI should expose, or whether CLI/API/MCP/Skill/UI is the right surface. Does not produce implementation code.
Review an OpenAPI specification against API standards and OpenAPI best practices. Point it at a spec — a path on disk, a URL, or a GitHub repo — and it reviews against its own bundled standards and best practices unless you supply yours. Produces a divergence report (verdict per standards section, each finding citing the rule it breaks) for the user to review; fixes are applied only after the user decides. Use when user says "/design-api-review" or asks to review, audit, or check an OpenAPI spec against standards. The spec is the only required input. Does not generate a spec (that is `design-api-spec`) and does not review implementation code.
Design an API end-to-end — from requirements to a validated OpenAPI spec. Generates stories for review, then produces a linted spec. Emmanuel Paraskakis's method for designing APIs with LLMs. Use when user says "/design-api" or asks to design an API from requirements or stories. For a single step only, use `design-api-stories`, `design-api-spec`, or `design-api-review` instead.
Generate an OpenAPI 3.1.0 specification from API design stories, a domain model, API standards, and OpenAPI best practices. Lints with RateMyOpenAPI and iterates to 100/100. Use when user says "/design-api-spec" or asks to generate an OpenAPI spec from stories. Does not write the stories (that is `design-api-stories`) and does not review an existing spec (that is `design-api-review`).