Printing Press

Generates production-ready CLIs for APIs with a single command. Point it at a spec, HAR file, or just an API name and it handles research, code generation, build verification, and real endpoint testing in one continuous loop. Version 2 strips out the busywork that inflated earlier workflows: no mandatory research docs before code exists, no late-stage validation theatrics. The dogfood phase actually runs every subcommand against live targets, not just structural checks. Ships with codex mode for offloading pure implementation to a specialized agent while keeping product decisions local. If you've ever burned an hour scaffolding a CLI by hand or shipped something that looked fine until you actually curled an endpoint, this closes that loop.

skills.sh installs: 7.9K
GitHub stars: 4.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mvanhorn/cli-printing-press --skill printing-press --agent claude-code

Installs into .claude/skills of the current project.

Files

/printing-press

Result: A working Go CLI in $PRESS_LIBRARY/<api-slug>/, plus up to five dense manuscripts archived to $PRESS_MANUSCRIPTS/<api-slug>/<run-id>/: research brief, absorb manifest, build log, shipcheck proof, and live smoke proof when live testing ran.

Next consumer: The user, who runs the CLI or ships it, and the sibling skills that take it from here: printing-press-polish for a second pass, printing-press-publish for the public library, printing-press-retro for findings against the Press itself.

Done: Every feature approved at the absorb gate is implemented, shipcheck reached ship, the live dogfood matrix ran against real targets, the CLI is promoted, and the receipt ledger closes on the last phase.

Intent: The best useful CLI for an API without an hour of phase theater. Optimize for time-to-ship, not time-to-document: reuse prior research when it is already good enough, run the cheap high-signal checks early, fix blockers before polish.