Polish a generated CLI to pass verification and become publish-ready. Runs diagnostics (dogfood, verify, scorecard, go vet, gosec), automatically fixes all issues (verify failures, static-analysis findings, dead code, descriptions, README, MCP tool quality), reports the before/after delta, and offers to publish. Use after any /printing-press run, or on any CLI in $PRESS_LIBRARY/. Trigger phrases: "polish", "improve the CLI", "fix verify", "make it publish-ready", "clean up the CLI", "get this ready to ship".
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow runs local diagnostics on the user's own CLI source, manuscripts, and spec files, and the only outsider-content path is the conditional browser re-discovery step, which reads arbitrary web pages the agent must actively navigate to.
mvanhorn/cli-printing-press
c9957c1
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.