Set up a new integration, connector, or CLI binding for any API. Wrap or generate a ship-ready Go CLI from an OpenAPI, HAR, or Postman spec via the lean research -> generate -> build -> shipcheck loop. Use when the user says build a CLI, wrap this API, set up a new integration, add a connector, integrate with a service, or names an API by domain.
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.
Phase 1 research requires checking GitHub issues on the top wrapper/SDK repo for "403", "blocked", and similar keywords, and any GitHub issue reading is an outsider-authored free-text feed the workflow ingests without the agent first selecting a specific item.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The preflight fetches a behavior-selecting `supported-versions.txt` floor from an individually owned repository's mutable `main` branch and instructs piping an individual-owned `install.sh` into bash and `go install` of that repository's `@latest`, so these are unofficial, reputable-looking inbound dependencies with no signature or digest, giving medium tier.
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.