Skip to content

Agent skills

Agent skills drive gplay from natural-language prompts. Each skill is a folder with a SKILL.md that documents the intent, the gplay commands it runs, and the safety rails it enforces. They live in a companion repository: PollyGlot/google-play-cli-skills.

Terminal window
npx skills add PollyGlot/google-play-cli-skills

Works with Claude Code and other agent frameworks that read the skills format.

One skill per shipped namespace, plus a foundation skill for cross-cutting conventions:

SkillDrives
gplay-cli-usageCross-cutting conventions: output, exit codes, auth resolution (foundation)
gplay-setupAuth onboarding — service account, login, doctor
gplay-appsApps registry + app details
gplay-release-flowupload / promote / staged rollouts
gplay-tracksTracks + closed-track testers
gplay-reviewsReview triage and replies
gplay-metadata-syncStore listings + images sync
gplay-complianceData Safety declarations
gplay-teamUsers, grants, permission vocabulary

Two more are gated until their CLI surfaces ship: gplay-vitals (#49) and gplay-subscription-management (#51).

A skill encodes the safe path for a workflow: which command sequence, which rehearsal steps (--dry-run first), which acknowledgment flags exist and when a human should approve them. The agent contract explains the CLI-level primitives the skills build on.