From antigravity-awesome-skills
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
npx claudepluginhub mit-network/antigravity-awesome-skillsThis skill uses the workspace's default tool permissions.
Orchestrate coding work as a state machine that ends only when acceptance criteria are verified with evidence or the task is explicitly escalated.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
Orchestrate coding work as a state machine that ends only when acceptance criteria are verified with evidence or the task is explicitly escalated.
Core rule: do not optimize for "code changed"; optimize for "DoD proven".
create-issue-gateclosed-loop-deliveryverification-before-completionOptional supporting skills:
deploy-devpr-watchpr-review-autopilotgit-shipRequire these inputs:
dev default)Fixed defaults:
23m -> 6m -> 10mintakeissue-gatedexecutingreview-loopdeploy-verifyacceptedescalatedIntake
Issue gate
create-issue-gate logic.ready or execution gate is not allowed, stop immediately.draft.Execute
closed-loop-delivery for implementation and local verification.Review loop
3m6m10m10m round, stop waiting and process all visible comments together.Deploy and runtime verification
dev by default.Completion gate
verification-before-completion.Move to accepted only when every acceptance criterion has matching evidence.
Move to escalated when any of these happen:
2 full roundsAlways stop for human confirmation on:
When reporting status, always include:
Status: intake / executing / accepted / escalatedAcceptance Criteria: pass/fail checklistEvidence: commands, logs, API results, or runtime proofOpen Risks: anything still uncertainNeed Human Input: smallest next decision, if blockedDo not report "done" unless status is accepted.