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 absjaded/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.
Verifies tests pass on completed feature branch, presents options to merge locally, create GitHub PR, keep as-is or discard; executes choice and cleans up worktree.
Guides root cause investigation for bugs, test failures, unexpected behavior, performance issues, and build failures before proposing fixes.
Writes implementation plans from specs for multi-step tasks, mapping files and breaking into TDD bite-sized steps before coding.
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.