Antigravity Skills - Build and Discover AI Agent SkillsAntigravity Skills

Acceptance Orchestrator Skill · Devops

Acceptance Orchestrator

Stop silent failures.

Automate coding tasks with a 2-round iteration limit and evidence-based verification. Deploy your AI agent skill today.

  • State Machine
  • Definition of Done
  • Runtime Verification
  • Issue Gating
  • Closed-Loop Delivery

About This Skill

Orchestrate coding work through a state machine featuring 7 distinct states and a strict 2-round iteration limit to ensure every task is proven via evidence before completion.

Quick Start

  1. 1Provide the issue ID and specific acceptance criteria (DoD)
  2. 2Allow the agent to pass through the issue gate verification
  3. 3Monitor the state machine as it moves from executing to accepted
Example Command
Run acceptance-orchestrator for issue #123 with DoD: 'API returns 200 OK on /health endpoint'

Core Capabilities

Intake

Automatically reads issues to extract task goals and the Definition of Done (DoD).

Issue Gate

Ensures implementation only begins when the issue is 'ready' and execution is explicitly allowed.

Review Loop

Manages PR feedback using a batched polling window of 3m, 6m, and 10m to optimize response times.

Deploy and Runtime Verification

Validates success using real logs and API behavior in the dev environment rather than assumptions.

Usage Examples

Input

Issue #45: Fix login timeout. DoD: Login takes < 2s.

Output

Status: accepted. Evidence: Log shows 1.2s response time.

Input

Issue #88: Update API docs. DoD: Swagger UI reflects v2 changes.

Output

Status: accepted. Evidence: Screenshot of Swagger UI v2.

Before

Manual tracking of PRs and hoping the fix works in dev without hard evidence.

After

Automated state machine that only marks 'accepted' when runtime evidence proves the 100ms threshold is met.

SKILL.md

---
name: acceptance-orchestrator
description: 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.
risk: safe
source: community
date_added: "2026-03-12"
---

# Acceptance Orchestrator

## Overview

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".**

## When to Use
- The task already has an issue or clear acceptance criteria and should run end-to-end with minimal human re-intervention.
- You need structured handoff across implementation, review, deployment, and final verification.
- You want explicit stop conditions and escalation instead of silent partial completion.

## Required Sub-Skills

- `create-issue-gate`
- `closed-loop-delivery`
- `verification-before-completion`

Optional supporting skills:
- `deploy-dev`
- `pr-watch`
- `pr-review-autopilot`
- `git-ship`

## Inputs

Require these inputs:
- issue id or issue body
- issue status
- acceptance criteria (DoD)
- target environment (`dev` default)

Fixed defaults:
- max iteration rounds = `2`
- PR review polling = `3m -> 6m -> 10m`

## State Machine

- `intake`
- `issue-gated`
- `executing`
- `review-loop`
- `deploy-verify`
- `accepted`
- `escalated`

## Workflow

1. **Intake**
   - Read issue and extract task goal + DoD.

2. **Issue gate**
   - Use `create-issue-gate` logic.
   - If issue is not `ready` or execution gate is not `allowed`, stop immediately.
   - Do not implement anything while issue remains `draft`.

3. **Execute**
   - Hand off to `closed-loop-delivery` for implementation and local verification.

4. **Review loop**
   - If PR feedback is relevant, batch polling windows as:
     - wait `3m`
     - then `6m`
     - then `10m`
   - After the `10m` round, stop waiting and process all visible comments toge

Frequently Asked Questions

FAQ

Which tools is this skill compatible with?
It is compatible with any AI agent framework that supports git-based workflows and the antigravityskills standard.
Who is the target audience for this skill?
It is designed for developers and DevOps engineers who need high-reliability automation for issue-to-deployment pipelines.
How does this differ from standard CI/CD pipelines?
Unlike standard pipelines, it uses a state machine to orchestrate the entire lifecycle, including intake and evidence-based acceptance, rather than just running tests.
What programming languages does it support?
The skill is language-agnostic; it focuses on the orchestration of the workflow and the verification of the defined results.
What are the expected results when using this skill?
You will receive a definitive status of either 'accepted' with accompanying evidence or 'escalated' with a clear reason for the block.

Discussion

Discussion

0 comments
U

On This Page

Trigger Phrases

Use these phrases to activate this skill in your AI coding assistant:

orchestrate this issuerun acceptance orchestratorhandle this task end-to-endverify DoD for this issueexecute issue-to-acceptance workflow