acceptance-orchestrator
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.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- acceptance-orchestrator
- risk
- safe
- source
- community
- date_added
- 2026-03-12
- 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.
03 SKILL.md 正文
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-gateclosed-loop-deliveryverification-before-completion
Optional supporting skills:
deploy-devpr-watchpr-review-autopilotgit-ship
Inputs
Require these inputs:
- issue id or issue body
- issue status
- acceptance criteria (DoD)
- target environment (
devdefault)
Fixed defaults:
- max iteration rounds =
2 - PR review polling =
3m -> 6m -> 10m
State Machine
intakeissue-gatedexecutingreview-loopdeploy-verifyacceptedescalated
Workflow
-
Intake
- Read issue and extract task goal + DoD.
-
Issue gate
- Use
create-issue-gatelogic. - If issue is not
readyor execution gate is notallowed, stop immediately. - Do not implement anything while issue remains
draft.
- Use
-
Execute
- Hand off to
closed-loop-deliveryfor implementation and local verification.
- Hand off to
-
Review loop
- If PR feedback is relevant, batch polling windows as:
- wait
3m - then
6m - then
10m
- wait
- After the
10mround, stop waiting and process all visible comments together.
- If PR feedback is relevant, batch polling windows as:
-
Deploy and runtime verification
- If DoD depends on runtime behavior, deploy only to
devby default. - Verify with real logs/API/Lambda behavior, not assumptions.
- If DoD depends on runtime behavior, deploy only to
-
Completion gate
- Before any claim of completion, require
verification-before-completion. - No success claim without fresh evidence.
- Before any claim of completion, require
Stop Conditions
Move to accepted only when every acceptance criterion has matching evidence.
Move to escalated when any of these happen:
- DoD still fails after
2full rounds - missing secrets/permissions/external dependency blocks progress
- task needs production action or destructive operation approval
- review instructions conflict and cannot both be satisfied
Human Gates
Always stop for human confirmation on:
- prod/stage deploys beyond agreed scope
- destructive git/data operations
- billing or security posture changes
- missing user-provided acceptance criteria
Output Contract
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 blocked
Do not report "done" unless status is accepted.
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
04 同仓库更多 Skills
vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.