Agent Skills › open-mercato/open-mercato › om-auto-create-pr-loop

om-auto-create-pr-loop

GitHub

该 Skill 是 Open Mercato 仓库的 PR 自动创建循环扩展，定义了基于 AI 规范的自动化工作流。它明确了规范来源、集成测试门禁（Playwright）及 UI 风格检查，并规定了验证执行环境的选择，旨在实现代码提交的自动化闭环与质量保障。

.ai/skills/om-auto-create-pr-loop/SKILL.md open-mercato/open-mercato

Trigger Scenarios

需要基于 .ai/specs/ 下的规范自动生成 PR 时执行自动化测试门禁和集成测试流程时

Install

npx skills add open-mercato/open-mercato --skill om-auto-create-pr-loop -g -y

More Options

Non-standard path

npx skills add https://github.com/open-mercato/open-mercato/tree/main/.ai/skills/om-auto-create-pr-loop -g -y

Use without installing

npx skills use open-mercato/open-mercato@om-auto-create-pr-loop

指定 Agent (Claude Code)

npx skills add open-mercato/open-mercato --skill om-auto-create-pr-loop -a claude-code -g -y

安装 repo 全部 skill

npx skills add open-mercato/open-mercato --all -g -y

预览 repo 内 skill

npx skills add open-mercato/open-mercato --list

SKILL.md

Frontmatter

{
    "name": "om-auto-create-pr-loop",
    "description": "Open Mercato repo-local extension of the shared `om-auto-create-pr-loop` skill (installed from open-mercato\/skills into .agents\/skills\/). Pins the spec-completion gates (OM integration suites + om-ds-guardian) and the .ai\/specs\/enterprise spec scope."
}

Auto Create PR Loop — Open Mercato extension

This file extends the shared om-auto-create-pr-loop skill from open-mercato/skills (installed at .agents/skills/om-auto-create-pr-loop/SKILL.md). Follow the shared workflow with these repo specifics:

Spec sources: work may be driven by a file under .ai/specs/ or .ai/specs/enterprise/ (enterprise scope). The run-folder contract is documented in .ai/runs/README.md.
Spec-completion gates: "the repo's integration suite" means yarn test:integration (Playwright; see the om-integration-tests skill for ephemeral modes) plus yarn test:create-app:integration when the change touches template-synced surfaces. "Any style-compliance pass" means running the om-ds-guardian skill when UI was touched.
Checkpoint artifacts: browser-automation transcripts are Playwright transcripts (playwright.log) per the OM QA setup.
Validation runner: pick Docker vs local per root AGENTS.md § Validation Commands before running the gate.