code-yeongyu/oh-my-openagent · .opencode/skills/work-with-pr/SKILL.md

work-with-pr skillA

Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the smallest atomic, independently-mergeable PRs and builds the independent ones concurrently via one worktree per PR driven by parallel subagents or a team. Unbounded loop: any failing ga

Latest version
mdr add code-yeongyu/oh-my-openagent/work-with-pr@git:20260816.63d873b
Exact content
mdr add code-yeongyu/oh-my-openagent/work-with-pr@sha256:2daaab7275a5dc02
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_xdlablgxq273ldf3.svg)](https://markdownregistry.com/a/art_xdlablgxq273ldf3)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260816.63d873b latest2026-08-16 63d873b 18,663 BA view · diff
git:20260714.2e5e9eb2026-07-14 2e5e9eb 17,734 BA view · diff
git:20260714.0657c2f2026-07-14 0657c2f 19,736 BA view · diff
git:20260714.9d71ac52026-07-14 9d71ac5 19,636 BA view · diff
git:20260714.158402e2026-07-14 158402e 19,483 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.

Source

GitHub

code-yeongyu/oh-my-openagent · 68,731 stars · license NOASSERTION · pushed 2026-09-05 · branch dev

API

GET https://markdownregistry.com/api/v1/artifacts/art_xdlablgxq273ldf3
GET https://markdownregistry.com/api/v1/resolve?ref=code-yeongyu/oh-my-openagent/work-with-pr
GET https://markdownregistry.com/api/v1/blob/2daaab7275a5dc02f517e73deedf4763def22be25f83165fe48ab67b5be80cce