pr

GitHub

根据验证协议和ADR自动生成PR正文,包含摘要、证据对比及可逆性分析,确保内容基于已有事实并符合术语规范。

Trigger Scenarios

平台审查阶段完成报告生成 打开或实质性更新PR

Install

npx skills add Yeachan-Heo/oh-my-claudecode --skill pr -g -y
More Options

Use without installing

npx skills use Yeachan-Heo/oh-my-claudecode@pr

指定 Agent (Claude Code)

npx skills add Yeachan-Heo/oh-my-claudecode --skill pr -a claude-code -g -y

安装 repo 全部 skill

npx skills add Yeachan-Heo/oh-my-claudecode --all -g -y

预览 repo 内 skill

npx skills add Yeachan-Heo/oh-my-claudecode --list

SKILL.md

Frontmatter
{
    "name": "pr",
    "metadata": {
        "credits": {
            "url": "https:\/\/github.com\/humanlayer\/skills\/blob\/main\/plugins\/show-me\/skills\/show-me\/SKILL.md",
            "author": "Dex Horthy",
            "merge-danger": "mattpocock\/skills",
            "organisation": "Humanlayer",
            "summary-visuals": "show-me",
            "merge-danger-url": "https:\/\/github.com\/mattpocock\/skills"
        }
    },
    "description": "Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout."
}

PR Body

When work lands behind a review, the PR body is the one artifact a reviewer outside the session reads. Everything it needs already exists in the paper trail — this skill assembles it and adds nothing that was not already established. The summary-visual discipline is inspired by show-me (credited in the frontmatter).

Template

## Summary
<one-line claim, then the smallest visual that proves it>

## Evidence
- **Before:** <output / failing check>
  **After:** <output / passing check>

## Reversibility
<Rollback: cheap via <mechanism> | expensive because <reason>>
<Blast radius: one line>

Sections

Summary

State the change in one sentence, then show the smallest view that makes the point. Match the visual to the change:

  • logic or an algorithm → pseudocode
  • runtime control flow → a call tree
  • UI structure → a component tree
  • file responsibility or a broad refactor → a shallow file tree
  • component interaction or data flow → a Mermaid diagram
  • the delta itself → a diff shaped like the change (component, layout, call tree, or state machine)

Show the whole block only when most of it is new, omitted context would hide ownership, or the reviewer needs a copyable target shape. One visual usually suffices; never all forms.

Evidence

Consume the verify protocol's output — BUILD, TEST, LINT, FUNCTIONALITY evidence, freshness rule inherited. Present before/after pairs: the exact check that failed before and passes after, quoted from the output itself. When the change is visual, prefer a captured screenshot; qa-tester can drive the runtime for one. Never re-collect evidence here and never claim evidence the verify pass did not produce.

Reversibility

Run the ADR test on the diff itself — the same three questions launch applies to decisions: hard to reverse? surprising without context? the result of a real trade-off? A no on all three is a cheap rollback: say by what mechanism (revert the merge, toggle the flag). Any yes means an expensive rollback: say why. Classify the door first: a two-way door (undo is cheap and ordinary) needs no ceremony beyond naming the undo; a one-way door says so explicitly and names what makes the step irreversible. Link the ADR when the change implements or touches one. Close with the blast radius in one line — what else this change can move.

Language

Terms come from GLOSSARY.md where a glossary exists (legacy yards not yet migrated keep it in CONTEXT.md). The PR is read outside the session; the glossary is the only vocabulary the reader shares with it.

Triggers

  • launch Phase 5, when the platform reviews through PRs: the completion report carries a PR body drafted by this skill.
  • Any session that opens or materially updates a PR.

Output

  • The PR body, ready to paste
  • The paper-trail pointers it relies on (verify evidence, ADRs, spec)

Version History

  • 6688a30 Current 2026-10-19 08:28

Same Skill Collection

skills/agent-doc-discipline/SKILL.md
skills/ai-slop-cleaner/SKILL.md
skills/architecture-survey/SKILL.md
skills/ask-navigator/SKILL.md
skills/ask/SKILL.md
skills/autopilot/SKILL.md
skills/autoresearch/SKILL.md
skills/cancel/SKILL.md
skills/ccg/SKILL.md
skills/configure-notifications/SKILL.md
skills/debug/SKILL.md
skills/deep-dive/SKILL.md
skills/deep-interview/SKILL.md
skills/deepinit/SKILL.md
skills/diagram/SKILL.md
skills/drydock/SKILL.md
skills/execute/SKILL.md
skills/external-context/SKILL.md
skills/graph/SKILL.md
skills/harbor/SKILL.md
skills/hud/SKILL.md
skills/intent/SKILL.md
skills/learner/SKILL.md
skills/local-build-reminder/SKILL.md
skills/loft/SKILL.md
skills/map/SKILL.md
skills/mcp-setup/SKILL.md
skills/merge-readiness/SKILL.md
skills/minimal-code-discipline/SKILL.md
skills/minimal-prose-discipline/SKILL.md
skills/omc-doctor/SKILL.md
skills/omc-reference/SKILL.md
skills/omc-setup/SKILL.md
skills/omc-teams/SKILL.md
skills/plan/SKILL.md
skills/project-session-manager/SKILL.md
skills/ralph/SKILL.md
skills/ralplan/SKILL.md
skills/refit/SKILL.md
skills/release/SKILL.md
skills/remember/SKILL.md
skills/research/SKILL.md
skills/review/SKILL.md
skills/sciomc/SKILL.md
skills/self-improve/SKILL.md
skills/session-flow/SKILL.md
skills/setup/SKILL.md
skills/skill/SKILL.md
skills/skillify/SKILL.md

Metadata

Files
0
Version
6688a30
Hash
c80af121
Indexed
2026-10-19 08:28

홈 - 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-10-20 08:41
浙ICP备14020137号-1