Catalog
Yeachan-Heo/pr

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.

v1.0LATEST
NewUpdated Oct 2, 2026

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. 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 CONTEXT.md where a glossary exists. 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)
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

72/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

92

Quality

68

Clarity

76

Completeness

58

Summary

This skill guides an agent to draft high-quality pull request bodies by assembling evidence from a project's paper trail (verification outputs, ADRs, specs) into a structured template with summary, evidence, and reversibility sections. It emphasizes consuming existing documentation rather than re-collecting evidence, and uses visual aids (pseudocode, diagrams, diffs) to communicate changes clearly to reviewers.

Detected Capabilities

read verification outputsread project documentationread ADR filesread git diffsread spec filesread CONTEXT.md glossarygenerate markdown text

Trigger Keywords

Phrases that agents use to match this skill to user intent.

draft pr bodypr template assemblychange summary visualevidence from verifyreversibility assessment

Referenced Domains

External domains referenced in skill content, detected by static analysis.

github.com

Use Cases

  • Drafting PR body text for code review submissions
  • Summarizing code changes with supporting evidence and visuals
  • Documenting rollback procedures and blast radius for changes
  • Creating reversibility assessments for architectural decisions
  • Assembling verification outputs into reviewer-friendly format

Quality Notes

  • Skill defines a clear, structured template with well-motivated sections (Summary, Evidence, Reversibility)
  • Provides concrete guidance on matching visuals to change types (logic → pseudocode, UI → component tree, etc.)
  • Explicitly forbids re-collecting evidence and hallucinating claims—constrains agent to consume only existing paper trail
  • References external context (CONTEXT.md glossary, verify protocol, ADR test) without providing copies or inline definitions—depends on project state
  • Language and tone are mature and domain-specific (ADR, blast radius, rollback), but glossary terms are not defined in the skill itself
  • No explicit error handling guidance—unclear what agent should do if verify output is missing, ADR not found, or CONTEXT.md has no glossary
  • Output section lists 'paper-trail pointers' as deliverable but doesn't specify format (inline links, footnotes, structured list)
  • Trigger section mentions 'launch Phase 5' and 'qa-tester'—appears to assume specific platform or workflow context not documented
Model: claude-haiku-4-5-20251001Analyzed: Oct 2, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use Yeachan-Heo/pr in your dev environment

Command Palette

Search for a command to run...