SkillRepo
Sign InSign Up
Catalog
Yeachan-Heo/stacked-delivery

Yeachan-Heo

stacked-delivery

Deliver a queue of changes as one linear stacked PR chain — each PR lands on the last, verdicts record patch-ids, rebases trigger re-verification, and landing goes bottom-up only. For 'stack them, I'll land them' or review-gated queues.

v1.0LATEST
NewUpdated Nov 8, 2026

Stacked Delivery

Some queues cannot merge independently — each change depends on the last — so they ship as one stacked chain: PR 2 branches on PR 1, PR 3 on PR 2. The chain makes review sequential and landing strictly bottom-up; this skill keeps that honest.

When to use

  • changes depend on each other and the user chose stacking over independent PRs
  • review gating means only the bottom PR can actually merge at a time

When not to use

  • changes are independent — parallel PRs merge faster and fail smaller
  • the user wants everything in one PR — that is execute with a bigger brief

Workflow

  1. Cut the stack: one branch and PR per change, each branched on the last; the brief for each PR comes from sharpen/architect as usual. Every PR description links its parent and child.
  2. Build and verify each layer with its own checks — a red middle PR blocks the whole chain, so fix forward before adding layers on top.
  3. Record patch-ids: verification verdicts (from verify) record the head SHA they were earned on, in .omc/state/verification-ledger.tsv — the ledger's sha field. A verdict applies only to that exact patch. Review verdicts (interrogate pass/revise/block) are tracked in the PR's review thread, not the verification ledger — the ledger's vocabulary is verification evidence, and review outcomes have their own lane.
  4. On rebase: any PR whose base moved has its verdicts invalidated for the affected layers — re-run the checks and record fresh verdicts before the chain is "green" again. A stale green is the stack's most dangerous lie.
  5. Land bottom-up only: the human merges PR 1; the stack rebases onto the new trunk; re-verify; PR 2 becomes the new bottom. This skill never merges — landing authority stays with the human (babysit rules apply).
  6. Report: the chain shape (PR list with parent links), each layer's verdict and patch-id, and which layers are re-verified against the current trunk.

Rules

  • Never merge, rebase, or force-push shared branches on your own; rebase of own-branch layers uses --force-with-lease and says so.
  • Never present a layer as green whose base moved after its verdict was earned — the ledger's patch-id is the truth.
  • A failing layer stops the chain at that layer; layers above are blocked-and-waiting, not green.
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

62/100

Grade

C

Adequate

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

Safety

78

Quality

55

Clarity

70

Completeness

48

Summary

This skill guides an agent through managing a queue of dependent changes as a linear stacked PR chain, where each PR lands on the previous one. It provides workflow guidance for cutting stacks, recording verification verdicts against patch SHAs, managing rebases and re-verification, and ensuring landing occurs strictly bottom-up. The skill defines clear rules around merge authority, patch-id tracking, and state management without performing destructive operations itself.

Detected Capabilities

git branch and rebase operationsPR metadata reading and linkingverification ledger reading and writing (.omc/state/verification-ledger.tsv)SHA-based state trackingchain status reporting

Trigger Keywords

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

stacked pull requestsdependent changes landingstack rebase verificationpatch verification trackingbottom-up pr merge

Risk Signals

INFO

Rebase operations with --force-with-lease for own branches

Workflow step 5 and Rules section
INFO

Interaction with verification ledger file at .omc/state/verification-ledger.tsv

Workflow steps 3-4
INFO

No direct merge authority — landing stays with human

Workflow step 5 and Rules section

Referenced Domains

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

github.com

Use Cases

  • Manage a series of dependent PRs where each change builds on the previous one
  • Track verification verdicts against specific patch SHAs to detect stale or invalidated checks
  • Coordinate team review and landing of stacked changes in strict bottom-up order
  • Re-verify layers after rebases to ensure all checks remain valid against the current trunk
  • Report chain health and status including parent-child relationships and verification state

Quality Notes

  • Strengths: Clear workflow with numbered steps, explicit rules about what the skill does and does NOT do (never merges), well-defined concepts (patch-id tracking, verification ledger, bottom-up landing)
  • Strengths: 'When to use' and 'When not to use' sections provide important context for when stacking is appropriate vs. alternatives
  • Strengths: Safety guardrails documented (no shared branch manipulation without human authority, patch-id validation, re-verification on rebase)
  • Limitation: SKILL.md is entirely architectural/conceptual with no concrete command examples, API calls, or implementation details for the agent to follow
  • Limitation: Verification ledger format (TSV structure, fields) is mentioned but not documented—the skill references 'sha field' and 'verification evidence' but does not provide the schema
  • Limitation: No error handling patterns documented—what does the agent do if a layer fails verification? If rebase conflicts occur? If patch-ids are missing?
  • Limitation: No examples of PR descriptions or how parent/child links should be formatted in the description
  • Limitation: Interaction points with other skills ('sharpen', 'architect', 'verify', 'interrogate', 'babysit') are named but not explained—assumes prior knowledge of those skills
Model: claude-haiku-4-5-20251001Analyzed: Nov 8, 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/stacked-delivery in your dev environment

Start a Developer trial

Command Palette

Search for a command to run...