mcpField
G
gentle-ai-chained-pr

gentle-ai-chained-pr

github.com/gentleman-programmingDevelopment8.1k51 installsUpdated today
Repository

About gentle-ai-chained-pr

A coding-agent skill for planning chained pull requests when a change exceeds the stated review-size threshold or the user requests review slices. It defines strategy gates, PR boundaries, dependency context, and verification steps.

Key features

  1. 01400-line PR threshold and decision gates
  2. 02Stacked and feature-chain strategies
  3. 03PR context and dependency diagrams
  4. 04Independent verification and clean-diff checks

Use cases

  1. 01Breaking a large change into reviewable PRs
  2. 02Planning dependencies across feature-chain PRs
  3. 03Checking PR boundaries and verification plans

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/gentleman-programming/gentle-ai --skill gentle-ai-chained-pr

After installing, type/gentle-ai-chained-prin Claude Code to confirm it loaded.

Bundled filesreferences/chaining-details.md

Details

From the project README

Activation Contract

Load this skill when a planned PR may exceed 400 changed lines, SDD forecasts 400-line budget risk: High or Chained PRs recommended: Yes, or the user asks for chained/stacked PRs, review slices, or reviewer-load control.

Hard Rules

  • Split PRs over 400 changed lines unless a maintainer explicitly accepts size:exception.
  • Keep each PR reviewable in about ≤60 minutes.
  • Use one deliverable work unit per PR; keep tests/docs with the unit they verify.
  • State start, end, prior dependencies, follow-up work, and out-of-scope items in every chained PR.
  • Every child PR must include a dependency diagram marking the current PR with 📍.
  • In Feature Branch Chain, create a draft/no-merge tracker PR; child PR #1 targets the tracker branch, later children target the immediate parent branch.
  • Treat polluted diffs as base bugs: retarget or rebase until only the current work unit appears.
  • Do not mix chain strategies after the user chooses one.

Decision Gates

ConditionAction
PR ≤400 changed lines and focusedKeep single PR.
PR >400, each slice can land independentlyUse Stacked PRs to main.
PR >400, feature must integrate before mainUse Feature Branch Chain with tracker.
Generated/vendor/migration diff cannot split cleanlyAsk maintainer for size:exception.
SDD provides delivery_strategyFollow it before apply/PR creation.

Execution Steps

  1. Estimate changed lines and identify independent work units.
  2. Ask for a chain strategy when none is cached and the budget is exceeded.
  3. Create branches/PRs using the chosen strategy only.
  4. Add Chain Context to each PR without replacing the repo PR template.
  5. Verify each PR independently: CI/tests/docs/manual checks, rollback scope, and clean diff.
  6. Keep tracker PR draft/no-merge until all child PRs are reviewed and integrated.

Output Contract

Return the chosen strategy, PR order, current PR boundary, dependency diagram, review budget (additions + deletions), verification plan, and any size:exception rationale.

References

Comments

Markdown supported