mcpbeat Sign in

Azsdk Common Patch Mergeback Agent Skill

Prepare a merge-back PR that brings patch-release version, CHANGELOG, and pom.xml updates from a `release/patch/YYYYMMDD` branch back into `main`. **WORKFLOW SKILL**. USE FOR: "merge-back PR", "merge back patches", "patch release merge-back", "bring patch releases into main", "reconcile release/patch branch with main". DO NOT USE FOR: triggering SDK releases, incrementing versions for a new patch, general SDK code generation. INVOKES: eng/versioning/update_versions.py.

3k tokens
context cost
the whole folder, loaded on every use
3
files
instructions only
0
copies elsewhere
how many repositories repackaged it
2566
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/Azure/azure-sdk-for-java --skill azsdk-common-patch-mergeback

What comes with it

6 031 bytes besides the instruction
references/changelog-resolution.md
references/version-client-resolution.md

The instruction itself

7 sections, as written by the author

Patch Release Merge-back

Prepare a PR that merges the version, CHANGELOG, and downstream pom.xml

updates produced by a patch release (on a release/patch/YYYYMMDD branch) back

into main. Patches revert CHANGELOG.md and version files to the last stable

release, so a naive merge creates many conflicts. This skill encodes how to

resolve each file type correctly.

Triggers

WHEN: "merge-back PR", "merge back patches", "patch release merge-back", "bring patch releases into main", "reconcile the patch branch"

DO NOT USE FOR: triggering an SDK release, incrementing versions for a new patch cycle, code generation.

Inputs (variables)

Two values drive the whole workflow. Both come from the **"Increment versions

for patch releases"** PR (opened by azure-sdk-automation[bot]) that targets the

patch branch:

| Variable | How to determine it | Current value |

| ---------------- | ------------------------------------------------------------------------------- | ----------------------- |

| RELEASE_BRANCH | The branch the "Increment versions" PR targets: release/patch/YYYYMMDD. | release/patch/20260701 |

| PATCH_DATE | Derived from the branch name YYYYMMDDYYYY-MM-DD. Used in CHANGELOG entries. | 2026-07-01 |

If either value is ambiguous, ask the user to confirm before proceeding.

Critical Rules (read first)

  • Only the last two commits of RELEASE_BRANCH carry the updates to bring

back. Diff against RELEASE_BRANCH~2 to scope the change set.

  • Never edit pom.xml by hand. It is regenerated by

eng/versioning/update_versions.py after version_client.txt is correct.

  • Do not touch README.md files. Run the version script with --skip-readme

so READMEs are left unchanged (README updates are handled separately).

  • version_client.txt: update only the dependency-version of SDK

libraries that changed on the release branch; **always keep the

current-version from main.** Never reset beta versions to beta.1.

  • CHANGELOG.md: keep the PATCH_DATE entry from the release branch; every

other line must match main. Do not invent or edit any other CHANGELOG

content.

  • Base the merge-back branch on main, not on the release branch.

Workflow

  • Confirm inputs — Establish RELEASE_BRANCH and PATCH_DATE (see table

above). Fetch the branch: git fetch origin RELEASE_BRANCH.

  • Create the working branch from main:

git checkout main && git pull then

git checkout -b copilot/merge-back-release-patch-YYYYMMDD.

  • Scope the changes — List files touched by the last two commits:

git diff --name-only origin/RELEASE_BRANCH~2 origin/RELEASE_BRANCH.

Expect three kinds: eng/versioning/version_client.txt, many CHANGELOG.md,

and many pom.xml (+ possibly README.md).

  • Reconcile version_client.txt — Follow

references/version-client-resolution.md.

  • Reconcile each CHANGELOG.md — Follow

references/changelog-resolution.md.

  • Regenerate pom.xml — From the repo root run the version script with the

--skip-readme (--sr) flag so README.md files are left untouched:

   python eng/versioning/update_versions.py --skip-readme

Do not stage any manual pom.xml edits; only the generated output. Confirm no

README.md files appear in the resulting diff.

  • Review & sanity-check — Verify no v2 (*-v2) or unrelated libraries were

touched, no current-version values were altered, and no beta version was

reset to beta.1.

  • Commit and open the PR against main — Title it like

<Month> <Year> Patches Merge-back. Summarize: bumped dependency versions,

inserted PATCH_DATE CHANGELOG entries, and auto-generated pom.xml updates

(READMEs intentionally left unchanged via --skip-readme).

Examples

  • "Prepare the merge-back PR for release/patch/20260701 into main."
  • "Bring the July 2026 patch releases back into main."

Troubleshooting

  • current-version mismatch after regeneration (e.g. 2.59.0-beta.1 vs

2.59.0-beta.2): you likely overwrote a current-version. Restore it from

main; only dependency-version should change.

  • Unexpected pom.xml diffs: re-run update_versions.py only after

version_client.txt is fully correct; stray diffs usually mean the version

file still has a wrong entry.

  • Accidental v2 library changes: revert them — patch merge-backs only cover

the patched GA/beta libraries listed in the release branch diff.

  • Wrong CHANGELOG "from" versions in ## X.Y.Z (PATCH_DATE) dependency

bullets: correct them to match the actual previous release, per the release

branch entry.

Other skills for the same job

different authors, same section of the catalogue
MCP Builder
by anthropics
vendor ×13

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

30k tokens scripts
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
MCP Builder
by JayZeeDesign
×7

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

37k tokens scripts
Vercel React Native Skills
by vercel-labs
vendor ×6

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

39k tokens
Vercel React Best Practices
by ratacat
×5

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

34k tokens
Next Best Practices
by vercel-labs
vendor ×4

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

20k tokens
Using Git Worktrees
by ZhanlinCui
×4

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

1k tokens

How to use it

Copy the folder

Take azure/azsdk-common-patch-mergeback from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.