Merge Agent Skill
Wait for a Remotion pull request to become mergeable, handle merge conflicts, distinguish genuine CI failures from flakes, rerun flaky checks through the flake skill, and merge the PR. Use when asked to run /merge, merge a current PR after checks pass, or shepherd a Remotion PR through CI to merge.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/remotion-dev/remotion --skill mergeThe instruction itself
3 sections, as written by the author/merge
Use this skill for an existing pull request in the Remotion monorepo.
Loop
Start from the top after every pushed fix, conflict resolution, CI rerun, or other state change:
- Identify the PR:
gh pr view --json number,url,state,isDraft,baseRefName,headRefName,mergeable,mergeStateStatus,reviewDecision,statusCheckRollup
- If the PR is draft, closed, blocked by requested changes, missing required approval, or otherwise not eligible to merge for a non-CI reason, stop and report the blocker.
- If GitHub reports merge conflicts, resolve them using the
pr-readyworkflow. Commit and push the resolution when needed, then start this loop from the top.
- Wait for checks:
gh pr checks --watch --interval 30
- If all required checks pass and the PR is mergeable, merge it:
gh pr merge --squash --delete-branch
If the repository or PR clearly requires another merge method, use that method instead.
CI Failures
When checks fail, inspect the failed jobs and logs before deciding what to do:
gh pr checks --watch=false
gh run view <run-id> --json databaseId,status,conclusion,url,jobs
gh run view <run-id> --log-failed
If it is a genuine CI failure:
- Fix the underlying issue locally, using the
pr-readyworkflow when helpful. - Run the targeted local checks, plus broader checks when the change has broad impact.
- Commit and push the fix.
- Start the loop from the top.
If it is a CI flake:
- Use the
flakeskill in this monorepo. - Rerun the failed flaky job or failed jobs as directed by that skill.
- Start the loop from the top.
Other skills for the same job
different authors, same section of the catalogue
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
How to use it
Take remotion-dev/merge from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
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.