merge-queue
Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
Best use case
merge-queue is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
Teams using merge-queue should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/merge-queue/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How merge-queue Compares
| Feature / Agent | merge-queue | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Merge Queue (Refinery) ## Overview The Refinery is Gas Town's per-rig merge queue processor. It collects completed work from agents, detects conflicts between branches, resolves them (auto where possible), merges in dependency order, and verifies the integration. ## When to Use - After convoy beads are complete and ready to merge - When multiple agents have worked on overlapping areas - When integration testing is needed before landing - When conflict resolution requires coordination ## Process 1. **Collect** pending changes from all agent branches 2. **Detect** conflicts between branches and target 3. **Resolve** conflicts (auto-resolve where possible) 4. **Merge** in dependency order with attribution 5. **Verify** integration (tests, lint, build) ## Conflict Strategies - **auto**: Attempt automatic resolution, escalate on failure - **manual**: Always require human review - **theirs**: Prefer incoming changes - **ours**: Prefer target branch changes ## Tool Use Invoke via babysitter process: `methodologies/gastown/gastown-merge-queue`
Related Skills
merger-model-builder
M&A merger model construction skill with accretion/dilution analysis and synergy modeling
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.
project-install
Install the Babysitter Codex workspace integration into the current project.
plan
Plan a Babysitter workflow without executing the run.
observe
Observe, inspect, or monitor a Babysitter run.
model
Inspect or change Babysitter model-routing policy by phase.