cleanup-scope-outs

Batch GitHub issues by code path into a single cleanup PR.

12|2|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/jikig-ai/soleur --skill cleanup-scope-outs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cleanup-scope-outs
Source: https://github.com/jikig-ai/soleur/tree/main/plugins/soleur/skills/cleanup-scope-outs
Command: npx skills add https://github.com/jikig-ai/soleur --skill cleanup-scope-outs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gh, jq, awk, grep, and includes scripts (resource) components.

What problem does it solve?

Drain labeled backlog by batching issues that touch the same code area into a single focused refactor PR so operators can close multiple related tickets with one high-value change. This reduces PR noise, coordinates fixes that span the same top-level directory, and prevents many low-value single-issue PRs.

Core Features & Use Cases

  • Groups open GitHub issues by top two path segments (code area) by parsing file paths from issue bodies and ranking qualified references deeper-first.
  • Validates label and milestone existence, enforces a minimum cluster size, supports interactive and headless pipeline modes, and builds a one-shot scope argument delegated to soleur:one-shot.
  • Use cases: drain a deferred-scope-out backlog, close accumulated code-review findings, and create one cleanup PR that closes 3+ related issues.

Quick Start

Run the cleanup-scope-outs skill with a label and milestone to select a cluster and delegate the assembled scope to soleur:one-shot.

Frequently Asked Questions about cleanup-scope-outs

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I batch multiple related GitHub issues into a single cleanup PR?▼

Group related GitHub issues into one cleanup PR by parsing file path references from issue bodies, clustering them by top two path segments, and delegating the assembled scope to a one-shot refactor workflow.

What is the best way to drain a labeled GitHub backlog by code area?▼

Drain a labeled GitHub backlog by validating label and milestone existence, selecting qualified issue clusters by size and path depth, then batching matching code paths into one focused refactor PR.

Do I need gh CLI and jq installed to batch close GitHub issues?▼

Yes, the gh CLI and jq must be available on your PATH to parse issue data, validate labels and milestones, and build the one-shot scope argument for the cleanup PR.

How does grouping GitHub issues by file path references work for refactoring?▼

Grouping GitHub issues by file path references works by parsing issue bodies for file paths, ranking references deeper-first, and clustering them by the top two path segments to enforce a minimum cluster size for batching.

Can I automate closing accumulated code-review findings in a headless pipeline?▼

Yes, you can automate closing accumulated code-review findings using headless pipeline mode to select a cluster, build a one-shot scope argument, and delegate to the refactor workflow without interactive prompts.

What limitations exist when batching GitHub issues by top-level directory?▼

Batching GitHub issues by top-level directory requires issues to contain file path references, enforces a minimum cluster size, and only supports repositories using deferred-scope-out or code-review labels with valid milestones.