resolve_parallel_skill

Overview

This skill automates resolving all TODO comments across a codebase by analyzing, planning, and executing fixes using parallel subagents. It groups unresolved items, identifies dependencies, and runs per-item resolver tasks concurrently to maximize throughput. The workflow ends by committing and pushing changes to the repository.

How this skill works

The skill scans source files to collect all TODO comments and builds a Todo list grouped by type and dependency. It produces a simple flow plan that indicates which items can run in parallel and which require sequential ordering. For each unresolved item it spawns a pr-comment-resolver task in parallel, waits for results, applies changes, commits, and pushes the updates.

When to use it

• Large codebases with many independent TODO comments that can be resolved concurrently.
• When TODO items are mostly self-contained tasks (docs, small refactors, lint fixes).
• During maintenance sprints to clear backlog items quickly.
• Before a major release to reduce outstanding comments and improve code quality.
• When you want automated parallel agents to speed up PR comment resolution.

Best practices

• Scan and group TODOs by type and dependency before executing any changes.
• Prioritize dependency-critical items that other tasks rely on and run them first if necessary.
• Limit parallelism per repo to avoid conflicting edits on the same files.
• Use small, focused pr-comment-resolver tasks that modify minimal scope and include tests where possible.
• Review and approve aggregated commits from parallel tasks to catch integration issues.

Example use cases

• Resolve multiple isolated TODOs that add types or docstrings across many files in parallel.
• Automate simple refactors (rename, small API adjustments) that do not overlap file edits.
• Close lint or formatting TODOs across components simultaneously to meet codebase standards.
• Spawn parallel agents to answer reviewer comments in a PR that contains many independent notes.