simplify-code

Reviews recent code changes with four parallel reviewers and applies safe cleanup fixes.

Updated Aug 22, 2026
One-click install
npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill simplify-code-vivekgoquest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: simplify-code
Source: https://github.com/vivekgoquest/hermes-agent-stable/tree/main/skills/software-development/simplify-code
Command: npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill simplify-code-vivekgoquest

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Recent code changes often accumulate duplication, needless complexity, wasted work, and shallow band-aid fixes that a single broad review misses. This Skill runs four narrowly focused reviewers in parallel over your diff, aggregates their findings, and applies the fixes worth applying. ## Core Features & Use Cases - Parallel 4-Agent Review: Fans out reuse, quality, efficiency, and altitude reviewers concurrently via delegate_task batch mode, so you pay the latency of one review instead of four. - Risk-Tiered Application: Auto-applies SAFE fixes (unused imports, dead code), verifies CAREFUL refactors with tests, and flags RISKY changes (API renames, N+1 restructuring) for human decision. - Flexible Scoping: Supports focus modifiers (reuse, quality, efficiency, altitude), dry-run report-only mode, and diff scoping to staged changes, last commit, branch, or specific files. - Use Case: After finishing a feature branch, say "simplify my changes" to get duplication flagged against existing utilities, nested conditionals flattened, and band-aid fixes escalated — with tests re-run after every applied fix. ## Quick Start Ask the agent to simplify my recent uncommitted changes and apply only the safe fixes.

Frequently Asked Questions about simplify-code

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

FAQPage Schema
How do I clean up my recent code changes automatically?▼

Run the simplify command on your git diff to launch four parallel reviewers covering reuse, quality, efficiency, and altitude. Findings are merged, deduplicated, and applied in risk-tier order with tests run after each change.

How to review a git diff with multiple AI agents in parallel?▼

Pass all four reviewer tasks in one delegate_task batch call so they run concurrently, each receiving the complete diff plus the repo path. If delegation is unavailable, the same four review angles run sequentially inline.

Can I run a code cleanup review without changing any files?▼

Yes, request a dry run with phrases like "simplify but don't change anything" or "just report". The four reviewers still run and present findings across all risk tiers, but nothing is applied until you approve.

Does this skill find correctness bugs in my code?▼

No, it is a cleanup pass for code that already works, not a bug hunt. Genuine correctness bugs surfaced during review are reported separately, and pre-commit bug hunting belongs to a dedicated code review pass.

What happens when reviewers suggest conflicting fixes?▼

Conflicts resolve in a fixed order: correctness first, then the user's stated focus, then readability and reuse, then micro-performance. Mutually exclusive defensible options default to the one touching less code.

When should I not use parallel diff cleanup?▼

Avoid it for very large diffs over roughly 2000 lines without scoping down first, since four subagents each carrying the full diff is token-heavy. Also skip it when you need correctness or security review rather than quality cleanup.