agentsclimarketplace

Simplify

Skill yyykf/spellbook-skills/skills/simplify

Claude Code and Codex skills for daily engineering workflows: worktrees, merge requests, code review, YApi lookup, and Java DDD guidance.

Install
npx -y skills add yyykf/spellbook-skills --skill simplify

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Review all changed files for reuse, quality, and efficiency, then fix any issues found. Spawns three parallel review agents and aggregates findings into actionable fixes.

SKILL.md

3.2 KB, as published. Nobody here has run it

Simplify: Code Review and Cleanup

Overview

Review all changed files for reuse, quality, and efficiency. Fix any issues found.

Core principle: Identify changes -> Spawn three review agents in parallel -> Fix issues.

Announce at start: "I'm using the simplify skill to review changed code for reuse, quality, and efficiency."

Prerequisites

  • A git repository with uncommitted or recently committed changes.

Workflow

Phase 1: Identify Changes

Run git diff (or git diff HEAD if there are staged changes) to see what changed. If there are no git changes, review the most recently modified files that the user mentioned or that were edited earlier in this conversation.

Save the full diff output — it will be passed to each review agent.

Phase 2: Spawn Three Review Agents in Parallel

Launch all three agents concurrently in a single message. Pass each agent the full diff as context.

AgentRole
code-reuse-reviewerFinds duplicated logic and missed existing utilities
code-quality-reviewerFinds hacky patterns that hurt maintainability
code-efficiency-reviewerFinds performance and resource issues

For Codex, if the Spellbook reviewer agent roles are available, use the namespaced role names:

Codex Agent RoleRole
spellbook-code-reuse-reviewerFinds duplicated logic and missed existing utilities
spellbook-code-quality-reviewerFinds hacky patterns that hurt maintainability
spellbook-code-efficiency-reviewerFinds performance and resource issues

Invocation example (Claude Code):

Use the Agent tool three times in a single message, each with the corresponding subagent_type:

  • code-reuse-reviewer
  • code-quality-reviewer
  • code-efficiency-reviewer

Pass each agent a prompt like:

Review the following diff for [reuse/quality/efficiency] issues.

<full diff here>

Invocation example (Codex):

If the namespaced role names are available in the spawn_agent tool, launch all three agents concurrently with the corresponding agent_type:

  • spellbook-code-reuse-reviewer
  • spellbook-code-quality-reviewer
  • spellbook-code-efficiency-reviewer

Pass each agent the same full diff.

For platforms without named agent support: run the three reviews sequentially using each agent's checklist from their definitions.

Phase 3: Fix Issues

Wait for all three agents to complete. Aggregate their findings and fix each issue directly. If a finding is a false positive or not worth addressing, note it and move on — do not argue with the finding, just skip it.

Phase 4: Summary

Briefly summarize what was fixed (or confirm the code was already clean).

Notes

  • This is a cleanup pass, not a formal code review. After this skill, use a dedicated review skill or process when merge readiness needs to be judged.
  • Keep fixes small and local — preserve behavior exactly.
  • Run the narrowest practical verification for the touched area when possible.

Gives 0 of the 12 instructions most refactoring skills give

Counted across 521 of the 525 authors here whose files we hold, read 2026-08-06

  • run tests after each changein 59 of 521, across 56 files
  • write tests before refactoringin 27 of 521, across 24 files
  • preserve external behaviorin 26 of 521, across 22 files
  • remove dead codein 25 of 521, across 24 files
  • make small incremental changesin 20 of 521, across 17 files
  • break the implementation into tiny commitsin 18 of 521, across 5 files
  • ask the user about alternative optionsin 17 of 521, across 4 files
  • create a GitHub issue with the planin 17 of 521, across 4 files
  • explore the repository to verify assertionsin 17 of 521, across 4 files
  • interview the user about the refactorin 16 of 521, across 3 files
  • check the codebase for test coveragein 16 of 521, across 3 files
  • refactor one thing at a timein 16 of 521, across 12 files

Said here and by no other author read

  • announce skill usage at start
  • review recently modified files if no diff exists
  • save the full diff output
  • run three reviews sequentially if needed
  • wait for all agents to complete
  • fix each valid issue found

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.