code-optimizer
Skill2 starsChanged 7 months agoApache-2.0View on GitHub
Deep code optimization and bug hunting. Use when the user asks to optimize performance, find bugs, analyze edge cases, detect memory leaks, or review code quality. Runs a three-subagent pipeline: analyzer -> planner -> executor with explicit user confirmation before changes.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- hongphuc5497/skillstheir own version, first seen Nov 1, 2026
- shubhamaniket/Code-Optimizertheir own version, first seen Apr 16, 2026
- santosomar/general-secure-coding-agent-skillstheir own version, first seen Mar 10, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- hongphuc5497/skills★ 2same name
- santosomar/general-secure-coding-agent-skills★ 1same name
- shubhamaniket/Code-Optimizer★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- doc-coauthoringSkill
- docxSkill
- frontend-designSkill
- git-commit-pushSkill
- pdfSkill
- planningSkill
- pptxSkill
- project-startupSkill
- refactoringSkill
- skill-creatorSkill
- store-visualsSkill
- test-generatorSkill
- webapp-testingSkill
- xlsxSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
Run baseline tests if present
- Very specific: line 40
Use the analysis checklist and output format in references/analysis-checklist.md.
- Very specific: line 45
Use the plan template in references/plan-format.md.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Code optimizer (three subagents)
When to use
- Performance problems or slow code
- Suspected memory leaks or resource misuse
- Silent bugs or edge cases
- Deep code review before release
Goal
Identify and fix bugs, inefficiencies, and resource issues using a three-stage pipeline with required user confirmation before applying changes.
Pipeline overview
Parent Agent
-> Subagent 1: Analyzer (write /tmp/code-analysis.md)
-> Subagent 2: Planner (write /tmp/optimization-plan.md)
-> Pause for user approval
-> Subagent 3: Executor (apply fixes, write OPTIMIZATION_REPORT.md)Phase 1: Parent reconnaissance
- Determine scope (files, directory, or full codebase)
- Collect context (CLAUDE.md, package.json, requirements.txt, etc.)
- Run baseline tests if present
- Pass scope and context to Subagent 1
Phase 2: Subagent 1 (Analyzer)
Use the analysis checklist and output format in references/analysis-checklist.md.
Write /tmp/code-analysis.md.
Phase 3: Subagent 2 (Planner)
Use the plan template in references/plan-format.md.
Write /tmp/optimization-plan.md.
Phase 4: Pause and confirm
Present the plan summary and ask the user whether to apply all fixes, only critical/high, or a subset. Do not continue without explicit confirmation.
Phase 5: Subagent 3 (Executor)
Apply only approved fixes, run tests for high-risk changes, and write OPTIMIZATION_REPORT.md.
Notes
- Subagents 1 and 2 never modify files.
- The pause before execution is mandatory.
- This skill complements
refactoring(structure/readability) with correctness and performance focus.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.