Performance Optimization Playbook
Diagnose and optimize code performance by choosing the right Claude workflow (quick function-level analysis vs. project-wide Claude Code changes) and applying a repeatable performance triage loop.
Install
$ agentstack add skill-uygnoey-skills-from-claude-blog-performance-optimization-playbook ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Instructions
You are helping a developer improve code performance.
- Clarify the symptom
- What is slow (endpoint, job, UI screen, query)?
- What changed recently (deploy, config, dependency update, data volume)?
- What is the target (p95 latency, throughput, memory)?
- Choose the workflow
- Use the chat workflow when the problem is contained to a small snippet (roughly tens of lines) and you want fast complexity analysis and a rewrite proposal.
- Use Claude Code when the issue spans multiple files, requires coordinated refactors, or you want changes applied and tests run.
- Function-level analysis (chat workflow)
- Identify algorithmic complexity (e.g., nested loops, repeated scans).
- Look for I/O inside loops (database/network calls).
- Propose an improved approach (hash map lookup, batching, caching, reduced allocations).
- Provide an optimized version that preserves behavior.
- Project-wide optimization (Claude Code workflow)
- Start in the most performance-critical directories (e.g.,
api/,core/). - Ask for a hypothesis about the regression and where to measure.
- Apply the smallest safe change first.
- Re-run benchmarks/tests after each change.
- Document the result
- What bottleneck was found?
- What change fixed it?
- What measurement proves improvement?
Bundled references:
- templates/performance-triage-questions.md
- examples/dashboard-function-optimization.md
Examples
Example 1: Ask for function-level optimization
Use the prompt in examples/dashboard-function-optimization.md.
Example 2: Ask Claude Code to optimize a performance-critical area
In Claude Code, run a request like:
- Optimize this payment processing function and benchmark results
(If you need a fuller prompt structure, use templates/performance-triage-questions.md.)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: uygnoey
- Source: uygnoey/skills-from-claude-blog
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.