performance-optimizer

Performance analysis, profiling techniques, bottleneck identification, and optimization strategies for code and systems. Use when the user needs to improve performance, reduce resource usage, or identify and fix performance bottlenecks.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A comprehensive, highly actionable performance reference with strong code examples and a clear measure-optimize-verify workflow. Its main weaknesses are verbosity from restating concepts Claude already knows and a monolithic single-file structure that should use progressive disclosure for the reference material.

Suggestions

Trim or remove sections that restate knowledge Claude already has (e.g., the O(n²)-vs-O(n), N+1-query, lru_cache, and generator-vs-list examples) and keep only the non-obvious guidance.

Split the encyclopedic reference material (Profiling Tools, Optimization Techniques, Database/Web sections) into separate reference files under references/ and have SKILL.md link to them one level deep.

Add an explicit feedback loop to the workflow — e.g., in 'Verify Improvements', state 'if a regression appears, revert the change and re-profile the hot path'.

Dimension	Reasoning	Score
Conciseness	Quotes basic restatements like 'O(n²) when O(n) exists', 'N+1 queries', '@lru_cache', and generators-vs-lists — concepts Claude already knows — across a ~370-line encyclopedic reference; not 2 because the body is lean bullets-and-code rather than padded prose, and not 4 because several sections restate well-known material that could be trimmed.	3 / 5
Actionability	Quotes fully executable commands and code such as 'python -m cProfile -o output.prof script.py', 'hyperfine command1 command2', and '@lru_cache(maxsize=128)' — copy-paste ready examples covering the common cases across Python, JS, shell, and system-level profiling.	5 / 5
Workflow Clarity	Quotes a clear sequenced process — '1. Measure First', '2. Find the Bottleneck', '3. Optimize Strategically', '4. Verify Improvements' — with the verify step acting as a checkpoint; not 5 because explicit error-recovery feedback loops ('if regression, revert and re-profile') are implied rather than stated.	4 / 5
Progressive Disclosure	Quotes well-organized section headers ('## Profiling Tools', '## Optimization Techniques', '## Database Optimization') but no bundle files exist and all reference material is inlined in one ~370-line file; not 2 because section structure is clear, and not 4 because substantial reference content that belongs in separate files is not split out or signaled.	3 / 5
	Total	15 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-constructed description that names concrete capabilities and pairs them with explicit, natural-language trigger guidance. The only minor gap is coverage of common synonyms like 'speed up' or 'latency'.

Dimension	Reasoning	Score
Specificity	Quotes 'Performance analysis, profiling techniques, bottleneck identification, and optimization strategies' — four distinct, concrete capability areas with comprehensive coverage of the performance domain; not below 5 because coverage is broad and specific rather than minimal, and not the abstract single-domain naming of a 4.	5 / 5
Completeness	Explicitly answers both 'what' ('Performance analysis, profiling techniques, bottleneck identification, and optimization strategies') and 'when' ('Use when the user needs to improve performance, reduce resource usage, or identify and fix performance bottlenecks') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Quotes 'improve performance, reduce resource usage, or identify and fix performance bottlenecks' — good natural keyword coverage a user would say, but missing common synonyms like 'speed up', 'faster', 'slow', or 'latency' that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Has a clear performance niche with distinctive triggers ('profiling', 'bottleneck', 'reduce resource usage') and minimal conflict risk; not 4 because the triggers are specific enough to avoid overlap with general coding skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: einverne/dotfiles
Path: claude/skills/performance-optimizer/SKILL.md
Commit: 7d18cf4

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.