performance-expert
Performance optimization - profiling, benchmarking, optimization
55
Quality
42%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/performance-expert/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too terse and lacks the explicit trigger guidance needed for Claude to reliably select it. While it identifies the domain, it reads more like a category label than a functional description. The absence of a 'Use when...' clause and specific concrete actions significantly limits its utility for skill selection.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'slow', 'speed up', 'bottleneck', 'latency', 'memory usage', or 'performance issues'
Expand the capabilities with specific concrete actions such as 'identify bottlenecks', 'analyze memory usage', 'measure execution time', 'optimize database queries'
Specify the context or technology scope (e.g., 'Python code', 'web applications', 'API endpoints') to reduce conflict risk with other skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (performance optimization) and lists some actions (profiling, benchmarking, optimization), but these are high-level categories rather than concrete specific actions like 'identify memory leaks' or 'reduce CPU usage'. | 2 / 3 |
Completeness | Only addresses 'what' at a high level with no 'Use when...' clause or explicit trigger guidance. Missing any indication of when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes relevant technical terms (profiling, benchmarking, optimization) that users might say, but misses common variations like 'slow code', 'speed up', 'performance issues', 'bottleneck', or 'latency'. | 2 / 3 |
Distinctiveness Conflict Risk | Performance optimization is a recognizable niche, but the generic terms could overlap with debugging skills or general code review skills. Lacks specificity about what type of performance (web, database, algorithm, etc.). | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides excellent executable code examples across multiple performance optimization domains, making it highly actionable. However, it lacks workflow guidance on how to approach performance optimization systematically—there's no sequence for profiling, identifying bottlenecks, applying fixes, and validating improvements. The content reads more like a reference collection than an optimization guide.
Suggestions
Add a workflow section that sequences the optimization process: 1) Profile/measure baseline, 2) Identify bottlenecks, 3) Apply targeted optimization, 4) Validate improvement with metrics
Include validation steps showing how to interpret profiling output and confirm optimizations succeeded (e.g., 'If cumulative time > X, investigate function Y')
Remove the persona introduction and closing quote to improve conciseness
Consider splitting into separate files (PROFILING.md, DATABASE.md, FRONTEND.md) with SKILL.md as a quick-reference overview pointing to detailed guides
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good code examples, but includes some unnecessary elements like the persona framing ('You are Performance Expert'), the closing quote, and the optimization areas list that Claude already understands. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples across multiple languages and domains (Node.js profiling, Python profiling, SQL queries, TypeScript caching, React code splitting). Examples are concrete and complete. | 3 / 3 |
Workflow Clarity | No clear workflow or sequence for performance optimization tasks. Examples are isolated snippets without guidance on when to use each, how to interpret results, or validation steps to confirm optimizations worked. Missing feedback loops for measuring improvement. | 1 / 3 |
Progressive Disclosure | Content is organized into logical sections with headers, but it's a monolithic file with no references to external documentation. The breadth of topics (profiling, DB, frontend, caching, metrics) could benefit from splitting into separate focused files. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- TurnaboutHero/oh-my-antigravity
- Commit
fab464f
- Reviewed
Table of Contents
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.