application-performance-performance-optimization
Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning. Use when coordinating performance optimization across the stack.
65
51%
Does it follow best practices?
Impact
89%
1.71xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/application-performance-performance-optimization/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has good structural completeness with both a 'what' and 'when' clause, but lacks specificity in the concrete actions it covers and the trigger terms it provides. The broad category terms like 'profiling' and 'observability' don't give enough detail to confidently distinguish this skill from more focused performance-related skills or to match diverse user phrasings.
Suggestions
Add specific concrete actions such as 'analyze flame graphs, set up distributed tracing, optimize database queries, reduce bundle size, configure caching strategies' to improve specificity.
Expand trigger terms in the 'Use when' clause with natural user language like 'slow response times, high latency, memory leaks, CPU bottlenecks, page load speed, throughput issues.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (performance optimization) and mentions some areas like 'profiling, observability, and backend/frontend tuning,' but these are broad categories rather than concrete specific actions like 'run flame graphs,' 'set up distributed tracing,' or 'optimize database queries.' | 2 / 3 |
Completeness | Explicitly answers both 'what' (optimize end-to-end application performance with profiling, observability, and backend/frontend tuning) and 'when' (Use when coordinating performance optimization across the stack), with a clear 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'performance optimization,' 'profiling,' and 'observability,' but misses many natural user terms such as 'slow,' 'latency,' 'load time,' 'bottleneck,' 'memory leak,' 'CPU usage,' 'caching,' 'response time,' or 'APM.' | 2 / 3 |
Distinctiveness Conflict Risk | The 'across the stack' framing provides some distinction, but terms like 'performance optimization,' 'backend tuning,' and 'frontend tuning' could easily overlap with more specific backend-only or frontend-only performance skills, or general code optimization skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an ambitious orchestration workflow covering full-stack performance optimization, but it suffers from significant verbosity—explaining concepts Claude already understands and including lengthy prompt templates that inflate token cost without adding proportional value. The workflow structure is reasonable but lacks explicit validation gates between phases and concrete executable examples. The content would benefit greatly from condensing the subagent prompts, removing explanatory padding, and adding actual code/command examples.
Suggestions
Remove the extended thinking block and trim subagent prompt templates to essential parameters only—Claude knows what flame graphs, Core Web Vitals, and connection pooling are without explanation.
Add explicit validation checkpoints between phases (e.g., 'Verify baseline metrics are captured before proceeding to Phase 2') to create proper feedback loops for this multi-step destructive workflow.
Include at least one concrete, executable example—such as a k6 load test script snippet or a sample Grafana dashboard JSON—instead of relying entirely on delegated subagent prompts.
Extract detailed per-phase guidance into separate referenced files (e.g., DATABASE_OPTIMIZATION.md, FRONTEND_OPTIMIZATION.md) and keep SKILL.md as a concise orchestration overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~150+ lines with extensive explanations Claude already knows (what Core Web Vitals are, what APM tools do, how caching works). The extended thinking block adds unnecessary meta-commentary. Each step includes lengthy prompt templates that over-explain standard performance engineering concepts. | 1 / 3 |
Actionability | The skill provides structured steps with specific tool references and prompt templates, but nothing is truly executable—it's all delegated to subagents via prompt strings with placeholder variables like {context_from_phase_1} and $ARGUMENTS. No actual code, commands, or concrete examples of profiling output or optimization patterns are provided. | 2 / 3 |
Workflow Clarity | The 5-phase structure with 13 numbered steps provides clear sequencing, and the safety section mentions rollback plans. However, there are no explicit validation checkpoints between phases—no 'verify before proceeding' gates. Load testing production is flagged as risky but the workflow lacks concrete feedback loops for error recovery within phases. | 2 / 3 |
Progressive Disclosure | The content is organized into phases with clear headers, which is good structure. However, it's a monolithic wall of text with no references to external files for detailed guidance on specific areas (database optimization, frontend optimization, etc.). The massive prompt templates for each step should be externalized or condensed. | 2 / 3 |
Total | 7 / 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
- sickn33/antigravity-awesome-skills
- Commit
d739c8b
- 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.