providing-performance-optimization-advice
Provide comprehensive prioritized performance optimization recommendations for frontend, backend, and infrastructure. Use when analyzing bottlenecks or seeking improvement strategies. Trigger with phrases like "optimize performance", "improve speed", or "performance recommendations".
40
41%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/performance/performance-optimization-advisor/skills/providing-performance-optimization-advice/SKILL.mdQuality
Discovery
82%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 is well-structured with explicit 'Use when' and trigger phrases, making it strong on completeness and trigger term quality. However, the actual capabilities described are somewhat vague — 'recommendations' is abstract — and the broad scope across frontend, backend, and infrastructure creates moderate conflict risk with more specialized optimization skills.
Suggestions
Add specific concrete actions beyond 'recommendations', e.g., 'Identifies slow queries, reduces bundle sizes, recommends caching strategies, and suggests infrastructure scaling approaches'.
Narrow the scope or add more distinctive trigger terms to reduce overlap with domain-specific optimization skills, e.g., 'full-stack performance audit' or 'cross-layer optimization'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (performance optimization) and mentions frontend, backend, and infrastructure, but the actions are vague — 'recommendations' and 'analyzing bottlenecks' are abstract rather than concrete specific actions like 'profile database queries, reduce bundle size, configure CDN caching'. | 2 / 3 |
Completeness | Clearly answers both what ('provide comprehensive prioritized performance optimization recommendations for frontend, backend, and infrastructure') and when ('Use when analyzing bottlenecks or seeking improvement strategies. Trigger with phrases like...') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would say: 'optimize performance', 'improve speed', 'performance recommendations'. Also includes relevant domain terms like 'bottlenecks', 'frontend', 'backend', and 'infrastructure' that users might mention. | 3 / 3 |
Distinctiveness Conflict Risk | While 'performance optimization' is a recognizable niche, the broad scope covering frontend, backend, and infrastructure could overlap with more specific skills targeting any one of those areas. Terms like 'improve speed' could also conflict with database-specific or network-specific optimization skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is almost entirely descriptive rather than instructive — it explains what a performance optimization advisor would do without providing any concrete, actionable guidance on how to actually do it. It lacks specific code examples, concrete optimization patterns, tool commands, or measurable criteria. The content is heavily padded with sections that explain obvious concepts to Claude while omitting the technical substance that would make the skill useful.
Suggestions
Replace the abstract 'Instructions' list with concrete checklists per layer — e.g., specific frontend checks (bundle size thresholds, image format recommendations, render-blocking resource patterns) with actual code snippets or commands
Add executable examples: show a sample optimization report output format, include specific code patterns to look for (e.g., N+1 queries, missing indexes, uncompressed assets) with before/after code
Remove the 'Overview', 'How It Works', 'When to Use This Skill', 'Best Practices', 'Integration', and 'Resources' sections entirely — they explain concepts Claude already knows and consume tokens without adding actionable value
Add validation checkpoints to the workflow, such as 'measure baseline metrics before recommending changes' and 'verify each recommendation against actual profiling data rather than assumptions'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive sections explaining things Claude already knows (what performance optimization is, when to use it, how it works at a high level). The 'Overview', 'How It Works', 'When to Use This Skill', 'Best Practices', 'Integration', and 'Resources' sections are all padding that add no actionable value. The content could be reduced by 70%+ without losing useful information. | 1 / 3 |
Actionability | No concrete code examples, no specific commands, no executable guidance. The 'Instructions' section is a vague 6-step list ('Analyze frontend code for rendering and asset optimization') with no specifics about what to look for, what tools to use, or what patterns to apply. The examples describe what the skill 'will do' rather than showing actual output or concrete techniques. | 1 / 3 |
Workflow Clarity | The workflow steps are abstract and lack any validation checkpoints. Steps like 'Analyze frontend code for rendering and asset optimization' and 'Review backend code for query and processing efficiency' provide no concrete sequence, no specific checks, and no feedback loops. There's no guidance on what constitutes a complete analysis or how to verify recommendations. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files and no references to external resources. All content is inline but paradoxically lacks depth — it's both too long (verbose framing) and too shallow (no actual technical detail). No structured navigation to deeper content. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
69c73e9
- 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.