validating-performance-budgets
tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill validating-performance-budgetsValidate application performance against defined budgets to identify regressions early. Use when checking page load times, bundle sizes, or API response times against thresholds. Trigger with phrases like "validate performance budget", "check performance metrics", or "detect performance regression".
Validation
81%| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
Implementation
13%This skill is heavily padded with explanatory content that Claude doesn't need, while lacking the concrete, executable guidance that would make it useful. It describes what performance budget validation is rather than showing how to do it - no actual commands, code snippets, or example configurations are provided. The structure is verbose and monolithic rather than lean and well-organized.
Suggestions
Replace abstract instructions with executable code: show actual Lighthouse CLI commands (`lighthouse --budget-path=./budget.json`), example budget.json schema, and Python/JS code for parsing results
Remove sections explaining what performance budgets are and when to use them - Claude knows this. Keep only the 'how to execute' content
Add a concrete example budget.json file and show exact validation output format
Integrate validation checkpoints into the workflow: 'Run validation -> If threshold exceeded by >20%, block build -> If <20%, warn and continue'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanation of concepts Claude already knows. Sections like 'Overview', 'How It Works', and 'When to Use This Skill' explain what performance budgets are and why they matter - information Claude doesn't need. The content could be reduced by 70%+ while preserving all actionable information. | 1 / 3 |
Actionability | No concrete code, commands, or executable examples. The 'Instructions' section lists abstract steps like 'Load performance budget configuration' without showing how. No actual validation commands, no code snippets for reading budget files, no example budget JSON schema, no Lighthouse CLI commands. | 1 / 3 |
Workflow Clarity | The Instructions section provides a numbered sequence (1-6), but lacks validation checkpoints and feedback loops. No explicit 'if validation fails, do X' recovery steps. Error Handling section exists but is separate from the workflow rather than integrated as checkpoints. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline despite mentioning 'performance-budgets.json' and external tools. The 'Resources' section lists topics but provides no actual links or file references. Content that could be split (examples, error handling) is all in one file. | 1 / 3 |
Total | 5 / 12 Passed |
Activation
100%This is a well-crafted skill description that excels across all dimensions. It provides specific capabilities (validating performance against budgets), clear use cases (page load times, bundle sizes, API response times), and explicit trigger phrases. The description uses proper third-person voice and creates a distinct niche that minimizes conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'validate application performance against defined budgets', 'identify regressions', 'checking page load times, bundle sizes, or API response times against thresholds'. | 3 / 3 |
Completeness | Clearly answers both what (validate performance against budgets, identify regressions) AND when (explicit 'Use when...' clause plus 'Trigger with phrases like...' providing concrete trigger guidance). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'validate performance budget', 'check performance metrics', 'detect performance regression', 'page load times', 'bundle sizes', 'API response times'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on performance budgets and regression detection with distinct triggers like 'performance budget', 'performance regression', and specific metrics (bundle sizes, API response times) that are unlikely to conflict with general monitoring or testing skills. | 3 / 3 |
Total | 12 / 12 Passed |
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.