validating-performance-budgets

Validate 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".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

35%

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

The body is well-sectioned and conveys a clear high-level process, but it is padded with restatement and generic guidance and—most critically—provides no executable code or commands and never points to the substantial Python scripts bundled alongside it. Actionability is the dominant weakness.

Suggestions

Replace the abstract 'Instructions' list with concrete, copy-paste-ready command examples that invoke the bundled scripts (e.g. `python scripts/validate_budget.py --budget budget.json --metrics metrics.json`).

Link to the bundled scripts from the body (e.g. 'See scripts/validate_budget.py for the validation logic, scripts/create_budget.py to author budgets, scripts/report_violation.py for reporting') so progressive disclosure actually reaches them.

Trim the restated Overview/How It Works/When to Use sections and the link-less Best Practices/Resources lists to remove generic padding and respect the token budget.

Dimension	Reasoning	Score
Conciseness	Sections like Overview, How It Works, and When to Use restate the description, and Best Practices/Resources are generic padding with no links, so it could be tightened considerably — though it stops short of explaining external concepts Claude already knows.	2 / 3
Actionability	The body contains no code and no executable commands; the 'Instructions' section is an abstract numbered list, and it never references or invokes the substantial bundled scripts (validate_budget.py, create_budget.py, report_violation.py) that exist in scripts/.	1 / 3
Workflow Clarity	A six-step sequence is present (load config → collect metrics → compare → identify violations → report → remediate), but there are no validation checkpoints, no error feedback loops, and no concrete commands anchoring each step.	2 / 3
Progressive Disclosure	The body is organized into clear sections, but it fails to signal the bundled scripts one level deep — the real executable logic lives in scripts/ yet is never linked from SKILL.md, leaving navigation incomplete.	2 / 3
	Total	7 / 12 Passed

Description

90%

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-structured description: it states a concrete purpose, gives explicit 'Use when' triggers, and lists natural trigger phrases a user would say. The only weakness is that the named actions are variations of a single validate/compare task rather than several distinct capabilities.

Dimension	Reasoning	Score
Specificity	Names the performance-budget domain and concrete metric types ('page load times, bundle sizes, or API response times'), but the distinct action verbs reduce to one task (validate/identify/check against thresholds) rather than the multiple distinct actions a 3 requires.	2 / 3
Completeness	Clearly states both what it does ('Validate application performance against defined budgets to identify regressions early') and when to use it via an explicit 'Use when...' clause plus quoted trigger phrases.	3 / 3
Trigger Term Quality	Explicitly quotes natural user phrases — "validate performance budget", "check performance metrics", "detect performance regression" — giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear niche (performance budget validation / regression detection) with distinctive triggers; 'check performance metrics' is mildly generic but the budget framing keeps it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 2 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.