performance-profiling

Performance profiling principles. Measurement, analysis, and optimization techniques.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/performance-profiling/SKILL.md

Quality

Content

86%Weight 40%Scale 1-5

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

The body is a lean, well-structured web-performance reference: compact tables, concrete metric thresholds, a verified runnable script, and a clear measure-identify-fix-validate workflow. Its main weakness is that the headline workflow is expressed as abstract labels rather than executable commands, keeping actionability just below exemplary.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely compact tables with zero concept padding (no 'what Lighthouse is' bloat) and a single useful principle quote, matching anchor 5 'lean and efficient; every token earns its place'; there is no over-explanation to push it down to 4.	5 / 5
Actionability	Concrete thresholds (LCP < 2.5s, INP < 200ms), a copy-paste script invocation ('python scripts/lighthouse_audit.py https://example.com'), and problem→tool tables give mostly executable guidance; not 5 because the core 4-step workflow is shown as abstract labels (BASELINE/IDENTIFY/FIX/VALIDATE) rather than executable steps and most guidance is lookup tables rather than direct commands.	4 / 5
Workflow Clarity	Section 2 gives a clearly sequenced 4-step loop including a named VALIDATE step, matching anchor 4 'clear sequence with most checkpoints present'; the validation checkpoint is present but implicit (no concrete validate command), and profiling is read-only so the destructive-cap at 3 does not apply.	4 / 5
Progressive Disclosure	Seven well-headed numbered sections plus a runtime-scripts table referencing real bundle files (scripts/lighthouse_audit.py and scripts/bundle_analyzer.py, both verified present) one level deep with clear paths and usage, matching anchor 5 'clear overview with well-signaled one-level-deep references; easy navigation'.	5 / 5
	Total	18 / 20 Passed

Description

62%Weight 40%Scale 1-5

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 names the domain and several action areas with explicit trigger guidance supplied via the when_to_use field, but the 'what' is stated as abstract categories ('principles', 'techniques') rather than concrete capabilities, and natural user synonyms are thin. It is competent but not exemplary.

Suggestions

Replace abstract categories with concrete capabilities, e.g. 'Run Lighthouse audits, measure Core Web Vitals (LCP/INP/CLS), analyze bundle size, and identify runtime bottlenecks.'

Fold a few natural user trigger phrases into the description (e.g. 'slow page load', 'high latency', 'jank') so it triggers on how users actually phrase the problem.

Merge the when_to_use triggers into the description as an explicit 'Use when...' clause so both what and when live in one place.

Dimension	Reasoning	Score
Specificity	Quotes 'Performance profiling principles' (names the domain) and 'Measurement, analysis, and optimization techniques' (lists three action areas), but these are abstract categories rather than concrete named actions like the anchor-3 example 'extracts content', so it sits at 3 and not 4.	3 / 5
Completeness	The description gives a clear 'what' and the separate when_to_use field supplies explicit 'when' triggers ('diagnosing performance issues, running Lighthouse audits, analyzing bundle size, or optimizing Core Web Vitals'), satisfying 'equivalent explicit trigger guidance' so it is not capped at 3; not 5 because the two are split across fields and the 'what' is somewhat abstract.	4 / 5
Trigger Term Quality	'Performance profiling' is a natural user phrase, but common synonyms a user would actually say (slow, speed up, latency, jank) are absent from the description field, matching anchor 3 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	'Performance profiling' is a clear niche with distinct triggers (Lighthouse, Core Web Vitals) and minor overlap with general debugging skills, matching anchor 4 'mostly distinct; minor overlap risk'; not 5 because 'principles' and 'techniques' are slightly broad.	4 / 5
	Total	14 / 20 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: vudovn/ag-kit
Path: .agents/skills/performance-profiling/SKILL.md
Commit: 211561c

Reviewed: 8 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.