performance-profiling

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

Quality

57%

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

65%

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

The content is notably lean and well-organized into reference tables, but its guidance is mostly descriptive rather than executable, the profiling workflow lacks a concrete validation checkpoint, and one provided script is never surfaced in the body. It is efficient but stops short of fully actionable, validated instruction.

Suggestions

Add a concrete usage line for scripts/bundle_analyzer.py in the Runtime Scripts table (e.g. "python scripts/bundle_analyzer.py ./dist") so both provided scripts are discoverable and runnable.

Turn the abstract VALIDATE step into an explicit checkpoint, e.g. "Re-run scripts/lighthouse_audit.py and compare scores before and after the fix; only keep the change if the target metric improved."

Replace at least one descriptive mapping (e.g. Bundle Analysis "Big library → Import specific modules") with a copy-paste-ready code snippet so the skill is actionable rather than purely advisory.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely tight reference tables with no padded prose and no explanation of concepts Claude already knows (it gives Core Web Vitals thresholds without lecturing on what they are), matching the score-3 anchor of lean, efficient content where every token earns its place.	3 / 3
Actionability	One concrete executable command is given ("python scripts/lighthouse_audit.py https://example.com") and CWV thresholds are specific numbers, but most guidance is descriptive mappings ("Big library → Import specific modules", "Page load → Lighthouse") and the 4-step process is pseudocode, and the provided bundle_analyzer.py script is never shown how to run, matching the score-2 anchor of some concrete guidance that is incomplete.	2 / 3
Workflow Clarity	The 4-step process (BASELINE → IDENTIFY → FIX → VALIDATE) is a clear sequence, but validation is abstract ("Confirm improvement") with no concrete checkpoint or feedback loop such as re-running the audit and comparing scores, matching the score-2 anchor of steps present with implicit or missing checkpoints.	2 / 3
Progressive Disclosure	The body is well organized into numbered sections and signals the one-level-deep scripts/lighthouse_audit.py reference in a table, but the second bundle file scripts/bundle_analyzer.py exists yet is never referenced or surfaced in the body, leaving a provided script undiscoverable and matching the score-2 anchor of structure with references that could be better signaled.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 establishes a clear domain but relies on abstract action nouns and lacks an explicit "Use when..." trigger clause within the description field itself, leaving it at the mid-level across all dimensions. It is concise and in third person, but not comprehensive or trigger-rich.

Suggestions

Rewrite the description as concrete actions, e.g. "Run Lighthouse audits, measure Core Web Vitals (LCP/INP/CLS), analyze bundle size, and optimize rendering performance."

Append an explicit trigger clause to the description such as "Use when diagnosing slow page loads, low Lighthouse scores, large bundles, or poor Core Web Vitals."

Surface the specific trigger terms users actually say (Lighthouse, Core Web Vitals, bundle size, page speed) inside the description rather than only the generic measurement/analysis/optimization framing.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Performance profiling principles") and three action categories ("Measurement, analysis, and optimization techniques"), but these are abstract nouns rather than concrete actions like "extract text" or "fill forms", matching the score-2 anchor of naming a domain and some actions without being comprehensive.	2 / 3
Completeness	The description field answers "what" (profiling principles: measurement, analysis, optimization) but contains no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	"Performance profiling" is a natural term a user would say, but "Measurement, analysis, and optimization techniques" is generic and omits concrete variations users actually voice (Lighthouse, Core Web Vitals, bundle size, page speed), matching the score-2 anchor of some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	"Performance profiling" is a reasonably clear niche, but the generic tail "Measurement, analysis, and optimization techniques" could overlap with general optimization or debugging skills, matching the score-2 anchor of somewhat specific but still able to overlap with similar skills.	2 / 3
	Total	8 / 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: vudovn/ag-kit
Path: .agents/skills/performance-profiling/SKILL.md
Commit: 04514f0

Reviewed: about 12 hours 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.