benchmarking

Use this skill when writing or running performance benchmarks for Jazz packages. Covers cronometro setup, file conventions, gotchas with worker threads, and how to compare implementations.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/benchmarking/SKILL.md

Quality

Content

77%

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

The content is highly actionable with executable examples, exact commands, and a clear sequenced workflow capped by a checklist, but it is held back by redundant duplicated templates and a monolithic single-file structure with no progressive disclosure of detailed material.

Suggestions

Collapse the near-duplicate 'Basic Template' and 'Single Cronometro Instance Per Benchmark' code blocks into one canonical template referenced once.

Move the full end-to-end example and/or the gotchas into a separate reference file (e.g. EXAMPLES.md, GOTCHAS.md) linked from the overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The 'Basic Template' and 'Single Cronometro Instance Per Benchmark' sections are near-duplicate ~40-line cronometro blocks, and the full example repeats the context-creation and bench-options code, so while generally efficient it could be tightened considerably.	2 / 3
Actionability	Provides fully executable code, exact commands like 'node --experimental-strip-types --no-warnings', a concrete npm-alias JSON snippet, and a copy-paste-ready complete benchmark, matching the level-3 anchor.	3 / 3
Workflow Clarity	A clear sequence runs from directory structure through naming, templates, running, and gotchas, reinforced by a thorough closing checklist; benchmarking is non-destructive so the absence of a validate/retry loop does not cap the score.	3 / 3
Progressive Disclosure	The skill is a single ~425-line file with no bundle references, inlining the full example and gotchas that could be split out; it is well-organized but exceeds the under-50-line carve-out that would allow a 3.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 clearly states both purpose and trigger conditions and carves out a distinct Jazz-benchmarking niche, but its trigger-term coverage is somewhat narrow and the second-person imperative phrasing slightly weakens specificity per the rubric guidelines.

Suggestions

Add natural variations users are likely to say, e.g. 'measuring performance', 'regression', or 'comparing the speed of' Jazz packages.

Rephrase in third person (e.g. 'Benchmarks Jazz package performance ... Use when ...') to avoid the second-person voice penalty.

Dimension	Reasoning	Score
Specificity	Quotes 'Covers cronometro setup, file conventions, gotchas with worker threads, and how to compare implementations' name multiple concrete sub-areas, but the second-person phrasing 'Use this skill when...' incurs the voice penalty per the guidelines, holding it below 3.	2 / 3
Completeness	An explicit 'Use this skill when writing or running performance benchmarks for Jazz packages' trigger answers both what it covers and when to invoke it, matching the level-3 anchor with explicit triggers.	3 / 3
Trigger Term Quality	'performance benchmarks' and 'compare implementations' are relevant natural terms, but common variations a user might say (e.g. 'speed', 'regression', 'measuring') are missing, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The scope is tightly bounded to 'Jazz packages' benchmarks with cronometro-specific triggers, giving it a clear niche unlikely to conflict with unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: garden-co/classic-jazz
Path: .cursor/skills/benchmarking/SKILL.md
Commit: 4f90501

Reviewed: 6 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.