benchmark

Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.

Quality

72%

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 ./skills/benchmark/SKILL.md

The canonical home for this skill is tdg-personal/benchmark

Quality

Content

75%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.

A well-structured, mostly lean instruction skill with concrete metrics, targets, and commands across four benchmarking modes. Its main gap is the absence of executable measurement code or MCP call examples and lack of explicit feedback loops in the measurement modes.

Suggestions

Add a concrete example of an actual measurement call (e.g. a browser MCP snippet capturing LCP) so the per-mode steps are executable rather than descriptive.

Add an explicit validate/act loop for Mode 4 (e.g. "If any metric regresses past its target, flag as WARNING and do not mark the baseline as passing").

Consider moving the Core Web Vitals / resource target tables into a references file and keeping SKILL.md as a concise overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Lean metric/target lists and one-line mode intros assume Claude's competence without explaining what Core Web Vitals or p95 are; a 5 would require trimming the per-mode intro lines entirely.	4 / 5
Actionability	Concrete thresholds (LCP < 2.5s, JS < 200KB) and executable commands (`/benchmark baseline`, `/benchmark compare`) give mostly actionable guidance; falls short of 5 because the per-mode steps are checklist specs rather than runnable code or MCP call examples.	4 / 5
Workflow Clarity	Mode 4 lays out a clear baseline → change → compare sequence with a verdict table as a checkpoint; not a 5 because Modes 1–3 are flat checklists without explicit validate/fix/retry feedback loops.	4 / 5
Progressive Disclosure	Well-organized into clear sections (When to Use, How It Works, Output, Integration) in a single ~88-line file with no external references; not a 5 because the file exceeds the ~50-line simple-skill threshold and the metric/target catalogs could be split into a reference file.	4 / 5
	Total	16 / 20 Passed

Description

70%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.

A focused, third-person description with concrete actions and a clear niche, but it lacks an explicit "Use when..." trigger clause so completeness is capped. Trigger-term coverage is good though not exhaustive.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when measuring performance baselines, checking for regressions before/after a PR, or when users report something feels slow."

Broaden trigger terms with natural synonyms users say: "latency", "benchmark", "it feels slow", "Core Web Vitals".

Tighten specificity by hinting at measurement surfaces (page metrics, API endpoints, build times) so the scope is unambiguous.

Dimension	Reasoning	Score
Specificity	"measure performance baselines, detect regressions before/after PRs, and compare stack alternatives" names the domain plus three concrete actions, comparable to the anchor-4 example; not a 5 because the actions stay somewhat high-level without naming measurement surfaces.	4 / 5
Completeness	The description gives a clear "what" but opens with "Use this skill to..." rather than an explicit "Use when..." trigger clause, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural terms a user would say are present ("performance baselines", "regressions", "PRs", "stack"); a 5 would require synonyms/extensions like "latency", "benchmark", or "it feels slow" which are absent.	4 / 5
Distinctiveness Conflict Risk	"performance baselines, regressions before/after PRs, stack alternatives" carves a clear benchmarking niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/benchmark/SKILL.md
Commit: 06c5e11

Reviewed: 3 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.