perf-benchmarker

Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.

Quality

67%

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 ./perf/skills/benchmark/SKILL.md

Quality

Content

50%

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

The content is organized and free of concept padding, but it is held back by a missing concrete run-command example, an implicit rather than explicit validation/re-run workflow, a broken external reference, and mild redundancy between its output and rules sections.

Suggestions

Add one concrete benchmark invocation example (e.g. a hyperfine or cargo-bench command) so the run step is copy-paste ready, not just the output format.

Make the workflow an explicit numbered sequence with a validation checkpoint (detect anomaly → diagnose → re-run → confirm result) instead of a single "Re-run anomalies" bullet.

Either create docs/perf-requirements.md or remove the "Follow ... as the canonical contract" line, since the referenced file does not exist and the rules are already stated inline.

Dimension	Reasoning	Score
Conciseness	The body is terse and avoids concept teaching, but the "Follow docs/perf-requirements.md" line plus separate "Output Format" and "Output Contract" sections duplicate rules already in "Required Rules", so it could be tightened past the lean level-3 anchor.	2 / 3
Actionability	Concrete rules (60s/30s/10s warmup), an output template, and a JSON contract with markers are actionable, but no executable benchmark-invocation command is shown, leaving the "how to actually run it" key detail incomplete rather than copy-paste ready at level 3.	2 / 3
Workflow Clarity	Rules imply warmup → measure → re-run order and "Re-run anomalies" is a checkpoint, but there is no explicit numbered sequence or validate→diagnose→retry feedback loop, and batch-like repeated runs lack explicit validation, capping clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized and the skill is under 50 lines, but it references docs/perf-requirements.md as the canonical contract and that file does not exist in the bundle, a broken one-level reference that prevents the level-3 clean-navigation anchor.	2 / 3
	Total	8 / 12 Passed

Description

85%

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 is strong: explicit trigger, multiple concrete capabilities, and a distinctive niche with numeric constraints. Its only weakness is trigger-term breadth, missing common informal phrasings users might actually say.

Dimension	Reasoning	Score
Specificity	"running performance benchmarks, establishing baselines, or validating regressions" plus "Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks" lists multiple concrete actions with specific numeric constraints, matching the level-3 anchor.	3 / 3
Completeness	It opens with an explicit "Use when..." trigger and then states what the skill does and enforces, clearly answering both what and when, matching the level-3 anchor.	3 / 3
Trigger Term Quality	"performance benchmarks", "baselines", and "validating regressions" are relevant keywords, but common user phrasings like "speed test", "is it faster", or "measure performance" are missing, so coverage is partial rather than the broad level-3 set.	2 / 3
Distinctiveness Conflict Risk	The sequential-runs / 60s-minimum / no-parallel-benchmarks niche is specific with distinct triggers unlikely to collide with general skills, matching the level-3 anchor.	3 / 3
	Total	11 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: composio-community/awesome-claude-plugins
Path: perf/skills/benchmark/SKILL.md
Commit: e521f7a

Reviewed: about 13 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.