performance-engineer

Expert performance engineer specializing in modern observability,

Quality

30%

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/performance-engineer/SKILL.md

Quality

Content

20%

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 persona/catalog skill: it enumerates tools and concepts Claude already knows and gives abstract process guidance with no executable commands or validation loops. It is organized into clear sections but is verbose and lacks concrete, copy-paste-ready instruction.

Suggestions

Cut the product-name inventories and concept lists down to the non-obvious guidance Claude would not already know, to improve token efficiency.

Add concrete, executable examples (e.g. a k6 load-test snippet, a flamegraph command, an OpenTelemetry trace query) instead of abstract step descriptions.

Insert explicit validation/feedback checkpoints in the Response Approach (e.g. re-measure baseline after each change, abort+rollback on regression) and move detailed capability catalogs into separate reference files.

Dimension	Reasoning	Score
Conciseness	The ~175-line body is padded with long inventories of well-known product names (DataDog, New Relic, Dynatrace, Redis, Kafka, etc.) and concept enumerations Claude already knows, violating the token-efficiency guideline against explaining familiar material.	1 / 3
Actionability	Guidance is abstract throughout ("Collect traces, profiles, and load tests to isolate bottlenecks", "Propose optimizations with expected impact and tradeoffs") with no concrete commands, code, tool invocations, or copy-paste-ready examples.	1 / 3
Workflow Clarity	Numbered sequences exist (Instructions, 9-step Response Approach) and a Safety section mentions rollouts/rollback, but there are no explicit validation checkpoints or fix-retry feedback loops for risky changes like load testing or production rollouts.	2 / 3
Progressive Disclosure	The file is well-sectioned with headers, but it is a single monolithic document over 50 lines with large capability/knowledge inventories inlined that could be split into reference files; no bundle references exist.	2 / 3
	Total	6 / 12 Passed

Description

40%

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 a truncated role label rather than a capability statement: it names a domain but no concrete actions and provides no use-when trigger guidance. It is third-person and on-niche but underspecified for routing.

Suggestions

Rewrite the description to list concrete actions, e.g. "Diagnoses performance bottlenecks, designs load tests, sets up observability, and optimizes latency and throughput."

Add an explicit "Use when..." trigger clause naming natural user phrases such as performance, latency, bottlenecks, load testing, profiling, or Core Web Vitals.

Fix the truncated trailing comma so the description is a complete sentence.

Dimension	Reasoning	Score
Specificity	The description "Expert performance engineer specializing in modern observability," only labels a role/domain and lists no concrete actions (no diagnose, optimize, profile, etc.), matching the vague/no-actions anchor; it is also truncated mid-sentence with a trailing comma.	1 / 3
Completeness	It partially states the "what" (a performance/observability domain), but the "when to use it" is entirely missing with no "Use when..." trigger clause, capping completeness at 2; the trailing comma also makes the "what" feel incomplete.	2 / 3
Trigger Term Quality	"performance" and "observability" are relevant keywords a user might say, but "modern observability" leans toward jargon and common variations (latency, bottleneck, load testing, profiling) are absent.	2 / 3
Distinctiveness Conflict Risk	Performance engineering is a recognizable niche, but the description is so terse and generic it could overlap with general DevOps, SRE, or observability skills rather than carving a distinct trigger surface.	2 / 3
	Total	7 / 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: sickn33/antigravity-awesome-skills
Path: skills/performance-engineer/SKILL.md
Commit: 6f14c22

Reviewed: 2 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.