performance-engineer

Expert performance engineer specializing in modern observability, application optimization, and scalable system performance. Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals, and performance monitoring. Handles end-to-end optimization, real user monitoring, and scalability patterns. Use PROACTIVELY for performance optimization, observability, or scalability challenges.

Quality

48%

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

35%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.

The body reads as a persona profile rather than an operational skill: it is heavily padded with inventories of tools and concepts Claude already knows and provides almost no executable guidance. The two step lists are coherent but lack concrete validation checkpoints, and everything lives inline with no progressive disclosure.

Suggestions

Cut the Capabilities, Knowledge Base, and Behavioral Traits sections (or collapse them into a short one-level-deep reference file) — Claude already knows what DataDog, k6, and Redis are.

Make the Instructions workflow executable: add concrete commands or code for a baseline measurement, a tracing/profile collection step, and a before/after comparison with explicit pass/fail criteria and a fix-and-re-validate loop.

Remove the redundant Purpose section (it repeats the description verbatim) and the Example Interactions that only restate capability names.

Dimension	Reasoning	Score
Conciseness	The ~95-line Capabilities taxonomy, Knowledge Base, and Behavioral Traits sections enumerate tools and concepts Claude already knows (DataDog, k6, Redis, Kafka, Docker), and the Purpose section repeats the frontmatter description verbatim — noticeably verbose with several padded sections, though it is enumeration rather than the explanatory prose of a 1.	2 / 5
Actionability	Guidance is high-level direction ("Collect traces, profiles, and load tests to isolate bottlenecks", "Propose optimizations with expected impact and tradeoffs") with no code, commands, or specific tool invocations — minimal concrete guidance missing the specific steps to execute, above 1 only because the intent of each step is discernible.	2 / 5
Workflow Clarity	Both the 4-step Instructions and 9-step Response Approach give a coherent sequence including a 'Verify results' step, but validation checkpoints are implicit and there are no concrete validation commands or fix-and-retry feedback loops.	3 / 5
Progressive Disclosure	No bundle files exist and the body has genuine section structure, but ~95 lines of capability taxonomy that clearly belongs in a separate reference file are inlined in SKILL.md — 'some structure but content that should be separate is inline' rather than the well-split 4.	3 / 5
	Total	10 / 20 Passed

Description

62%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.

The description is well-formed: third person, covers both what and when, and includes an explicit 'Use PROACTIVELY' trigger. Its main weaknesses are buzzword-heavy capability claims instead of concrete actions and thin trigger-term coverage missing natural user phrases like latency, slow, or profiling.

Suggestions

Replace capability claims ('Masters OpenTelemetry...') with concrete user-facing actions, e.g. 'Diagnose bottlenecks with distributed tracing, design load tests, tune caching layers'.

Broaden the 'Use when' clause with natural trigger phrases users actually say: 'slow responses', 'high latency', 'profiling', 'throughput', 'capacity planning'.

Trim promotional adjectives ('Expert', 'Masters', 'comprehensive') to reduce over-claim tone and save description tokens.

Dimension	Reasoning	Score
Specificity	The description names the domain and technologies ("Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals") and a couple of actions ("Handles end-to-end optimization, real user monitoring"), but these are capability claims and buzzwords rather than a list of several concrete actions, so it sits between anchor 3 and 4 — closer to 3.	3 / 5
Completeness	It answers both 'what' (observability, optimization, scalability expertise) and 'when' ("Use PROACTIVELY for performance optimization, observability, or scalability challenges"), but the 'when' clause is broad and lacks the concrete, varied trigger phrases of a 5.	4 / 5
Trigger Term Quality	Relevant keywords like "performance optimization", "observability", and "scalability" appear, but common natural variations users would say — "latency", "slow", "profiling", "throughput", "load testing" — are absent, matching 'some relevant keywords but missing common variations or synonyms' rather than the 4-level 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	The performance/observability niche is clear with distinct triggers and only minor overlap risk with general backend or frontend engineering skills — mostly distinct rather than a fully conflict-free niche.	4 / 5
	Total	14 / 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: rmyndharis/antigravity-skills
Path: skills/performance-engineer/SKILL.md
Commit: 3eff4af

Reviewed: 8 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.