performance-engineer

Expert performance engineer specializing in modern observability,

Quality

31%

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 is a persona definition rather than an operational skill: the bulk is an encyclopedic catalog of tools and traits Claude already knows, while the actionable core (when to use, 4-step instructions, safety notes) is thin and abstract. It would benefit from cutting the persona sections and adding concrete methodology, tool commands, and validation steps.

Suggestions

Cut the Capabilities, Behavioral Traits, Knowledge Base, and Example Interactions sections (~120 lines of tool lists Claude already knows) and keep only the decision-relevant guidance: use/don't-use criteria, methodology, and safety.

Make the workflow actionable: specify how to collect data (e.g., flame graph tooling, k6 script structure, trace-analysis queries) and what 'verify results' means concretely (regression thresholds, before/after metric comparison).

Move domain-specific reference material (per-tool profiling commands, caching invalidation patterns) into a references/ file linked one level deep, keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Roughly 140 of the 175 lines are persona padding — capability catalogs listing tools Claude already knows ('Redis, Memcached, Hazelcast', 'LCP, FID, CLS optimization'), Behavioral Traits, and a Knowledge Base section that restate common knowledge. This matches anchor 2 ('noticeably verbose; several padded sections'); it is above anchor 1 because there is no tutorial-style concept explanation and the Use/Do-not-use/Instructions/Safety sections are lean.	2 / 5
Actionability	Instructions like 'Collect traces, profiles, and load tests to isolate bottlenecks' are high-level direction with no code, commands, tool invocations, or metric thresholds anywhere in the body. This fits anchor 2 ('minimal concrete guidance; high-level hints missing specific steps'); not 1 because the Instructions and Response Approach sections do provide a real, if abstract, process skeleton.	2 / 5
Workflow Clarity	Steps are sequenced ('Confirm performance goals... Collect traces... Propose optimizations... Verify results and add guardrails') with a more detailed 9-step Response Approach, but validation is a single vague mention with no concrete checkpoints, commands, or error-recovery loops. Matches anchor 3 ('steps listed but validation gaps; checkpoints missing or implicit'); not 4 because checkpoints are implicit rather than actionable.	3 / 5
Progressive Disclosure	Section headers are clear and well-organized, but the entire capability reference material (~100 lines of tool catalogs) is inlined in one 175-line file with no bundle files or references at all — content that clearly belongs in separate reference files sits inline. Matches anchor 3 ('some structure, content that should be separate is inline'); not 2 because the structure is genuinely organized, not minimal.	3 / 5
	Total	10 / 20 Passed

Description

28%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 a truncated persona tagline rather than a functional skill description: it names the performance-engineering domain but states no concrete actions, no trigger phrases, and no use-when guidance. It reads as metadata for a persona and would rarely match a user's natural request phrasing.

Suggestions

Rewrite the description as a capability statement with concrete actions, e.g. 'Diagnose performance bottlenecks, design load tests, set up observability with OpenTelemetry/Prometheus, and optimize latency, throughput, and resource efficiency.'

Append an explicit trigger clause: 'Use when the user mentions slow responses, latency, throughput, load testing, profiling, or setting up monitoring/observability.'

Remove the trailing comma and persona framing ('Expert ... specializing in') in favor of third-person action verbs so the description is complete and specific.

Dimension	Reasoning	Score
Specificity	The description 'Expert performance engineer specializing in modern observability,' names the domain clearly but lists zero concrete actions — it is a role label, matching the anchor 'names the domain but actions are minimal or generic'. It is above anchor 1 because the domain is specifically stated rather than pure abstraction, but below anchor 3 because no action verbs or capabilities appear.	2 / 5
Completeness	It offers a vague 'what' (a persona title, truncated with a trailing comma) and no 'when' clause at all — exactly anchor 2. The 'Use when' cap of 3 is not reached because the 'what' itself is also vague, keeping it at 2 rather than 3.	2 / 5
Trigger Term Quality	Only 'performance engineer' and 'modern observability' appear as keywords; natural phrases users would actually say ('optimize latency', 'slow API', 'load test', 'profile this service') are entirely missing. Fits anchor 2 ('one or two generic keywords, missing natural phrases'); not 3 because no common variations or synonyms are present.	2 / 5
Distinctiveness Conflict Risk	The performance/observability domain is somewhat specific, but with no explicit trigger guidance the description could overlap with SRE, debugging, or cloud-ops skills. Matches anchor 3 ('somewhat specific but could still overlap'); not 4 because distinct triggers are entirely absent.	3 / 5
	Total	9 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/performance-engineer/SKILL.md
Commit: 7b534bc

Reviewed: 5 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.