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

31%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 verbose taxonomy of familiar tool names with no executable guidance, weak validation checkpoints for risky operations, and no progressive disclosure via reference files. It reads as a capability catalog rather than an actionable skill.

Suggestions

Replace the tool-name catalog with concrete, executable guidance: example profiling/load-test commands, key metrics to collect, and decision thresholds.

Add explicit validate-fix-retry checkpoints in the workflow for load testing and production rollouts (e.g. run test, check regressions, adjust, re-run).

Move the large Capabilities/Knowledge Base taxonomy into separate reference files (e.g. references/tools.md, references/patterns.md) and link to them from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~170-line body is a padded catalog of tool names Claude already knows, with restated purpose/knowledge-base sections that overlap the frontmatter; noticeably verbose.	2 / 5
Actionability	Content is predominantly descriptive capabilities and behavioral traits with no code, commands, or concrete profiling/load-test procedures; the Instructions and Response Approach are high-level hints.	2 / 5
Workflow Clarity	Instructions and Response Approach provide a rough sequence with a light 'verify results' step, but validation checkpoints for risky load-testing/prod-rollout operations are only implicit, capping it at 3.	3 / 5
Progressive Disclosure	No bundle/reference files exist; the large capability taxonomy and knowledge base are inlined into one monolithic SKILL.md when they clearly belong in separate reference files.	2 / 5
	Total	9 / 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, single-clause sentence naming the domain and one specialization, with no concrete actions, no 'Use when' trigger guidance, and only minimal natural keywords. It is below the midpoint on specificity, triggers, and completeness, with moderate overlap risk.

Suggestions

Complete the truncated description and list 3-4 concrete actions (e.g. 'Diagnose performance bottlenecks, design load tests, set up observability, optimize latency').

Add an explicit 'Use when...' clause with natural trigger phrases users would say (e.g. 'Use when diagnosing latency, designing load tests, or setting up tracing/APM').

Include common synonyms/file-format-style cues (e.g. Core Web Vitals, flame graphs, SLI/SLO) to improve trigger matching and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('performance engineer') and one specialization ('modern observability') but lists no concrete actions and the sentence is truncated mid-clause, so actions remain minimal.	2 / 5
Completeness	The 'what' is present but truncated and there is no 'Use when...' / trigger clause; the missing-when guideline and incomplete what push this below the midpoint.	2 / 5
Trigger Term Quality	'performance engineer' and 'observability' are domain-relevant but lean technical, with no natural user phrases (e.g. 'optimize latency', 'load testing') or synonyms included.	2 / 5
Distinctiveness Conflict Risk	'performance engineer / observability' is a recognizable niche but the description lacks distinct trigger phrases and could overlap with general devops/engineering skills.	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: b1aebac

Reviewed: ~15 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.