CtrlK
BlogDocsLog inGet started
Tessl Logo

performance-engineer

Expert performance engineer specializing in modern observability,

58

1.03x
Quality

37%

Does it follow best practices?

Impact

96%

1.03x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/performance-engineer/SKILL.md

The canonical home for this skill is performance-engineer in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

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 skill is a persona definition: well-organized and sequenced, but verbose and abstract. It lists tool catalogs Claude already knows and gives high-level directives instead of concrete, executable guidance, with only implicit validation in its workflow.

Suggestions

Trim the Capabilities catalog to the handful of decisions that actually shape behavior; move exhaustive tool lists to a reference file if needed rather than enumerating every product.

Add concrete, executable guidance — example commands or code for representative tasks (e.g., a k6 load test snippet, a flame-graph capture command, an OpenTelemetry trace query).

Make validation explicit in the workflow: add a clear "verify baseline vs. after" checkpoint and a validate-then-proceed loop before any production-affecting change.

DimensionReasoningScore

Conciseness

The Capabilities section is an encyclopedic enumeration of tools and concepts Claude already knows (every APM platform, profiler, load tester, CDN, cache, etc.), which is padded listing rather than earned tokens, matching "Noticeably verbose; several unnecessary explanations or padded sections."

2 / 5

Actionability

Guidance is high-level directives ("Collect traces, profiles, and load tests", "Propose optimizations with expected impact") with no concrete commands, code, tool invocations, or specific steps, fitting "Minimal concrete guidance; high-level hints but missing the specific steps to execute."

2 / 5

Workflow Clarity

Instructions and Response Approach give sequenced steps with a verify/guardrail step, but validation checkpoints are implicit and the skill involves risky operations (production load testing) without explicit validate-then-proceed feedback loops, fitting the level-3 anchor and the destructive-operations cap.

3 / 5

Progressive Disclosure

The body is well-sectioned with headers, but at ~170 lines the large Capabilities catalog is inlined content that would belong in a separate reference file; no bundle files exist, so it is monolithic-ish with some structure, fitting "Some structure but could be better organized; content that should be separate is inline."

3 / 5

Total

10

/

20

Passed

Description

40%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 title: it names a specialty but states no concrete actions and lacks any explicit use-when trigger guidance. It is reasonably distinctive but fails on completeness and specificity.

Suggestions

Rewrite as a concrete action statement, e.g. "Diagnoses performance bottlenecks, designs load tests, sets up observability stacks, and optimizes latency/throughput across backend, frontend, and infrastructure."

Add an explicit "Use when..." trigger clause listing natural phrases users would say (performance, latency, throughput, load testing, profiling, Core Web Vitals, SLI/SLO).

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

DimensionReasoningScore

Specificity

The description names the domain ("performance engineer", "modern observability") but provides no concrete actions — it is a role title rather than a statement of what the skill does, matching the anchor "Names the domain but actions are minimal or generic."

2 / 5

Completeness

It offers only a vague role-based "what" and no "when"/Use-when clause at all; the text also appears truncated mid-sentence (trailing comma), fitting "Has a vague 'what' and no 'when'" rather than the level-3 anchor which requires a clear what.

2 / 5

Trigger Term Quality

"performance engineer" and "observability" are natural terms users might say, but common variations like latency, throughput, optimization, load testing, and profiling are absent, fitting "Some relevant keywords but missing common variations or synonyms."

3 / 5

Distinctiveness Conflict Risk

"performance engineer specializing in modern observability" carves a recognizable niche with mostly distinct triggers, with only minor overlap risk against general optimization or observability skills.

4 / 5

Total

11

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.