CtrlK
BlogDocsLog inGet started
Tessl Logo

common-performance-engineering

Enforce universal standards for high-performance development. Use when profiling bottlenecks, reducing latency, fixing memory leaks, improving throughput, or optimizing algorithm complexity in any language.

52

Quality

58%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/skills/common/common-performance-engineering/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description has a well-structured format with an explicit 'Use when...' clause and good trigger term coverage for performance-related queries. Its main weaknesses are the vague framing of 'enforce universal standards' which doesn't convey concrete actions, and the very broad scope ('any language') which could create overlap with more specific optimization skills.

Suggestions

Replace 'Enforce universal standards for high-performance development' with more concrete actions like 'Identifies performance bottlenecks, recommends optimization strategies, and refactors code for efficiency'

Consider narrowing scope or adding distinguishing details to reduce potential conflict with language-specific or domain-specific optimization skills

DimensionReasoningScore

Specificity

The description names a domain (performance optimization) and lists several actions like 'profiling bottlenecks, reducing latency, fixing memory leaks, improving throughput, optimizing algorithm complexity,' but these read more like categories of concern than concrete, specific actions (e.g., no mention of specific techniques, tools, or outputs). 'Enforce universal standards' is vague.

2 / 3

Completeness

Clearly answers both 'what' (enforce universal standards for high-performance development) and 'when' with an explicit 'Use when...' clause listing five specific trigger scenarios. Both components are present and explicit.

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would actually say: 'profiling', 'bottlenecks', 'latency', 'memory leaks', 'throughput', 'algorithm complexity', 'optimizing'. These cover a good range of performance-related queries a user might naturally express.

3 / 3

Distinctiveness Conflict Risk

While performance optimization is a recognizable niche, the phrase 'in any language' and 'universal standards' make it broad enough to potentially overlap with language-specific optimization skills or general code review skills. The trigger terms help but the scope is very wide.

2 / 3

Total

10

/

12

Passed

Implementation

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads more like a high-level checklist or coding standards document than an actionable skill for Claude. It covers broad performance engineering topics but lacks the concrete code examples, specific tool commands, and executable guidance needed to make it truly useful. The referenced implementation.md file is missing from the bundle, leaving the skill without the detailed patterns it promises.

Suggestions

Add concrete, executable code examples for key patterns (e.g., memoization, batching, profiling setup) either inline or in the referenced implementation.md file that must actually be included in the bundle.

Specify concrete profiling tools and commands for the Baseline step (e.g., `py-spy`, `perf`, `clinic.js`, browser DevTools commands) rather than just saying 'profile.'

Remove or significantly trim sections that state things Claude already knows (UI/UX Performance, basic data structure choices, what SLIs/SLOs are) to improve conciseness.

Add specific verification criteria to the workflow's Verify step, such as 'latency must decrease by >10%' or 'memory usage must not increase' to make the feedback loop actionable.

DimensionReasoningScore

Conciseness

Mostly efficient but includes some unnecessary explanations Claude already knows (e.g., explaining what SLIs/SLOs stand for, what tree shaking is, what Set vs List are for). Some sections like UI/UX Performance and Monitoring & Testing are fairly generic advice that doesn't add much beyond what Claude already knows.

2 / 3

Actionability

The skill provides no concrete code, commands, or executable examples. Everything is abstract guidance like 'use efficient serialization,' 'implement multi-level caching,' and 'write micro-benchmarks' without showing how. The referenced implementation.md file is not provided in the bundle, so the promised concrete patterns are missing.

1 / 3

Workflow Clarity

The 4-step workflow (Baseline → Identify → Fix → Verify) is a reasonable sequence with an implicit feedback loop, but it lacks specific validation commands, profiling tool recommendations, or concrete checkpoints. The verify step says 're-profile' but doesn't specify how to confirm improvement or what constitutes a regression.

2 / 3

Progressive Disclosure

The skill references implementation.md for detailed patterns, which is a good structural choice, but the bundle file is not provided, meaning the reference is broken. The main file's organization into sections is reasonable but some sections (UI/UX, Monitoring) could be split out or removed since they're generic advice without actionable depth.

2 / 3

Total

7

/

12

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

9

/

11

Passed

Repository
HoangNguyen0403/agent-skills-standard
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.