CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

providing-performance-optimization-advice

Produce a prioritized performance-optimization roadmap across frontend, backend, and infrastructure. Use as an explicit/manual helper after bottlenecks are known or suspected, not as the owner of regression detection, profiling capture, or test execution.

48

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/providing-performance-optimization-advice/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

43%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 admirably concise and well-organized as an overview, but it provides no executable guidance and never connects to the bundled scripts and reference docs that would make it actionable. Workflow is unsequenced with no validation, capping its practical usefulness.

Suggestions

Add concrete, executable guidance: reference and show how to invoke the bundled scripts (performance_profiler.py, optimization_suggestions.py, impact_estimator.py) with example commands, lifting actionability off anchor 1.

Define a short sequenced workflow with validation checkpoints (e.g. profile -> estimate impact -> rank -> validate the optimization worked) to move workflow_clarity above 2.

Link to the bundle explicitly (e.g. "See references/performance_optimization_best_practices.md" and the scripts) so progressive disclosure is one-level-deep and clearly signaled rather than missing.

DimensionReasoningScore

Conciseness

The body is lean throughout: short sections, bullets, no padding, and no explaining of concepts Claude already knows, matching anchor 5 ("Lean and efficient; assumes Claude's competence; every token earns its place").

5 / 5

Actionability

The body only describes outputs ("A ranked optimization backlog", "Concrete hotspots by layer") with no concrete code, commands, or steps, and never references the bundled scripts, matching anchor 1 ("only describes rather than instructs").

1 / 5

Workflow Clarity

Only a rough shape is implied via "When to Use" inputs and "Typical Outputs"; there is no sequenced workflow, no steps, and no validation checkpoints for the batch-style ranking output, fitting anchor 2 ("rough sequence present but many gaps; validation absent").

2 / 5

Progressive Disclosure

The body is well-sectioned, but it never links to its own bundle (references/, scripts/, assets/) even though those files exist, so references are effectively missing/unsignaled rather than one-level-deep and clearly navigated.

3 / 5

Total

11

/

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 concise, third-person, and clearly states both what it does and when to use it, with strong boundary signaling against related skills. Its main weakness is moderate specificity and trigger-term coverage, listing one primary action and leaning on abstract conditions rather than concrete user phrases.

Suggestions

Enumerate 2-3 concrete actions the skill performs (e.g. "rank bottlenecks by impact and effort, estimate gains, suggest validation steps") to lift specificity toward anchor 4-5.

Add natural trigger phrases users actually say ("slow API responses", "high latency", "page load times", "reduce cloud spend") to broaden trigger-term coverage.

Sharpen the "when" clause with concrete user triggers rather than the abstract "after bottlenecks are known or suspected" to move completeness toward anchor 5.

DimensionReasoningScore

Specificity

"Produce a prioritized performance-optimization roadmap across frontend, backend, and infrastructure" names the domain and one concrete action with layer scope, but does not enumerate multiple distinct actions (e.g. rank, size, validate), so it falls at anchor 3 rather than 4.

3 / 5

Completeness

It gives a clear "what" (produce a prioritized roadmap) and an explicit "when" ("Use as an explicit/manual helper after bottlenecks are known or suspected"), but the trigger is an abstract condition rather than a concrete user phrase, so it is anchor 4 not 5.

4 / 5

Trigger Term Quality

Terms like "performance-optimization", "bottlenecks", and "frontend, backend, and infrastructure" are relevant, but common natural phrasings users say ("slow", "latency", "speed up", "load times") are missing, placing it between anchors 3 and 4.

3 / 5

Distinctiveness Conflict Risk

The clause "not as the owner of regression detection, profiling capture, or test execution" carves out a clear niche from sibling skills, giving mostly-distinct positioning with only minor overlap risk in the broad performance space.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

foryourhealth111-pixel/Vibe-Skills

Path

bundled/skills/providing-performance-optimization-advice/SKILL.md

Revision

5ce2258

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill