CtrlK
BlogDocsLog inGet started
Tessl Logo

import-on-interaction

Use when reviewing slow initial loads caused by optional features. Prioritize code that is expensive to download or execute and not required for the first viewport, first input, or core task completion.

62

Quality

73%

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 ./skills/import-on-interaction/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is well-structured with actionable, specific review guidance and a clean one-level reference to rule.md. Its main weaknesses are mild redundancy across sections and a workflow that lacks explicit numbered steps and a validation feedback loop.

Suggestions

Trim the opening rationale paragraph and de-duplicate the Check, Fix, and Code Review sections so each section adds distinct information.

Number the Check → Fix → Verify sequence and add an explicit validate-then-retry checkpoint so the workflow reads as a sequenced process.

Surface the natural trigger vocabulary (lazy loading, code splitting, bundle size, dynamic import) in the body to match how users describe this need.

DimensionReasoningScore

Conciseness

The body is brief and sectioned, but the opening paragraph re-explains the well-known rationale for import-on-interaction and the Check, Fix, and Code Review sections repeat the same guidance (defer non-critical code behind user-triggered dynamic import), so it could be tightened.

2 / 3

Actionability

As an instruction/review skill it gives concrete, specific guidance—"Use dynamic import() so the code is absent from the initial route bundle", named inspection targets (event handlers, modal triggers, drawers, editors, maps, export actions), and a specific fix—so the absence of inline code is not penalized.

3 / 3

Workflow Clarity

Check, Fix, and Code Review form an implicit sequence and the Code Review section does mention verifying the fix ("verify the fix keeps the initial path lighter without degrading the triggered flow"), but steps are not numbered and there is no explicit validate-fix-retry feedback loop.

2 / 3

Progressive Disclosure

The SKILL.md is a concise overview with well-organized sections and a single clearly signaled one-level-deep reference—"see references/rule.md" for full implementation details and code examples—and that file exists in the bundle.

3 / 3

Total

10

/

12

Passed

Description

75%

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 clear, trigger-explicit, and well-scoped to a distinct performance niche. It could be improved by adding the natural developer vocabulary (lazy load, code splitting, dynamic import) and naming more concrete actions.

DimensionReasoningScore

Specificity

The description names the domain and concrete selection criteria ("expensive to download or execute", "not required for the first viewport, first input, or core task completion"), but the only actions are the review-meta verbs "reviewing" and "Prioritize", which is not a comprehensive action list.

2 / 3

Completeness

It opens with an explicit "Use when reviewing slow initial loads caused by optional features" trigger and follows with a clear statement of what to do (prioritize expensive, non-critical code), answering both what and when.

3 / 3

Trigger Term Quality

Phrases like "slow initial loads", "optional features", and "first viewport" are natural, but common developer variations such as lazy loading, code splitting, bundle size, and dynamic import are missing.

2 / 3

Distinctiveness Conflict Risk

The niche is specific—optional features not needed for the first viewport, input, or core task—and the trigger is narrow enough to avoid firing for adjacent performance skills like image optimization or render-blocking fixes.

3 / 3

Total

10

/

12

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
thedaviddias/Front-End-Checklist
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.