CtrlK
BlogDocsLog inGet started
Tessl Logo

avoid-eval

Use when reviewing scripts, client components, bundles, or runtime behavior related to Never use eval() or unsafe dynamic code execution. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.

60

Quality

71%

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/avoid-eval/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

The content is a clean, well-organized instruction skill with good progressive disclosure to a real reference file. Its weaker dimensions are actionability and workflow clarity, where the Fix guidance stays somewhat abstract and lacks a verification checkpoint after replacing eval calls.

Suggestions

Add a concrete before/after code example for the most common replacement (e.g., eval(data) -> JSON.parse(data), and setTimeout('doX()', 0) -> setTimeout(doX, 0)) so the Fix is copy-paste ready.

Add a verification step after fixing, e.g., confirm the replacement preserves behavior and that no string-argument setTimeout/setInterval or new Function remains via a follow-up search.

Trim the intro's background explanation of XSS consequences; keep only what Claude needs to prioritize the rule.

DimensionReasoningScore

Conciseness

The body is mostly lean and well-sectioned, but the intro paragraph explains eval/XSS background ("stealing sessions, making requests as the user, or redirecting to malicious sites") that Claude already knows, and the Quick Reference partly restates it.

2 / 3

Actionability

The Check and Fix sections name specific APIs and replacements (eval -> JSON.parse, setTimeout string -> function reference, new Function flagged), but "object lookups for dynamic dispatch" is abstract and no complete executable example demonstrates the replacement.

2 / 3

Workflow Clarity

The Check/Fix/Explain/Code Review sections read as parallel modes rather than one clearly sequenced, validated workflow; for a fix that changes code there is no verification step confirming the replacement preserves behavior.

2 / 3

Progressive Disclosure

The under-50-line body is organized into clear sections and signals a real one-level-deep reference ("For full implementation details, code examples, and framework-specific guidance, see references/rule.md"), matching the well-signaled one-level-deep anchor.

3 / 3

Total

9

/

12

Passed

Description

85%

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 strong, with an explicit "Use when..." trigger, multiple concrete review targets, and a distinct eval/XSS niche. Its weakest point is trigger-term quality, where the core security phrasing is awkwardly embedded in a rule-title construction rather than natural user speech.

Suggestions

Reword the security trigger so eval/XSS appear as natural user phrases (e.g., "Use when reviewing code for eval(), new Function(), or XSS risks from dynamic code execution") rather than embedding the rule title.

Lead with the core action ("Reviews code for eval() and unsafe dynamic code execution") before the "Use when" clause to make the what immediately scannable.

DimensionReasoningScore

Specificity

Lists multiple concrete review targets ("scripts, client components, bundles, or runtime behavior") and a concrete verification action ("Inspect both source code and the browser execution path so fixes target the real bottleneck or bug"), matching the multiple-specific-actions anchor.

3 / 3

Completeness

Opens with an explicit "Use when reviewing scripts, client components, bundles, or runtime behavior..." trigger and states what the skill does (review/inspect eval usage), clearly answering both what and when.

3 / 3

Trigger Term Quality

Includes natural review terms (scripts, client components, bundles, runtime behavior, source code, browser execution path), but the distinctive security triggers (eval, XSS, dynamic code execution) are embedded in a rule-title clause rather than phrased as a user would naturally say them.

2 / 3

Distinctiveness Conflict Risk

Scoped to a specific rule (eval / unsafe dynamic code execution) with concrete review contexts (client components, browser execution path), giving it a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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.