CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

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

71%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 a lean, well-structured overview with concrete check-and-fix guidance and an exemplary one-level-deep reference split — references/rule.md exists and delivers exactly what the pointer promises. The main weaknesses are mild redundancy (intro vs. Explain/Code Review sections) and the absence of any verbatim command or code snippet in the body itself.

Suggestions

Trim the intro's XSS-consequence explanation to one line and merge or cut the redundant "Explain" and "Code Review" sections, which restate the intro and the description.

Add one concrete executable artifact to the Check section, e.g. a ready-to-run grep/ripgrep pattern for eval(, new Function(, and string-argument timers.

DimensionReasoningScore

Conciseness

The body is short, but the intro paragraph explains XSS consequences Claude already knows ("stealing sessions, making requests as the user, or redirecting to malicious sites"), and the "Explain" and "Code Review" sections largely restate the intro and the frontmatter description. It fits 'mostly efficient but includes some unnecessary explanation or could be tightened'; it is not 2 because there is no heavy padding and the Quick Reference is dense and useful.

3 / 5

Actionability

"Search this codebase for any use of eval(), new Function(), or setTimeout/setInterval with string arguments" and "JSON.parse for data, object lookups for dynamic dispatch, and Function references for timers" give concrete, executable direction. It is not 5 because the body itself contains no verbatim command or code (e.g., an actual grep pattern or replacement snippet), deferring all examples to the reference file.

4 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections form a clear, logical sequence and the operation is not destructive or batch, so no validation cap applies. It is not 5 because verification steps (which exist in references/rule.md) are not signaled in the body's workflow, and the "Code Review" section partially duplicates "Check", blurring the sequence.

4 / 5

Progressive Disclosure

The body is a concise, well-sectioned overview (Quick Reference, Check, Fix, Explain, Code Review) and points to a single, clearly signaled, one-level-deep reference: "For full implementation details, code examples, and framework-specific guidance, see references/rule.md" — a real, well-organized file covering code examples, safe alternatives, ESLint, CSP, and verification. Content is appropriately split with easy navigation.

5 / 5

Total

16

/

20

Passed

Description

58%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 has an explicit and reasonably targeted 'Use when' trigger, but the capability side is under-specified: it says where to look rather than what the skill does, and it omits natural trigger synonyms (XSS, security, new Function, CSP). The awkwardly embedded rule title reads as generated rather than natural.

Suggestions

Lead with a concrete 'what' before the trigger, e.g. "Flags eval(), new Function(), and string-argument setTimeout/setInterval usage and maps each to a safe alternative (JSON.parse, object lookups, function references)."

Add natural trigger synonyms users would actually say: "Use when reviewing JavaScript for security issues, XSS risks, eval(), new Function(), or unsafe dynamic code execution."

Trim filler like "so fixes target the real bottleneck or bug" and narrow the overly broad "reviewing scripts, client components, bundles, or runtime behavior" scope, which conflicts with general code-review skills.

DimensionReasoningScore

Specificity

The description names the domain ("reviewing scripts, client components, bundles, or runtime behavior") and one concrete action ("Inspect both source code and the browser execution path"), but the verbs are generic and it never states what the skill actually does (flag eval() violations, map safe alternatives). "so fixes target the real bottleneck or bug" is filler. It is not 4 because it does not list several specific capability actions, and not 2 because it goes beyond naming the domain with no actions.

3 / 5

Completeness

Both parts are present: an explicit trigger ("Use when reviewing scripts, client components, bundles, or runtime behavior...") and a 'what' ("Inspect both source code and the browser execution path"). It is not 5 because the 'what' side is comparatively vague and the phrasing stitches the rule title in awkwardly rather than giving concrete trigger phrases; it is not 3 because the 'when' is explicit, not merely implied.

4 / 5

Trigger Term Quality

It includes relevant keywords like "eval()", "unsafe dynamic code execution", "scripts", "client components", and "browser", but misses common natural variations a user would say such as "XSS", "security review", "new Function", "setTimeout", or "CSP". This matches the anchor for some relevant keywords missing common variations, below the good-coverage anchor 4.

3 / 5

Distinctiveness Conflict Risk

The eval()/dynamic-code-execution phrase carves out a niche, but the broad opening "reviewing scripts, client components, bundles, or runtime behavior" overlaps heavily with generic code-review and frontend-review skills, so it could trigger for the wrong skill. It sits between the overlap-risk and mostly-distinct anchors.

3 / 5

Total

13

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/avoid-eval/SKILL.md

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.