CtrlK
BlogDocsLog inGet started
Tessl Logo

const-let

Use when reviewing scripts, client components, bundles, or runtime behavior related to Prefer const and let over var. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.

52

Quality

58%

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/const-let/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 establishes a clear, compact task structure (Check/Fix/Explain/Code Review) and correctly defers code examples to a real, one-level-deep reference file. Its main costs are token spend restating JavaScript basics Claude already knows and the absence of an explicit post-fix validation step for a batch code-editing operation.

Suggestions

Cut the opening paragraph and Quick Reference bullets that restate var/const/let fundamentals; keep the rule name and the Check/Fix/Explain/Code Review directives, which carry all the unique value.

Add an explicit validation checkpoint after the Fix step (e.g. re-verify behavior in the browser, especially loop closures and callbacks that captured var-scoped variables) instead of leaving verification to the Code Review section and reference file.

Deduplicate the 'Why It Matters' rationale, which appears nearly verbatim in both the body and references/rule.md.

DimensionReasoningScore

Conciseness

The opening paragraph and Quick Reference bullets restate JavaScript fundamentals Claude already knows (var's function scope and hoisting, const signaling no reassignment, 'const does not mean immutable'), and the rationale paragraph is duplicated verbatim in references/rule.md's 'Why It Matters'. Multiple sections of known-concept padding place this below the 'mostly efficient' anchor.

2 / 5

Actionability

Concrete, executable directives are present ('Scan this JavaScript file for any use of var and flag every occurrence with line numbers', 'Use const when the variable is never reassigned, let otherwise') and complete code examples live in references/rule.md (verified to exist and be runnable). Minor gaps keep it from a 5: the body has no code of its own and 'this JavaScript file' leaves the target implicit.

4 / 5

Workflow Clarity

The Check → Fix → Explain sections form a clear sequence, but the batch 'Replace all var declarations' step has no explicit validation checkpoint in the body — verification is only implied via the Code Review section and deferred to the reference file. This matches 'steps listed but validation gaps' rather than 'most checkpoints present'.

3 / 5

Progressive Disclosure

The body is a compact overview with a clearly signaled one-level-deep pointer ('see references/rule.md' — verified real, containing the code examples and ESLint config). Not a 5 because the why-it-matters paragraph is duplicated between body and reference instead of being cleanly split.

4 / 5

Total

13

/

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 has an explicit, specific 'Use when' clause anchored to the const/let/var rule, and a serviceable 'what' built around inspecting source code and browser execution paths. Its weaknesses are limited action specificity and missing natural synonyms (var, variable declarations, scope, hoisting) that users would actually say.

Suggestions

State the core operation concretely in the 'what' clause, e.g. 'Flags var declarations with line numbers and replaces them with const or let' instead of only 'Inspect... source code and the browser execution path'.

Add natural trigger synonyms users would say, such as 'var', 'variable declarations', 'block scope', 'hoisting', or 'ESLint no-var/prefer-const'.

Trim the generic 'scripts, client components, bundles, or runtime behavior' framing, which overlaps with sibling rule skills, in favor of rule-specific triggers.

DimensionReasoningScore

Specificity

Names the domain ('Prefer const and let over var') and a couple of concrete actions ('reviewing scripts, client components, bundles, or runtime behavior' and 'Inspect both source code and the browser execution path'), but the actions stay at the review/inspect level without stating concrete outputs like flagging or replacing var. Coverage is not comprehensive enough for a 4.

3 / 5

Completeness

Both parts are explicit: the 'what' ('Inspect both source code and the browser execution path so fixes target the real bottleneck or bug') and a clear 'Use when reviewing scripts, client components, bundles, or runtime behavior related to...' trigger. Not a 5 because the 'what' never states the skill's core operation (detecting and replacing var declarations).

4 / 5

Trigger Term Quality

Relevant keywords are present ('scripts', 'client components', 'bundles', 'const and let over var', 'browser execution path'), but common variations users would naturally say are missing — e.g. 'var', 'variable declarations', 'block scope', 'hoisting', or 'ESLint no-var'. This matches 'some relevant keywords but missing common variations or synonyms' rather than the good-coverage anchor.

3 / 5

Distinctiveness Conflict Risk

The rule-specific phrase 'Prefer const and let over var' carves a clear niche with minimal conflict risk, but the generic framing 'reviewing scripts, client components, bundles, or runtime behavior' would overlap with sibling frontend-checklist rule skills that share the same template.

4 / 5

Total

14

/

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
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.