CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

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

Quality

Content

65%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 well structured with an exemplary progressive-disclosure split into references/rule.md, and the Check/Fix instructions are actionable. The main weaknesses are the redundant re-teaching of basic var/const semantics in both the intro and Quick Reference, and the absence of a validation step after the batch var-replacement.

Suggestions

Cut the duplicated var-scope/hoisting explanation — keep either the intro paragraph or the Quick Reference bullets, and drop lines like 'const does not mean immutable' that restate knowledge Claude already has.

Add a validation checkpoint to the Fix workflow, e.g. 'After replacing, re-scan the file to confirm zero var occurrences and verify runtime behavior is unchanged' — the batch replacement currently has no verification step (the Verification section exists only in references/rule.md).

DimensionReasoningScore

Conciseness

The intro paragraph ('var's function scope and hoisting behavior regularly causes bugs...') and the Quick Reference bullets ('Never use var — it has function scope and is hoisted', 'const does not mean immutable') re-explain basic JavaScript concepts Claude already knows, and the var-scope explanation is stated twice (intro and Quick Reference). It is short overall, so it is 'mostly efficient but includes some unnecessary explanation' (anchor 3) rather than anchor 2's noticeably verbose.

3 / 5

Actionability

The Check, Fix, and Code Review sections give concrete, executable instruction: 'Scan this JavaScript file for any use of var and flag every occurrence with line numbers' and 'Replace all var declarations with const or let as appropriate. Use const when the variable is never reassigned, let otherwise.' Minor gaps remain (no example of how to report a flagged occurrence, ESLint enforcement only lives in the reference file), fitting anchor 4's 'mostly executable guidance with minor gaps' rather than anchor 5's fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

Check → Fix → Explain → Code Review is a recognizable sequence, but there is no validation checkpoint after the batch replacement ('Replace all var declarations') — e.g. re-run the scan to confirm zero var occurrences or verify behavior is unchanged. Per the guideline capping batch operations without validation steps at 3, this lands on anchor 3 ('steps listed but validation gaps') despite the otherwise clear order.

3 / 5

Progressive Disclosure

The body is a lean ~33-line overview with well-organized sections (Quick Reference, Check, Fix, Explain, Code Review), and all implementation details (code examples, ESLint config, framework guidance) are split into a single one-level-deep reference ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md') that exists as a real file. This matches anchor 5's clear overview with well-signaled one-level-deep references; no nesting or buried content.

5 / 5

Total

15

/

20

Passed

Description

70%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.

A solid description with an explicit and well-targeted 'Use when' clause and mostly concrete inspect/review actions. Its main weakness is that the core capability (detecting and replacing var declarations) is only implied by the rule's name rather than stated as a concrete action.

Suggestions

State the skill's core actions explicitly, e.g. 'Flags var declarations and replaces them with const or let' — currently the what is only implied by the rule name.

Add common natural trigger phrases such as 'block scope', 'hoisting', or 'ES6/ES2015 declarations' so users phrasing the need differently still match.

DimensionReasoningScore

Specificity

The description names the domain ('Prefer const and let over var') and 1-2 concrete actions — 'reviewing scripts, client components, bundles, or runtime behavior' and 'Inspect both source code and the browser execution path' — but never states the skill's core actions (flagging or replacing var declarations), so coverage is not comprehensive. It sits between anchor 3 and 4: more than a bare domain mention, but fewer concrete actions than anchor 4's 'several specific actions with minor gaps'.

3 / 5

Completeness

Both parts are present: the 'when' is explicit and specific ('Use when reviewing scripts, client components, bundles, or runtime behavior related to...'), and the 'what' is present through the inspect/review actions. It falls short of anchor 5 because the 'what' is indirect — it never plainly states what the skill does to var declarations (flag, replace, lint), so the what could be more explicit.

4 / 5

Trigger Term Quality

Good keyword coverage: 'scripts, client components, bundles, runtime behavior', 'source code', 'browser execution path', 'const and let', 'var'. A few natural terms are missing — users might say 'ES6/ES2015 declarations', 'block scope', 'hoisting', or 'var vs let' — which is exactly anchor 4's 'good coverage; a few natural terms missing', below anchor 5's synonym/extension completeness.

4 / 5

Distinctiveness Conflict Risk

The named rule 'Prefer const and let over var' carves a clear niche among JavaScript lint-style skills, and the var/const/let vocabulary is distinctive. Minor overlap risk remains with other JavaScript code-review skills that also trigger on 'scripts', 'client components', and 'runtime behavior', matching anchor 4 ('mostly distinct; minor overlap risk with closely related skills') rather than anchor 5's minimal conflict risk.

4 / 5

Total

15

/

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/const-let/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.