json-safety

Use when reviewing scripts, client components, bundles, or runtime behavior related to Parse JSON safely with error handling. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/json-safety/SKILL.md

Quality

Content

60%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 compact, well-sectioned review workflow with a clean one-level-deep pointer to a real reference file containing the executable examples. Its weaknesses are the duplicated known-concept intro paragraph (which also appears verbatim in the reference), the complete absence of any code snippet in the body itself, and verification being directed rather than built in as a checkpoint.

Suggestions

Drop the intro paragraph or reduce it to one sentence — it explains a concept Claude already knows and duplicates 'Why It Matters' in references/rule.md verbatim.

Inline one minimal safe-parse snippet (try/catch with fallback) in the Fix section so the body is actionable even before opening the reference.

Turn the browser-verification remark into an explicit final step of the workflow (e.g. 'Verify: confirm the page loads and the fallback path is exercised in the browser') to close the feedback loop.

Dimension	Reasoning	Score
Conciseness	The Check/Fix/Explain/Code Review sections are terse, but the opening paragraph re-explains what Claude already knows ('JSON.parse() on invalid input throws a SyntaxError that will crash your application if uncaught...') and duplicates the 'Why It Matters' text in references/rule.md verbatim — a clear trim target.	3 / 5
Actionability	Concrete procedural guidance is present ('Find all JSON.parse() calls in this file and check whether each one is wrapped in try/catch', 'Add try/catch error handling... add shape validation'), but the body contains zero executable code — the try/catch and validation examples live only in the reference, so the body itself stops short of copy-paste-ready guidance.	3 / 5
Workflow Clarity	The Check -> Fix -> Explain -> Code Review sequence is coherent and verification is addressed ('state how the change should be verified in the browser'). Not 5 because verification is an instruction to state rather than a built-in checkpoint, and there is no feedback loop for the fix step.	4 / 5
Progressive Disclosure	A short, well-sectioned overview points to a single clearly-signaled, verified, one-level-deep reference (references/rule.md) for code examples and framework guidance. Not 5 because the 'why it matters' paragraph is inlined in both the body and the reference — content that should live in only one place.	4 / 5
	Total	14 / 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 'Use when' trigger and gestures at concrete review actions, but the core capability is stuffed into a title phrase ('related to Parse JSON safely with error handling') instead of being stated as concrete actions, and it lacks the natural trigger terms (JSON.parse, try/catch, localStorage, API responses) users would say. The broad 'reviewing scripts, client components, bundles' framing also creates overlap risk with generic frontend review skills.

Suggestions

Rewrite as a third-person capability statement with concrete actions, e.g. 'Flags unguarded JSON.parse() calls, wraps them in try/catch, and validates parsed shapes before use. Use when reviewing code that parses JSON from API responses, localStorage, or user input.'

Add natural trigger terms users would actually say — 'JSON.parse', 'try/catch', 'safe parsing', 'localStorage', 'API response' — instead of the generic 'scripts, client components, bundles'.

State 'what' and 'when' in two clean sentences instead of embedding the rule title inside the 'Use when' clause.

Dimension	Reasoning	Score
Specificity	The description names the domain (JSON parsing safety) and 1-2 concrete actions ('reviewing scripts, client components, bundles, or runtime behavior', 'Inspect both source code and the browser execution path'), but the core capability is expressed as a crammed-in title phrase ('related to Parse JSON safely with error handling') rather than a list of specific capabilities, leaving coverage incomplete.	3 / 5
Completeness	Both parts are present: 'when' is explicit ('Use when reviewing scripts, client components, bundles, or runtime behavior...') and 'what' is stated (inspect source code and the browser execution path for JSON safety). Not 5 because the 'what' is awkwardly embedded in a title-like clause rather than cleanly stated as concrete capabilities.	4 / 5
Trigger Term Quality	It includes some relevant keywords ('JSON', 'error handling', 'scripts', 'runtime behavior', 'bundles') but misses the natural phrases users would actually say — 'JSON.parse', 'try/catch', 'localStorage', 'API response', 'safe parsing' — so common variations and synonyms are absent.	3 / 5
Distinctiveness Conflict Risk	'Reviewing scripts, client components, bundles, or runtime behavior' is broad and would overlap with many general frontend code-review skills; only the JSON-safety tie narrows it, so overlap risk with closely related skills remains.	3 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: thedaviddias/Front-End-Checklist
Path: skills/json-safety/SKILL.md
Commit: 7bfd868

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.