CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

70%

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/json-safety/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 a well-organized overview that appropriately defers detail to a single real reference file, with concrete review directives. It loses points for an over-explanatory intro paragraph and for presenting review modes without an explicit validation feedback loop.

Suggestions

Trim or remove the opening paragraph that restates what JSON.parse throws and why early catching matters — Claude already knows this; lead with the Quick Reference instead.

Convert Check → Fix → Code Review into an explicit sequenced workflow with a validation checkpoint (e.g., 'after fixing, verify in the browser via DevTools; re-check remaining JSON.parse calls before done') to add a fix→verify feedback loop.

Make the reference pointer a clickable link (e.g., 'see [references/rule.md](references/rule.md)') so navigation is unambiguous.

DimensionReasoningScore

Conciseness

The opening paragraph explains that JSON.parse throws a SyntaxError and why catching early matters — concepts Claude already knows — while the Quick Reference and Check/Fix sections are tight, so it is mostly efficient with a notable unnecessary explanatory block rather than the lean 4 or 5.

3 / 5

Actionability

Concrete directives ('Find all JSON.parse() calls... check whether each one is wrapped in try/catch and whether the result is validated') and a specific Quick Reference give actionable guidance; the instruction-skill carve-out covers the absence of inline code since full examples live in the reference, leaving only minor gaps.

4 / 5

Workflow Clarity

Check/Fix/Explain/Code Review read more as parallel modes than a sequenced workflow, and explicit validation checkpoints or fix→retry feedback loops are absent from the body (only a passing 'state how the change should be verified in the browser' mention), matching the 'steps listed but validation gaps' anchor.

3 / 5

Progressive Disclosure

The body is a concise overview with well-organized sections and a single, clearly signaled one-level-deep pointer ('see references/rule.md') that resolves to a real file containing the detailed examples, fitting the clear-overview-with-one-level-deep-references anchor for a simple skill.

5 / 5

Total

15

/

20

Passed

Description

75%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 is well-structured with an explicit 'Use when' trigger, concrete review actions, and a clear JSON-safety niche. It is strong across all dimensions but stops short of the top anchor because trigger synonyms are missing and the 'when' clause mixes in procedural guidance.

DimensionReasoningScore

Specificity

Names the domain ('Parse JSON safely with error handling') and several concrete review actions — 'reviewing scripts, client components, bundles, or runtime behavior' and 'Inspect both source code and the browser execution path' — with only minor coverage gaps, fitting the 'lists several specific actions' anchor rather than the comprehensive 5.

4 / 5

Completeness

Explicit 'Use when...' trigger is present and the 'what' (reviewing/inspecting JSON safety) is clear, satisfying the gate above 3; the 'when' is explicit but blends in how-to guidance ('Inspect both source code and the browser execution path'), so it is not the crisp concrete-trigger-phrases level of a 5.

4 / 5

Trigger Term Quality

Includes natural terms a user would say ('Parse JSON safely', 'error handling', 'scripts', 'client components', 'bundles', 'runtime behavior', 'browser execution path') but misses common synonyms like 'JSON.parse', 'try/catch', or file extensions, so it is good but not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

The 'Parse JSON safely with error handling' niche is distinct with minimal conflict risk, but the broad 'reviewing scripts, client components, bundles, or runtime behavior' framing creates minor overlap with general JS/code-review skills, keeping it just below the clearly-distinct 5.

4 / 5

Total

16

/

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.

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.