CtrlK
BlogDocsLog inGet started
Tessl Logo

error-handling

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

58

Quality

67%

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/error-handling/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

A well-structured, lean overview that defers code examples to a real, one-level-deep reference file with a clear pointer. The main weakness is that the Check/Fix/Code Review flow is presented as parallel sections rather than a sequenced workflow with an explicit verification step.

Suggestions

Turn the Check → Fix → Code Review sections into an explicitly numbered sequence ending with a verification step (e.g. '4. Verify in the browser: exercise the changed handler and one error path (network failure) via DevTools'), which would add the missing validation checkpoint.

Drop or shrink the 'Explain' section — explaining standard try-catch/Promise/error-boundary concepts is knowledge Claude already has and duplicates references/rule.md.

DimensionReasoningScore

Conciseness

The ~30-line body is lean and section-driven ('Wrap async operations in try-catch blocks', 'Always re-throw or handle—never silently swallow errors') with no padding of concepts Claude already knows. Minor trims exist — the 'Explain' section ('Explain JavaScript error handling best practices...') covers knowledge Claude already has, and the intro sentence duplicates the reference file — so it fits anchor 4 rather than anchor 5's 'every token earns its place'.

4 / 5

Actionability

Guidance is concrete for an instruction-only skill: 'Add try-catch blocks to async operations and implement error boundaries for React components' and the Code Review section's 'Flag exact imports, event handlers, runtime side effects, or blocking operations... state how the change should be verified in the browser' tell Claude exactly what to do. It stops short of anchor 5 because specifics like what logging-with-context looks like are deferred to references/rule.md, but this matches 'mostly executable guidance; concrete... with minor gaps' rather than anchor 3's pseudocode/incompleteness.

4 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections provide an implicit sequence, and verification appears only as an output requirement ('state how the change should be verified in the browser') rather than an explicit validation checkpoint in the workflow. This matches anchor 3 ('steps listed but validation gaps; sequence present but checkpoints missing or implicit') — the destructive/batch cap does not apply, and anchor 4 requires checkpoints actually present in the steps.

3 / 5

Progressive Disclosure

The body is a concise overview with well-signaled, one-level-deep references: 'For full implementation details, code examples, and framework-specific guidance, see references/rule.md', and references/rule.md exists, is self-contained (no further nesting), and holds the code examples the body deliberately omits. This matches anchor 5 ('clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation').

5 / 5

Total

16

/

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 'Use when...' trigger and a concrete two-part what (source code + browser execution path), but it embeds the rule title verbatim ('related to Implement proper error handling'), which weakens both natural phrasing and specificity. It is serviceable but reads as generated boilerplate rather than a naturally worded trigger.

Suggestions

Rewrite the 'when' clause around natural user phrasing, e.g. 'Use when the user mentions uncaught errors, try-catch, Promise rejections, crashes, or error boundaries in JavaScript/React code' — this adds the missing synonyms and file/tech triggers that would raise trigger_term_quality.

State the skill's concrete actions explicitly (check async operations for try-catch, verify errors are logged with context, add React error boundaries) instead of the generic 'reviewing... related to <rule title>' boilerplate, which currently caps specificity.

Remove the awkward embedded rule-title phrase 'related to Implement proper error handling' — flatten it to 'related to error handling' so the sentence reads as a natural trigger condition.

DimensionReasoningScore

Specificity

The description names the domain (error-handling review) and 1-2 concrete actions — 'reviewing scripts, client components, bundles, or runtime behavior' and 'Inspect both source code and the browser execution path' — but coverage is not comprehensive; it never states what the skill actually does beyond reviewing/inspecting. It fits the 'names domain and 1-2 concrete actions, but not comprehensive' anchor rather than 4, which requires several specific listed actions, and is clearly above anchor 2, whose actions are minimal or generic.

3 / 5

Completeness

Both parts are present: 'when' is explicit ('Use when reviewing scripts, client components, bundles, or runtime behavior related to...') and 'what' is stated ('Inspect both source code and the browser execution path so fixes target the real bottleneck or bug'). It falls short of anchor 5 because the 'when' clause is awkwardly phrased (the embedded rule title 'Implement proper error handling' reads as boilerplate rather than a concrete trigger phrase) and the 'what' is thin; it is above anchor 3 since both what and when are explicitly present.

4 / 5

Trigger Term Quality

It includes some relevant natural terms ('error handling', 'scripts', 'client components', 'runtime behavior', 'bug', 'browser'), but misses the phrases a user would most naturally say for this need — 'try-catch', 'uncaught exceptions', 'error boundaries', 'Promise rejection', 'crash'. This matches 'some relevant keywords but missing common variations or synonyms' rather than anchor 4's 'good keyword coverage; a few natural terms missing', since the most common trigger vocabulary for error handling is absent.

3 / 5

Distinctiveness Conflict Risk

The error-handling scope ('related to Implement proper error handling', 'bottleneck or bug') gives it a clear niche distinct from most skills, with only minor overlap risk against generic code-review skills that also trigger on 'reviewing scripts... runtime behavior'. It is not anchor 5 because the boilerplate review-scope phrasing is shared with sibling checklist rules and general review skills, keeping some conflict risk.

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.