CtrlK
BlogDocsLog inGet started
Tessl Logo

error-handling

Apply Wellcrafted Result patterns to fallible operations and preserve failures at boundaries. Use when replacing try/catch, adding trySync or tryAsync, choosing fallback or propagation, or mapping errors.

71

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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-engineered body: lean decision tables, executable code, a final checklist, and properly gated references. The only costs are minor meta-maintenance text in the Source Of Truth section and a small amount of rule repetition.

DimensionReasoningScore

Conciseness

Dense, imperative rules with a compact decision table and no padding on concepts Claude already knows. Minor trims remain: the "Source Of Truth" section carries maintenance-meta text ("confirm that Epicenter's installed version matches the source being read... dependency freshness is handled outside this skill") and the "error !== null" discriminator rule appears in two sections. Not 5 because of this small redundancy; well above 3.

4 / 5

Actionability

Fully executable, copy-paste-ready examples cover the common cases: tryAsync with fetch and a defineErrors factory, unwrap(await openDocument(id)), and void save().then((result) => toastOnError(result, 'Save failed')), plus a concrete contract-selection table. Anchored rules ("Never construct Err(null)") are exact and followable.

5 / 5

Workflow Clarity

The decision flow is clearly sequenced (choose contract → cross boundaries → consume Err branches → own the Promise) and closes with a 5-item "Final Check" checklist. Not 5 because there are no explicit validate/fix feedback-loop steps, though the skill is decision guidance rather than a destructive or batch pipeline, so the workflow-clarity cap does not apply; well above 3 given the checklist.

4 / 5

Progressive Disclosure

Three one-level-deep references (wrapping-boundaries.md, toast-on-error.md, http-boundaries.md) — all verified to exist — each gated by an explicit read-when condition tied to a concrete decision point. The body stays a lean overview and the split is appropriate, matching the top anchor.

5 / 5

Total

18

/

20

Passed

Description

88%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 strong description: concrete actions, explicit Use-when triggers, and third-person voice. Trigger-term coverage and distinctiveness are the only soft spots — adding natural synonyms (e.g., "error handling", "exceptions", "Result type") would sharpen both.

DimensionReasoningScore

Specificity

Lists multiple concrete actions covering the domain comprehensively: "replacing try/catch", "adding trySync or tryAsync", "choosing fallback or propagation", "mapping errors", and "preserve failures at boundaries". Nothing significant is missing from the skill's stated scope.

5 / 5

Completeness

Explicitly answers both what ("Apply Wellcrafted Result patterns to fallible operations and preserve failures at boundaries") and when ("Use when replacing try/catch, adding trySync or tryAsync, choosing fallback or propagation, or mapping errors") with concrete trigger phrases. Matches the top anchor exactly.

5 / 5

Trigger Term Quality

Good natural-keyword coverage ("try/catch", "fallback", "mapping errors", "trySync/tryAsync") but misses common synonyms a user might say, such as "error handling", "exceptions", or "Result type". Not 5 because a few natural trigger phrases are absent; not 3 because coverage is clearly more than partial.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Wellcrafted Result boundary handling) with distinct triggers, but fairly general phrases like "choosing fallback" and "mapping errors" carry minor overlap risk with closely related error-handling skills. Distinct enough to be above anchor 3, not niche-exclusive enough for 5.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
EpicenterHQ/epicenter
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.