define-errors

defineErrors from wellcrafted: variant factories, extractErrorMessage, InferErrors/InferError, call site patterns. Use when creating error types or reviewing error patterns.

Quality

81%

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

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable code and a clear rule-and-pattern structure, but it is over-long and monolithic. Tightening the repeated examples and offloading the philosophy/history sections into reference files would improve both conciseness and progressive disclosure.

Suggestions

Trim repetition: the CompressFailed/VerifyFailed FfmpegError example appears in Patterns, Anti-Patterns, and elsewhere — keep it once and cross-reference.

Move the ad-hoc {ok} Result philosophy, the wire-format corollary, and the Err(null)/'data'-field PR history into a separate reference file linked from a short inline summary, reducing the monolithic wall of text.

Add explicit progressive-disclosure links ('See references/error-philosophy.md for why Result{ok} is banned') so the overview stays lean while detail is one level deep.

Dimension	Reasoning	Score
Conciseness	The body is dense and code-centric and assumes Claude's competence, but it is long (~393 lines) with some repetition (the CompressFailed/VerifyFailed example recurs) and verbose rationale such as PR history around the 'data' field convention that could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready TypeScript across imports, factory definitions, call sites, and exhaustive-switch patterns, with explicit WRONG/CORRECT pairs for every anti-pattern.	3 / 3
Workflow Clarity	Ten sequenced Core Rules plus a pattern catalog progressing from simple to complex (Patterns 1–5) give a clear, organized structure; as an idioms skill with no destructive/batch operations, no validation checkpoint is required.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a large monolithic single-file document (~393 lines); content like the long anti-pattern catalog, the Result/{ok} philosophy, and the Err(null) deep-dive is inline when it could be split into reference files with one-level-deep navigation.	2 / 3
	Total	10 / 12 Passed

Description

85%

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, concrete description that pairs a specific capability list with an explicit usage trigger and a clearly bounded wellcrafted niche. Its only weakness is trigger-term breadth, where more natural user phrasings would help discovery.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete API surfaces — 'variant factories, extractErrorMessage, InferErrors/InferError, call site patterns' — going beyond naming the domain to listing specific capabilities.	3 / 3
Completeness	It answers both what ('variant factories, extractErrorMessage, InferErrors/InferError, call site patterns') and when with an explicit 'Use when creating error types or reviewing error patterns' trigger clause.	3 / 3
Trigger Term Quality	It includes relevant triggers like 'creating error types' and 'reviewing error patterns', plus the literal 'defineErrors', but misses common user variations such as 'define error', 'tagged error', or 'Result error', so coverage is only partial.	2 / 3
Distinctiveness Conflict Risk	The 'defineErrors from wellcrafted' framing pins a clear niche tied to a specific library's error API, making it unlikely to trigger for unrelated error-handling skills.	3 / 3
	Total	11 / 12 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/define-errors/SKILL.md
Commit: cb12bcc

Reviewed: 3 days 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.