An exemplary lean skill body: non-obvious, repo-specific guidance with fully executable examples and clear decision rules, with no wasted tokens. The only defect is the References section, whose two article links point to paths outside the skill bundle that do not resolve.

Suggestions

Fix or remove the References links: '../../../docs/articles/typebox-is-a-beast.md' and '.../20260429T120000-typebox-standard-schema-pivot.md' do not resolve from the skill's location; either move the articles into a references/ directory in the bundle or drop the section.

Dimension	Reasoning	Score
Conciseness	The body is lean and every token earns its place: deprecated package guidance, a needs-to-tool table, executable code, a Standard Schema boundary rule, and a dense repo policy. It explains nothing Claude already knows and includes no padding.	5 / 5
Actionability	Copy-paste-ready imports and code covering the common cases (define a schema, Value.Check, Compile, validator.Check/Parse), plus a concrete needs-to-tool table and an unambiguous TypeBox-vs-Arktype selection policy. Time-sensitive info (the deprecated package) is correctly isolated in a deprecation context.	5 / 5
Workflow Clarity	This is a single-purpose pattern/policy skill with no multi-step workflow, and the simple-skill exception applies: the decision routing (which library per surface, Value vs Compile per need) is unambiguous. There are no destructive or batch operations, so the validation cap does not apply.	5 / 5
Progressive Disclosure	Sections are well-organized and the body is appropriately short, but the two References links ('../../../docs/articles/typebox-is-a-beast.md' and '.../20260429T120000-typebox-standard-schema-pivot.md') point outside the bundle and do not resolve to real files in this environment, so navigation is only mostly reliable. Not a 3 because the body itself needs no external files and structure is otherwise good; not a 5 because the references are not verifiable one-level-deep bundle files.	4 / 5
	Total	19 / 20 Passed

Description

78%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, concise description that clearly states what the skill does and when to use it with concrete trigger terms. Its main weakness is limited action coverage (only two capabilities named) and omission of the deprecated '@sinclair/typebox' trigger that users plausibly still mention.

Suggestions

Add one or two more concrete capabilities to the what-clause, e.g. 'schema compilation and Static<> type inference', to lift specificity.

Include '@sinclair/typebox' and 'JSON Schema' as trigger terms, since users migrating from the deprecated package would mention them.

Dimension	Reasoning	Score
Specificity	Names the domain ('TypeBox patterns') with two concrete actions ('runtime schema validation and JSON Schema generation'), matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because it lists only two capabilities, omitting others the skill covers (compilation, Static<> type inference, JSON Schema portability).	3 / 5
Completeness	Explicitly answers both 'what' ('TypeBox patterns for runtime schema validation and JSON Schema generation') and 'when' ('Use when mentioning TypeBox, Standard Schema, or schema-based validation') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	'TypeBox', 'Standard Schema', and 'schema-based validation' are natural phrases users would say, giving good keyword coverage. Not a 5 because common variations are missing — notably the deprecated '@sinclair/typebox' package name (a highly likely user mention) and 'JSON Schema'.	4 / 5
Distinctiveness Conflict Risk	TypeBox is a clear niche with distinct triggers, but 'Standard Schema' and 'schema-based validation' could route requests toward this skill that belong to sibling schema-library skills (the body itself says Standard Schema work should prefer Arktype). Minor overlap risk with closely related skills, not minimal.	4 / 5
	Total	16 / 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/typebox/SKILL.md
Commit: f9441c8

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.