portaljs-define-schema

Define a dataset's metadata profile — infer a Frictionless Table Schema from its data, add Data Package metadata (license, sources, keywords), and write it into datasets.json so the showcase renders a typed field table. Extend or customize via the L0-L3 profile ladder. Use when a registered dataset needs field types, constraints, or catalog metadata before publishing.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

73%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-organized, concise body with a strong validation-backed workflow and good reference structure. Its main weakness is actionability: the executable core is outsourced to an external command file rather than inlined, so the skill itself stops short of copy-paste-ready guidance.

Suggestions

Inline the key executable steps (sample/parse CSV, infer types, write the schema fields block to datasets.json) as concrete code or commands instead of delegating the whole workflow to the external GitHub URL, so the skill is actionable without network access.

Move at least a minimal 'common cases' code snippet (e.g. a sample datasets.json entry before/after) into the body or references so the most frequent L0 path is self-contained.

Tighten the Examples section narrations and drop the duplicated L0–L3 ladder table (already implied by the description) to reclaim tokens.

Dimension	Reasoning	Score
Conciseness	Efficient, well-structured body that assumes Claude's competence and avoids explaining Frictionless/Data Package concepts; a few example narrations and the L0–L3 restatement could be trimmed further, keeping it just below the leanest anchor.	4 / 5
Actionability	Provides a concrete 9-step list with real commands and file paths, but the actual executable workflow is delegated off-skill to an external GitHub URL described as 'the single source of truth', so in-body guidance is incomplete for direct execution.	3 / 5
Workflow Clarity	A clear numbered sequence with an explicit validation checkpoint (step 8 'npx next build') and a fix-and-rebuild feedback loop, reinforced by a symptom/cause/fix Error Handling table — satisfying the validation requirement for an in-place write operation.	5 / 5
Progressive Disclosure	Overview points to a verified one-level-deep local reference (references/reference.md) and a clearly signaled external workflow link with easy navigation, but the bulk of executable detail lives off-site rather than being appropriately split into local files.	4 / 5
	Total	16 / 20 Passed

Description

92%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, third-person description that states concrete capabilities and an explicit 'Use when' trigger, with minimal conflict risk against related PortalJS skills. It is comprehensive on what/when and only slightly light on natural-term synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'infer a Frictionless Table Schema', 'add Data Package metadata (license, sources, keywords)', and 'write it into datasets.json' — with comprehensive coverage of what the skill does.	5 / 5
Completeness	Clearly answers 'what' (infer schema, add Data Package metadata, write to datasets.json) and explicitly answers 'when' with the concrete trigger phrase 'Use when a registered dataset needs field types, constraints, or catalog metadata before publishing.'	5 / 5
Trigger Term Quality	Includes natural domain terms ('field types, constraints, catalog metadata', 'Frictionless Table Schema', 'Data Package metadata') that users would plausibly say, though a few synonyms/variations are absent and the dataset format has no file extension to cover.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Frictionless schema authoring for registered datasets) and is explicitly distinguished from sibling skills like portaljs-add-dataset, so it is unlikely to trigger for the wrong skill.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: datopian/portaljs
Path: skills/portaljs-define-schema/SKILL.md
Commit: ebfd391

Reviewed: 7 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.