portaljs-add-dataset

Add a dataset (CSV, TSV, JSON, or GeoJSON) to an existing PortalJS portal. Appends an entry to datasets.json so the catalog and showcase render it automatically; routes the data by source (local file vs remote URL) — R2 via Git LFS by default, remote URLs by passthrough. Use when registering a new dataset in a scaffolded portal.

Quality

88%

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

85%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.

The body is well-structured, concise, and workflow-driven with explicit validation and error-recovery loops. Its main limitation is that the fully executable step-by-step workflow lives in an external canonical file, so the in-skill guidance is summary-level rather than copy-paste ready end-to-end.

Suggestions

Inline a minimal fully-executable command sequence (e.g. the git lfs install/track/add/push and the datasets.json append) so the skill is actionable without round-tripping to the external command file.

Tighten the routing-detail sentences in the Overview and Instructions, delegating more to references/reference.md, to push conciseness toward the leanest anchor.

Add a short pre-flight validation snippet (e.g. a one-liner checking for datasets.json, package.json, and pages/[owner]/[slug].tsx) to make the step-2 portal check concrete and copy-pasteable.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or explanations of concepts Claude already knows; a few routing-detail sentences could be trimmed or delegated to the reference, keeping it just below the leanest anchor.	4 / 5
Actionability	Concrete commands (npx next build, git lfs install/track), real file paths, and example invocations are present, but the end-to-end executable workflow is summarized and deferred to an external canonical command file rather than fully inlined.	4 / 5
Workflow Clarity	A 7-step sequenced workflow includes an explicit validation checkpoint (verify with npx next build; fix before reporting success) plus an error-handling table providing feedback loops for recovery.	5 / 5
Progressive Disclosure	SKILL.md acts as an overview with clearly signaled one-level-deep references to references/reference.md (confirmed present) and the canonical external command URL; detailed field and routing content is appropriately split into the reference file.	5 / 5
	Total	18 / 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.

The description is concrete, well-scoped, and explicitly covers both what the skill does and when to use it. Trigger-term coverage is strong with format extensions and synonyms, leaving only minor room for additional natural phrasings.

Dimension	Reasoning	Score
Specificity	Multiple concrete actions are listed — appending an entry to datasets.json, routing by source, R2 via Git LFS, and passthrough — with explicit format coverage (CSV, TSV, JSON, GeoJSON), matching the comprehensive anchor.	5 / 5
Completeness	Clearly states what it does (append manifest entry, route bytes by source) and explicitly when to use it via 'Use when registering a new dataset in a scaffolded portal.'	5 / 5
Trigger Term Quality	Strong natural terms including 'Add a dataset', 'registering a new dataset', format names and file extensions; a few common user phrasings are absent, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to PortalJS portals with a distinct format list and scaffolded-portal trigger, giving it a clear niche with minimal overlap risk.	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-add-dataset/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.