portaljs-migrate

Migrate (harvest) datasets between open-data platforms. Reads CKAN, a DCAT-US /data.json catalog (DKAN, ArcGIS Hub, data.gov), a DCAT / DCAT-AP RDF feed (JSON-LD, Turtle, or RDF/XML), Socrata, OpenDataSoft, or an ArcGIS FeatureServer, and writes them to a static PortalJS catalog or pushes them into a CKAN instance over its API. Use when moving datasets from an external open-data platform into a PortalJS portal, or bridging one CKAN instance to another.

Quality

90%

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

88%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 tight, well-structured skill body with concrete examples, explicit validation checkpoints, and a real one-level reference file. The main limitation is that the complete executable command detail lives in an external GitHub URL rather than a bundled reference.

Suggestions

Bundle the full command workflow markdown into ./references/ (instead of only linking the GitHub URL) so the skill is self-contained and reviewable offline.

Add a short inline canonical-shape snippet or a one-line per-source read pointer in the body so Claude can start executing without first fetching the external command file.

Surface the `--source` auto-detection order (present in reference.md) as a brief inline note to aid the step-3 source-type detection step.

Dimension	Reasoning	Score
Conciseness	Lean and action-oriented throughout — it assumes Claude's competence, does not explain what CKAN/DCAT/RDF are, and every section (prerequisites, numbered workflow, error table, examples) earns its tokens.	5 / 5
Actionability	Provides four copy-paste CLI invocations, a 9-step workflow, and a symptom/cause/fix table, but the fully executable per-source field mappings and command details are deferred to an external GitHub command file rather than being self-contained.	4 / 5
Workflow Clarity	A clearly sequenced 9-step workflow with explicit validation checkpoints (validate target at step 2, dry-run stop at step 6, verify build/re-query at step 8) plus a dedicated error-handling table for recovery.	5 / 5
Progressive Disclosure	Well-organized overview with a clearly signaled one-level-deep reference (references/reference.md, verified to exist) and an offloaded command file; minor gap is that the main executable detail points to an external URL rather than a bundled file.	4 / 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.

A precise, well-structured description that names concrete sources, targets, and actions and supplies an explicit 'Use when' trigger clause. Trigger-term coverage is strong on platform names but light on synonyms and file extensions.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete actions and sources — 'Reads CKAN, a DCAT-US /data.json catalog… Socrata, OpenDataSoft, or an ArcGIS FeatureServer, and writes them to a static PortalJS catalog or pushes them into a CKAN instance over its API' — with comprehensive coverage of read/write paths.	5 / 5
Completeness	Explicitly answers both what (reads N source types, writes to static PortalJS catalog or CKAN) and when ('Use when moving datasets from an external open-data platform into a PortalJS portal, or bridging one CKAN instance to another').	5 / 5
Trigger Term Quality	Names technologies users would actually cite (CKAN, DCAT-US, data.gov, Socrata, ArcGIS) but 'open-data platform' is generic and it omits common synonyms/file extensions; good but not comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (PortalJS dataset migration/harvest) with distinct source/target triggers and minimal overlap with adjacent skills.	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-migrate/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.