portaljs-add-resource

Add another file (resource) to an EXISTING dataset in a PortalJS portal — a data dictionary, methodology, or an additional data file. Turns a single-file dataset into a multi-resource one; the showcase renders a section per resource. Use when a dataset needs a second file, such as a data dictionary, methodology doc, or an additional period's data.

Quality

80%

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

71%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.

Well-structured, navigable content with a clear validated workflow and good progressive disclosure that points to a real reference bundle. The main weakness is actionability: the core JSON-manipulation steps are described rather than given as executable commands or code, with detail offloaded to an external file.

Suggestions

Add a concrete snippet showing the exact datasets.json mutation (single-to-multi-resource migration and resource append) so the steps are executable without consulting the external command file.

Provide the literal verification command (e.g. `npx next build 2>&1 | tee build.log`) instead of only describing that output is captured to a log file.

Trim the Overview's restatement of the Frictionless Data Package model, since the description and references already convey it.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence (no explanation of what CSV/JSON or Next.js are), but the Overview re-explains the Frictionless Data Package model and the Instructions section restates workflow that is delegated to the canonical command file, which is mild redundancy.	4 / 5
Actionability	The steps describe what to do at a high level (detect format, fetch, copy into public/data, update datasets.json, run npx next build) but provide no copy-paste-ready code or concrete commands for the actual JSON mutation; execution detail is deferred to the external command file, leaving gaps Claude would have to fill.	3 / 5
Workflow Clarity	A clear six-step sequence is present with an explicit validation checkpoint (npx next build capturing output, fixing malformed JSON before reporting success) and a recovery loop, plus a thorough error-handling table; only minor checkpoint gaps keep it from a 5.	4 / 5
Progressive Disclosure	The SKILL.md is an overview that clearly signals one-level-deep references (the canonical command file on GitHub, references/reference.md which exists as a real bundle file, and sibling skills) with a Resources section for navigation; content is appropriately split rather than inlined.	5 / 5
	Total	16 / 20 Passed

Description

90%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 explicitly states both what the skill does and when to use it, with concrete trigger phrases and a clear niche distinct from sibling dataset-creation skills. Minor specificity gap is the only thing keeping it from a perfect profile.

Dimension	Reasoning	Score
Specificity	Concrete actions are named ('Add another file (resource) to an EXISTING dataset', 'Turns a single-file dataset into a multi-resource one', 'the showcase renders a section per resource') covering the migration and rendering outcomes, but it stops short of the fully comprehensive action list a score 5 would require.	4 / 5
Completeness	It explicitly answers both 'what' (add a resource to an existing dataset, migrate single-to-multi-resource) and 'when' with the explicit 'Use when a dataset needs a second file, such as a data dictionary, methodology doc, or an additional period's data' trigger clause.	5 / 5
Trigger Term Quality	It includes the natural user phrases and synonyms a person would say ('data dictionary', 'methodology', 'additional data file', 'a dataset needs a second file', 'methodology doc') plus concrete file-type triggers, giving comprehensive natural-term coverage.	5 / 5
Distinctiveness Conflict Risk	The niche is clearly scoped to adding a file to an EXISTING PortalJS dataset and is explicitly contrasted with creating a new dataset, giving it distinct triggers and minimal conflict risk with sibling 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-add-resource/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.