Portaljs Add Dataset

OrganizationPopular

datopian

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.

Overview

Publisher	datopian
Repository	`portaljs`
Skill name	`portaljs-add-dataset`
Stars	2.4K
Forks	332
Bundled files	1
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by datopian on GitHub. Read the source before you install it.

Installation

Install the Portaljs Add Dataset AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/datopian/portaljs.git /tmp/portaljs
mkdir -p .claude/skills
cp -r /tmp/portaljs/skills/portaljs-add-dataset .claude/skills/portaljs-add-dataset

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Portaljs Add Dataset in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Portaljs Add Dataset on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Portaljs Add Dataset is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PortalJS — Add Dataset

Overview

Register a dataset in a PortalJS (portaljs-catalog) portal. The skill appends one entry to datasets.json — the single source of truth for the catalog — and routes the underlying bytes by source first, then size: a local file defaults to R2 via Git LFS, a remote URL defaults to passthrough (no copy). No per-dataset page is created; the catalog at /search lists the new entry and the dynamic showcase route pages/[owner]/[slug].tsx renders it automatically at /@<namespace>/<slug>. Supported formats for the showcase preview: CSV, TSV, JSON (array), and GeoJSON.

Prerequisites

A scaffolded PortalJS portal (see portaljs-new-portal) with datasets.json, package.json, and pages/[owner]/[slug].tsx present.
The source data: a local file path or a publicly reachable URL.
For the R2/Git LFS default route: git and git-lfs installed, and an Arc account token (or an OSS Giftless key) to mint a push-scoped LFS credential.
Node 18+ and npm available in the portal directory.

Instructions

The canonical, full step-by-step workflow is .claude/commands/portaljs-add-dataset.md — the single source of truth. Read and follow it when executing. Summary:

Gather input from $ARGUMENTS — source (file path or URL), portal directory (default .), dataset name/slug, description, namespace. If the source is missing, interview the user; never dead-end.
Validate the portal directory: confirm datasets.json, package.json, and pages/[owner]/[slug].tsx exist.
Detect the format from the file extension, URL extension, or Content-Type header (CSV, TSV, JSON array, or GeoJSON); reject anything else and ask for a conversion.
Route the data by source: remote URL → passthrough (default) or adopt into R2 (opt-in); local file → R2 via Git LFS (default) or inline into public/data/ (fenced exception for bundled samples or an OSS-no-R2 fallback).
Append one entry to datasets.json — slug, namespace, name, description, file (the routed path/URL), format — keeping (namespace, slug) unique.
Verify the build with npx next build; fix errors (commonly malformed JSON) before reporting success.
Report the route taken, the manifest change, and the showcase URL.

Output

Modified: datasets.json (one entry appended).
Created (route-dependent): data/<slug>.<ext> tracked via Git LFS (R2 default), or public/data/<slug>.<ext> (inline exception). Nothing is created for remote passthrough.
Verified: npx next build passes.
Result: the dataset appears in /search and renders at /@<namespace>/<slug>.

Error Handling

Symptom	Cause	Fix
Fetch fails for a URL source	Non-200 status or unreachable host	Report the HTTP status and ask the user to confirm the URL is publicly accessible.
"Not a portaljs-catalog portal"	`datasets.json` missing	This is an older single-page template; ask the user how to proceed rather than failing silently.
Unsupported format	Extension/content-type isn't csv/tsv/json/geojson	Ask the user to convert the source before continuing.
`git lfs push` has nothing to stream	`git lfs install --local` never ran, so raw bytes were committed instead of a pointer	Run `git lfs install --local` before `git lfs track`, re-add and re-commit the file.
R2 PUT returns 400	A broad `http.extraHeader` was set and replayed onto the presigned URL	Use the `_jwt` Basic-auth piggyback in `lfs.url` only — never a global `http.extraHeader`.
`(namespace, slug)` clash	Another entry already uses that pair	Ask the user for a different slug or namespace.
`next build` fails	Malformed JSON in `datasets.json`	Print the build log, fix the JSON, rebuild before reporting success.

Examples

Example 1 — Local CSV, default R2 route


/portaljs-add-dataset ./data/co2-emissions.csv namespace=climate

Moves the file into data/, tracks it with Git LFS, pushes it to R2, and appends a manifest entry whose file is the resulting https://data.portaljs.com/... URL.

Example 2 — Remote URL, passthrough (no download)


/portaljs-add-dataset https://example.org/open-data/trade.csv namespace=trade

Detects the format from the response headers and records the URL as-is in datasets.json — no bytes are copied.

Example 3 — GeoJSON adopted into R2


/portaljs-add-dataset https://example.org/boundaries.geojson namespace=reference adopt=true

Downloads the file, then routes it as a local file through the Git LFS → R2 path so it is hosted and versioned under the portal (useful when in-browser range queries are needed).

Example 4 — Bundled sample data, inline exception


/portaljs-add-dataset ./samples/demo.csv namespace=reference

When the portal has no R2 credentials (OSS self-host) or the file is bundled sample data, the skill copies it into public/data/ instead, per the .gitattributes inline fence.

Resources

Full workflow: .claude/commands/portaljs-add-dataset.md
Manifest fields and routing details: references/reference.md
Related skills: portaljs-new-portal, portaljs-add-chart, portaljs-add-map, portaljs-define-schema
Git LFS documentation: https://git-lfs.com/

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/reference.md4 KB

Frequently asked questions

What does the Portaljs Add Dataset AI skill do?

Why use Portaljs Add Dataset on TypingMind?

Because you install it once and use it with any model. Portaljs Add Dataset is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Portaljs Add Dataset in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/datopian/portaljs/tree/main/skills/portaljs-add-dataset. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Portaljs Add Dataset?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Portaljs Add Dataset?

As many as you like. As long as a model supports skills, you can use Portaljs Add Dataset with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Portaljs Add Dataset AI skill free?

Yes. It is published on GitHub by datopian under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

To Spec

mattpocock

CommunityPopular

Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.

To Tickets

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket…

Triage

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

Claude Handoff

Hand the current conversation off to a fresh background agent that picks up the work immediately.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

PortalJS — Add Dataset

Overview

Prerequisites

Instructions

Output

Error Handling

Examples

Example 1 — Local CSV, default R2 route

Example 2 — Remote URL, passthrough (no download)

Example 3 — GeoJSON adopted into R2

Example 4 — Bundled sample data, inline exception

Resources

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now