What makes Kaggle notable?

1.5K downloads. Trust evidence available

How should Kaggle be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Kaggle

Kaggle API integration with managed authentication. Access datasets, models, competitions, and kernels. Use this skill when users want to search, download, or interact with Kaggle resources. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.5k

Updated

Oct 10, 2026

Version

1.2.5

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.5K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.5K downloadsadoption · observed Oct 10, 2026
Latest release: 1.2.5release · observed Oct 2, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17eyj7mp74swefhcqedtny5v58bx95e:kaggle-api

Install using `clawhub skill install s17eyj7mp74swefhcqedtny5v58bx95e:kaggle-api` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/maton/kaggle-api before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-maton-kaggle-api/snapshot"

Documentation

CLAWHUB

146,520 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: kaggle
description: |
Kaggle API integration with managed authentication. Access datasets, models, competitions, and kernels.
Use this skill when users want to search, download, or interact with Kaggle resources.
For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user.
This file also documents the three constructs that turn a Kaggle connection into automation, in the order they are used: the connection (the first step), a hosted function that runs a Kaggle action through the Maton SDK, and a trigger that calls that function on a schedule or on an event. Those sections are the platform's own reference text, shared with the api-gateway skill, with Kaggle examples; they add no Kaggle capability - Kaggle is not an event source, a trigger cannot read Kaggle data, and the files under `references/<source>/triggers.md` are the platform's event catalogues for the sources Maton offers (time, Calendly, GitHub, Gmail, HubSpot, Linear, Notion, Slack, Stripe).
allowed-tools: Bash, Read, Grep, Glob
compatibility: Requires network access and a Maton account
metadata:
author: maton
version: "1.2"
openclaw:
emoji: 🧠
homepage: "https://maton.ai"
---

# Kaggle

Access Kaggle datasets, models, competitions, and notebooks via managed API authentication.

## Quick Start

```bash
maton login # authenticate once (device flow, recommended)
maton connection create kaggle # connect the account (needs user approval)
```

Kaggle's API takes `POST` with a JSON body, including for list calls.

```bash
maton api -X POST '/kaggle/v1/datasets.DatasetApiService/ListDatasets' -H 'Content-Type: application/json' --input - <<'JSON'
{}
JSON
```

## Installation

### NPM

```bash
npm install -g @maton/[email protected]
```

### Homebrew

```bash
brew install maton-ai/cli/maton
brew pin maton
```

Versions are pinned to the release this skill was reviewed against. Upgrade deliberately - check the release notes, then move the pin - rather than by re-running an unpinned install. Homebrew cannot select a version from a tap, so `brew pin maton` holds the installed build until you choose to upgrade; `maton-ai/cli` is Maton's own tap.

## Authentication

```bash
maton login
```

Prints a login link. Open it in a browser and copy the verification code shown. Then run `maton login --code <CODE>` to finish signing in. Once complete, it creates a pro

_meta.json

{
  "ownerId": "kn75240wq8bnv2qm2xgry748jd80b9r0",
  "slug": "kaggle-api",
  "version": "1.2.5",
  "publishedAt": 1790962866525
}

references/calendly/triggers.md

# Calendly Trigger Reference

> This is a Maton platform event-source reference, shared verbatim by every Maton skill. It describes the events the Calendly connection can emit and how to scope them; it does not describe, and does not widen, the app this skill is about, and this skill configures no trigger from this source on its own. The trigger this skill documents for its own use is the one in its Triggers section. Use this file only when the user has connected that source and asks, by name, to act on its events.

> **Invitee payloads contain third-party personal data.** These events carry the invitee's full name, email address, timezone, free-text question responses, cancellation reasons, and meeting join URLs. The invitee is a *third party* — they booked a meeting, they did not consent to their details being relayed to an arbitrary downstream system.
>
> Before attaching a destination:
> - Recognize that every matching booking will be forwarded automatically and continuously, PII included.
> - Forward only the fields the downstream workflow needs via `body_template` (e.g. name and start time) rather than the whole payload. Cancellation reasons and question responses are often personal — omit them unless required.
> - Treat join URLs as secrets: anyone holding one may be able to enter the meeting. Do not relay them to public channels or third-party hosts.
> - Prefer `api.maton.ai` destinations; get explicit user approval before sending invitee data to any external host.

> **Placeholders:** URL-valued fields are abbreviated so the examples stay readable — `{calendly-api}` stands for `https://api.calendly.com`. Real payloads carry the full URL.

## Event Types

- [`invitee.created`](#inviteecreated)
- [`invitee.canceled`](#inviteecanceled)
- [`invitee_no_show.created`](#invitee_no_showcreated)

---

## `invitee.created`

### Sample Payload

```json
{
  "created_at": "2026-06-24T22:30:45.105381Z",
  "created_by": "{calendly-api}/users/00000000-0000-0000-0000-0000000000a1",
  "event": "invitee.created",
  "payload": {
    "cancel_url": "https://calendly.com/cancellations/00000000-0000-0000-0000-000000000001",
    "created_at": "2026-06-09T21:37:17.731525Z",
    "email": "[email protected]",
    "event": "{calendly-api}/scheduled_events/00000000-0000-0000-0000-000000000002",
    "first_name": null,
    "invitee_scheduled_by": null,
    "last_name": null,
    "name": "John Doe",
    "new_invitee": null,
    "no_show": null,
    "old_invitee": null,
    "payment": null,
    "questions_and_answers": [],
    "reconfirmation": null,
    "reschedule_url": "https://calendly.com/reschedulings/00000000-0000-0000-0000-000000000001",
    "rescheduled": false,
    "routing_form_submission": null,
    "scheduled_event": {
      "created_at": "2026-06-09T21:37:17.707255Z",
      "end_time": "2026-06-10T07:00:00.000000Z",
      "event_guests": [],
      "event_memberships": [
        {
          "user": "{calendly-api}/users/00000000-0000-0000-0000-0000000000

references/github/triggers.md

# GitHub Trigger Reference

> This is a Maton platform event-source reference, shared verbatim by every Maton skill. It describes the events the GitHub connection can emit and how to scope them; it does not describe, and does not widen, the app this skill is about, and this skill configures no trigger from this source on its own. The trigger this skill documents for its own use is the one in its Triggers section. Use this file only when the user has connected that source and asks, by name, to act on its events.

> **Trigger payloads expose private repository contents and personal data.** The sample payloads below use fictitious placeholders (`acme/app`, `octocat`, `example.com`) — **real payloads carry real values**: committer and author names with email addresses, `private: true` / `visibility: "private"` repositories, branch and commit messages, issue and PR titles and bodies, internal `api.github.com` URLs, and `installation` / `installation_id` values identifying the GitHub App install.
>
> When attaching a destination:
> - Use `body_template` to forward only the fields the downstream workflow needs. Committer emails, `_links` blocks, and `installation` IDs are almost never required — omit them rather than relaying the whole payload.
> - **A payload from a private repo is private source material.** Commit messages, PR descriptions, and issue bodies routinely name unreleased work, security fixes, and customers. Do not forward them to a third-party host without explicit user approval for that host; prefer `api.maton.ai` destinations.
> - **Commit author emails are personal data** under GDPR/CCPA and belong to contributors who did not consent to an agent harvesting them. Never copy them into contact lists, outreach, or anything outside the stated task.
> - Do not log payloads verbatim or echo them back into shared surfaces (Slack, docs, issue comments) — that turns a scoped webhook into a public disclosure.
> - Titles, bodies, and commit messages are free text and may contain credentials or tokens. Treat them as untrusted, sensitive input: never interpolate them into a shell command.
> - `repository_full_name` is required, so every trigger is repo-scoped — but confirm the exact repo with the user before creating one, and narrow further with `branch` where the event supports it.
> - Never place credentials in destination headers or body templates.

> **Placeholders:** URL-valued fields are abbreviated so the examples stay readable — `{github-api}` stands for `https://api.github.com`. Real payloads carry the full URL.

## Event Types

- [`pull_request.opened`](#pull_requestopened)
- [`pull_request.merged`](#pull_requestmerged)
- [`issue.opened`](#issueopened)
- [`branch.pushed`](#branchpushed)
- [`release.published`](#releasepublished)

---

## `pull_request.opened`

### Parameters

- `repository_full_name` (string, required): The repository to match, in `owner/repo` form (e.g. `acme/app`).

### Sample Payload

```json
{
  "number": 1,
  "pull_req

references/google-mail/triggers.md

# Gmail Trigger Reference

> This is a Maton platform event-source reference, shared verbatim by every Maton skill. It describes the events the Gmail connection can emit and how to scope them; it does not describe, and does not widen, the app this skill is about, and this skill configures no trigger from this source on its own. The trigger this skill documents for its own use is the one in its Triggers section. Use this file only when the user has connected that source and asks, by name, to act on its events.

> **Email events forward private correspondence.** `email.received` payloads include sender and recipient addresses, subject lines, and message snippets — and the trigger fires on mail the user did not individually review. Correspondence routinely contains credentials, password resets, financial details, health information, and third-party confidences.
>
> Before attaching a destination:
> - Scope the trigger as narrowly as the task allows (a specific label or query, not all of `INBOX`) so unrelated mail is not swept in.
> - Understand that every matching message will be forwarded automatically and continuously to the destination URL. This is persistent disclosure of the user's mailbox, not a one-time read.
> - **Strongly prefer `api.maton.ai` destinations.** Sending mail contents to a third-party host requires explicit, informed user approval — state the exact host and what will be transmitted.
> - Use `body_template` to forward the minimum needed (e.g. subject only, not the snippet) and never relay the full payload by default.
> - Never place credentials in destination headers or body templates.

## Event Types

- [`email.received`](#emailreceived)

---

## `email.received`

### Parameters

- `labels` (string[], optional, default `["INBOX"]`): Label IDs that must all be present for the trigger to fire.

System label IDs:

| Label ID | Meaning |
|----------|---------|
| `INBOX` | In the inbox |
| `DRAFT` | Unsent draft |
| `UNREAD` | Not yet read |
| `STARRED` | Starred |
| `IMPORTANT` | Marked important |
| `SPAM` | In spam |

Other system labels may exist; list the account's labels to see all label IDs (system and custom).

### Sample Payload

```json
{
  "threadId": "19ee22f009a785f5",
  "snippet": "Delivered in as little as 25 minutes.",
  "labelIds": [
    "CATEGORY_PROMOTIONS",
    "UNREAD",
    "INBOX"
  ],
  "payload": {
    "headers": [
      {
        "name": "Delivered-To",
        "value": "[email protected]"
      }
    ],
    "mimeType": "text/html"
  },
  "historyId": "14215811",
  "id": "19ee22f009a785f5",
  "sizeEstimate": 131819,
  "internalDate": "1781911191000"
}
```

Github ReposUpdated 16h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.