Skip to main content
skill CX Codex

publish — Claude Code skill: publish Harbor tasks and datasets

Publishes Harbor tasks and datasets to the registry. Checks auth, task identifiers, and walks through every upload step.

Apache-2.0 202 installs ★ 7,321 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add harbor-framework/harbor --skill publish -a claude-code
Open on GitHub

What publish does

The skill verifies login with uvx harbor auth status, then ensures each task has an identifier like <org>/<name> in task.toml. Missing identifiers trigger uvx harbor task update with the --org flag. For datasets, it first initializes the manifest with uvx harbor dataset init, then adds tasks from local folders or the registry using uvx harbor dataset add. Before publishing a dataset, it syncs digests of changed tasks with uvx harbor sync.

Publishes privately by default; --public makes the task or dataset visible to everyone. The latest tag is automatic; add more with -t. After publishing, change visibility on hub.harborframework.com or with uvx harbor task visibility. Run a published dataset with uvx harbor run -d "<org>/<dataset>@v1.0".

What it helps with

  • upload a Harbor task to the registry with org identifier check
  • publish a dataset with a custom metric and tasks from multiple folders
  • sync local task digests before republishing a dataset
  • tag a release and make it public in one publish command

Example prompts for the agent

  • Publish the task in tasks/simple-math to the Harbor registry
  • Create a dataset myorg/benchmark-2024 with description "Agent tests" and add tasks from tasks/
  • Sync the dataset digests and publish it with tag v2.1 and --public

How to install publish

1Skills CLI (Vercel)

npx skills add harbor-framework/harbor --skill publish -a claude-code

2Manually: put the files in place

~/.claude/skills/publish/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/publish/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about publish

How to install publish in Claude Code?

Run npx skills add harbor-framework/harbor --skill publish -a claude-code; the skill will appear in ~/.claude/skills/publish/SKILL.md.

What does the publish skill do?

Guides you through publishing Harbor tasks and datasets: checks auth and identifiers, syncs digests, and uploads to the registry with tags and visibility settings.

What do I need to publish a Harbor dataset?

Initialize the manifest with uvx harbor dataset init, add tasks with uvx harbor dataset add, sync digests with uvx harbor sync, then run uvx harbor publish.

Source text

SKILL.md · Apache-2.0
---
name: publish
description: Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.
---

Help the user publish a Harbor task or dataset to the registry. Walk them through each step, checking prerequisites and confirming before running publish commands.

All commands use `uvx harbor` so the user does not need to install the CLI globally.

## Prerequisites

1. **Auth**: Ensure the user is logged in by running `uvx harbor auth status`. If not logged in, prompt them to run `uvx harbor auth login`.

2. **Task identifiers**: All tasks must have a `[task]` section in their `task.toml` with a name like `<org>/<name>`. If missing, run:
   ```bash
   uvx harbor task update "<path/to/task>" --org "<org>"
   ```
   To update all tasks in a directory:
   ```bash
   uvx harbor task update "<path/to/tasks>" --org "<org>" --scan
   ```

## Publishing a task

```bash
uvx harbor publish "<path/to/task>"
```

Publish multiple tasks or all tasks in a directory:
```bash
uvx harbor publish "<path/to/task-a>" "<path/to/task-b>"
uvx harbor publish "<path/to/tasks>"
```

## Publishing a dataset

### 1. Initialize the dataset manifest (if no `dataset.toml` exists)

```bash
uvx harbor dataset init "<org>/<dataset>" \
  --description "<description>" \
  --author "Jane Doe <[email protected]>"
```

Add `--with-metric` if the user needs a custom metric script. If omitted, the dataset uses the default metric (average reward across tasks, with missing values treated as 0).

**Auto-add behavior:** If `dataset init` is run in a directory that already contains tasks, those tasks are automatically added to the manifest. After init, **ask the user if they want to add additional tasks** — either from the Harbor registry or from other local folders.

### 2. Add additional tasks and files (optional)

```bash
cd "<path/to/dataset>"
uvx harbor dataset add "<path/to/task-a>" "<path/to/task-b>"   # local tasks from elsewhere
uvx harbor dataset add "<path/to/folder>" --scan                 # all tasks in another folder
uvx harbor dataset add org/task-name                             # published tasks from registry
uvx harbor dataset add org/dataset-name                          # all tasks from a published dataset
uvx harbor dataset add metric.py                                 # metric file (same dir as dataset.toml)
uvx harbor dataset remove "<org>/<task-name>"                     # remove a task
```

Specific versions: `org/task@tag`, `org/task@revision`, or `org/task@sha256:<hash>`.

### 3. Sync digests (if tasks/metrics changed since last publish)

```bash
uvx harbor sync
uvx harbor sync --upgrade   # also upgrade remote tasks to latest
```

### 4. Publish the dataset

```bash
uvx harbor publish "<path/to/dataset>"
```

`uvx harbor publish` automatically refreshes digests of local tasks in the dataset directory.

## Publish options (tasks and datasets)

- `-t / --tag`: add tags (repeatable). `latest` is always included.
- `-c / --concurrency`: control upload concurrency.
- `--public`: make public (private by default).
- `--no-tasks` (datasets only): skip publishing tasks in the dataset directory.

Example:
```bash
uvx harbor publish "<path>" -t v1.0 --public
```

## After publishing

- Visibility can be changed later with `uvx harbor task visibility` / `uvx harbor dataset visibility` or on https://hub.harborframework.com/.
- Run a published dataset with:
  ```bash
  uvx harbor run -d "<org>/<dataset>@v1.0" -a "<agent>" -m "<model>"
  ```

© harbor-framework · Apache-2.0 · harbor-framework/harbor

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set3

Project sponsors

Companies that keep this analytics open