New to Claude Skills? Learn how to install them →

nexu-io on GitHub

Library Curator

Free

Effortlessly reuse assets from your OD Library.

Get this skill

Free · Opens the source repo

What Library Curator does

The Library Curator skill allows developers and designers to seamlessly integrate assets from their existing OD Library into their current projects without the need for re-uploading. This is particularly useful when users want to reference images they have previously captured or uploaded, such as logos or screenshots. By streamlining the process of asset retrieval, this skill enhances productivity and ensures that users can maintain consistency in their design work by utilizing their own media rather than generating new assets.

This skill operates through two main API endpoints: search and apply. The search function allows users to query their library for specific assets based on keywords and asset types. For example, a user could search for a "blue hero background" and receive a list of relevant images. The skill employs a straightforward filtering mechanism that ranks results based on metadata, enabling users to quickly find the best fit for their needs.

Once an asset is selected, the apply function copies it into the current project directory, providing a relative path that can be directly referenced in the project's HTML or CSS. This eliminates the guesswork involved in asset management and ensures that the paths generated are valid and usable. The skill is designed to enhance the workflow of those who frequently utilize their own media in design projects, making it a valuable tool for both individual creators and teams.

In summary, Library Curator is ideal for users who prefer to leverage their existing media assets, allowing for efficient project development and design consistency. It is particularly suited for designers and developers who regularly reference previously used images and want to streamline their workflow without unnecessary uploads or complications.

When to use it

Use this skill when you want to quickly pull in images or media from your existing OD Library during project development.

When not to use it

This skill is not suitable for scenarios where you need to create new assets or when you do not have any existing media in your library.

What you can build with it

Pulling a logo from the library

When a user needs to add their logo to a project, they can quickly search their library and apply it without re-uploading.

Incorporating a previously used image

If a user wants to reuse a screenshot they captured earlier, they can search for it in their OD Library and insert it directly.

Finding design system assets

When building a new page, a designer can search for design system components stored in their library to maintain consistency.

How to install Library Curator

View source

1. Install with the skills CLI

npx skills add nexu-io/open-design/library-curator --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by nexu-io

library-curator

Reuse assets that already live in the user's OD Library — images captured with the OD Clipper, manual uploads, agent-generated media, and design-system material — without asking the user to re-upload them.

When to use

  • The user references an asset they already have ("the screenshot I clipped", "my logo", "that hero image from earlier").
  • You need an image for the page you're building and the user prefers their own library over freshly generated media.

Tools (tool-token track)

Both endpoints authenticate with the run's tool token (OD_TOOL_TOKEN, injected by the daemon) and operate on the project the run belongs to.

Search

POST /api/tools/library/search

{ "query": "blue hero background", "kind": "image", "limit": 20 }

Returns { "results": [{ "asset": { "id": "...", "kind": "image", "sourceTitle": "...", "width": 1600, "height": 900, "sources": [...] }, "score": 0 }], "semantic": false }.

semantic: false means keyword/metadata matching (no embedding model configured). Filter and rank the results yourself from the asset metadata.

Apply

POST /api/tools/library/apply

{ "assetId": "<id from search>", "dir": "assets" }

Copies the asset into the project (default subdir library/, or the dir you pass) and returns { "relPath": "assets/<hash>.png" }. Reference that relPath from the HTML/CSS you write (e.g. <img src="assets/ab12cd34ef.png">).

Recipe

  1. Search with a tight query for the kind you need.
  2. Pick the best result by dimensions / title / source.
  3. Apply it to get a project-relative path.
  4. Wire that path into the artifact you're editing.

If search returns nothing, fall back to media generation rather than guessing a path — never invent a relPath that apply did not return.

Frequently asked questions about Library Curator

Similar skills