Skip to content
cccskills
FreePublished on GitHubEnglish overview

library-curator

Find images, logos, and screenshots already stored in OD Library and reuse them in the current project. Select assets by their metadata, copy them into the project, and connect the returned file paths to the page.

OriginalShow the original description

Search the OD Library (the global asset registry) and apply matching assets into the current project mid-task. Use when the user asks to reuse an image they captured/uploaded earlier, "pull a logo/screenshot from my library", or to find and drop a stored asset into the page being built.

AI rating90/ 100See how to install

Good for

  • Reuse a screenshot captured earlier
  • Insert a stored logo into a page
  • Find a hero image in an existing library
  • Add uploaded or agent-generated assets to a project

Overview

What it does

library-curator finds assets saved in OD Library, brings them into the current project, and incorporates them into a page. It can reuse images saved with OD Clipper, manually uploaded assets, agent-generated media, and design-system materials. It compares dimensions, titles, and sources in search results to choose an asset. After copying it into the project, it uses the returned project-relative path in HTML or CSS.

When it helps

Use it when you want to reuse a screenshot or logo saved earlier without uploading it again. It also helps when you want to ask for a previously used hero image during page creation, or prefer assets you already have over newly generated media.

Example requests

  • “Find the screenshot I captured earlier and add it to this page.”
  • “Import the logo from my library and place it on the page.”
  • “Find saved images that could work as a blue background.”

Notes

It requires the OD runtime and uses the environment-provided OD_TOOL_TOKEN for searching and importing. Without an embedding model configured, searches use keywords and metadata. If no asset is found, the workflow switches to media generation without inventing a file path.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?
AGoodIt explicitly identifies when to search saved assets and how they are brought into the current project.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?
AGoodIt provides search and apply API input/output examples and four steps from asset selection to relative-path use.
SafetyAre sending data, deleting files, and running commands disclosed?
AGoodIt specifies the OD_TOOL_TOKEN source, target project, asset-copy operation, and use of returned paths.
Easy setupDoes it need few tools or API keys, and are they documented?
BPartly lackingIt explains injected OD_TOOL_TOKEN authentication and behavior without an embedding model, but gives no OD setup steps.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 20, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (1)

  • SKILL.md2.2 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

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.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

8-bit-orbit-video-template

FreeSummaryAI rating 90

Create a three-scene video composition in a retro pixel style using a Hyperframes HTML template. Customize titles, labels, and colors while preserving scene transitions, short scene durations, and repeatable animation timing.

  • Create a retro pixel presentation video
  • Customize a three-scene video template
  • Preview scene transitions and motion in HTML
nexu-io/open-design103.1KUpdated Oct 22, 2026

ad-creative

FreeSummaryAI rating 80

Create and revise headlines, descriptions, and main text for paid social and search ads. Use it to develop ad copy options and refine wording through repeated rounds of revision.

  • Drafting headlines for paid social ads
  • Creating descriptions for search ads
  • Revising the main text of an ad
nexu-io/open-design103.1KUpdated Oct 22, 2026

after-hours-editorial-template

FreeSummaryAI rating 80

Create a three-page editorial motion sequence with dark backgrounds, serif typography, staged text reveals, and chapter transitions. The result is a single HTML file suited to fashion-inspired storytelling and short visual presentations.

  • Creating a fashion-inspired motion presentation
  • Presenting a short story across three pages
  • Applying existing brand rules to a dark editorial sequence
nexu-io/open-design103.1KUpdated Oct 22, 2026

agent-browser

FreeSummaryAI rating 100

Inspect and test web pages through a browser automation command-line tool. Navigate, click, enter text, capture screenshots, and extract page details, with a focus on checking local OpenDesign previews and reviewing web app quality.

  • Checking local OpenDesign previews
  • Testing clicks and text entry in web apps
  • Capturing page or element screenshots
nexu-io/open-design103.1KUpdated Oct 22, 2026

ai-music-album

FreeSummaryAI rating 80

Plan an AI music album from its concept through lyric drafts, track order, and export. Intended for independent album experiments and brand soundtracks, with the full production workflow provided through a separately installed upstream bundle.

  • Planning an experimental independent album
  • Drafting lyrics around an album concept
  • Deciding the running order of tracks
nexu-io/open-design103.1KUpdated Oct 22, 2026

algorithmic-art

FreeSummaryAI rating 80

Create generative art, or images made with programmed rules, using p5.js. Fixed random seeds make each rendering reproducible, supporting procedural posters, still images that suggest motion, and studies of artistic frame composition.

  • Posters generated with programmed rules
  • Still images that suggest motion
  • Studies of artistic frame composition
nexu-io/open-design103.1KUpdated Oct 22, 2026

See all skills by nexu-io

Report a problem with this skill