Skills fiftyone-embeddings-visualization
📦
fiftyone-embeddings-visualization
Content revision r1 Safe ⚙️ External commands🌐 Network access
Visualize FiftyOne Embeddings
Image datasets can hide clusters, outliers, and label problems. This skill guides Claude, Codex, and Claude Code through FiftyOne embedding visualizations.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "fiftyone-embeddings-visualization" from https://skillstore.io/skills/adonaivera-fiftyone-embeddings-visualization.md and its manifest at https://skillstore.io/api/skills/adonaivera-fiftyone-embeddings-visualization/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "fiftyone-embeddings-visualization". Visualize my product-images dataset with UMAP.
Expected outcome:
- The dataset context is set to product-images.
- Existing CLIP embeddings were found and used for a 2D visualization named exploration.
- Open the FiftyOne App and choose the exploration brain key in the Embeddings panel.
Using "fiftyone-embeddings-visualization". Find likely outliers in my wildlife dataset.
Expected outcome:
- A uniqueness score was computed for the dataset.
- The highest uniqueness samples are sorted first for review.
- Isolated points in the Embeddings panel are good candidates for annotation checks.
Using "fiftyone-embeddings-visualization". Compare ground truth and predictions in embedding space.
Expected outcome:
- A 2D embedding view was prepared for model review.
- Color by ground truth to inspect class structure, then color by predictions to compare model behavior.
- Regions where colors diverge are likely places to inspect prediction errors.
Security Audit
Safev8 • 7/5/2026 Open versioned report
All static command findings are Markdown code fences, inline parameter names, or FiftyOne MCP examples rather than executable Ruby or shell backticks. The network findings are localhost app directions and public documentation links, and no prompt injection, exfiltration intent, or malicious behavior was found.
1
Files scanned
531
Lines analyzed
0
Review items
0
False positives ignored
Risk Factors
⚙️ External commands (77)
SKILL.md:22 SKILL.md:30-32 SKILL.md:32-36 SKILL.md:36-38 SKILL.md:38-42 SKILL.md:42-48 SKILL.md:48-52 SKILL.md:52-63 SKILL.md:63-66 SKILL.md:66-68 SKILL.md:68-73 SKILL.md:73-79 SKILL.md:79-82 SKILL.md:82-92 SKILL.md:92-95 SKILL.md:95-101 SKILL.md:101-106 SKILL.md:106-110 SKILL.md:110-115 SKILL.md:115-126 SKILL.md:126-129 SKILL.md:129-130 SKILL.md:130-131 SKILL.md:131-132 SKILL.md:132 SKILL.md:133 SKILL.md:136-137 SKILL.md:137-138 SKILL.md:138-139 SKILL.md:139-144 SKILL.md:144-165 SKILL.md:165-168 SKILL.md:168 SKILL.md:169-170 SKILL.md:170-177 SKILL.md:177-179 SKILL.md:179 SKILL.md:182-187 SKILL.md:187-196 SKILL.md:196-204 SKILL.md:204-215 SKILL.md:215-227 SKILL.md:227-237 SKILL.md:237-240 SKILL.md:240-242 SKILL.md:242-250 SKILL.md:250-251 SKILL.md:251-252 SKILL.md:252-253 SKILL.md:253-254 SKILL.md:254-258 SKILL.md:258 SKILL.md:262-263 SKILL.md:263-264 SKILL.md:264-265 SKILL.md:265-271 SKILL.md:271-293 SKILL.md:293-297 SKILL.md:297-338 SKILL.md:338-342 SKILL.md:342-380 SKILL.md:380-384 SKILL.md:384-420 SKILL.md:420-424 SKILL.md:424-458 SKILL.md:458-464 SKILL.md:464-468 SKILL.md:468 SKILL.md:472 SKILL.md:474-475 SKILL.md:475-477 SKILL.md:477-478 SKILL.md:478 SKILL.md:479 SKILL.md:484-485 SKILL.md:485-498 SKILL.md:498
🌐 Network access (9)
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/adonaivera-fiftyone-embeddings-visualization/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/adonaivera-fiftyone-embeddings-visualization?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/adonaivera-fiftyone-embeddings-visualization?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/adonaivera-fiftyone-embeddings-visualization/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/adonaivera-fiftyone-embeddings-visualization.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
AdonaiVera. (2026). fiftyone-embeddings-visualization security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/adonaivera-fiftyone-embeddings-visualization/audits/8BibTeX citation
@techreport{adonaivera-adonaivera-fiftyone-embeddings-visualization-2026,
author = {AdonaiVera},
title = {fiftyone-embeddings-visualization security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/adonaivera-fiftyone-embeddings-visualization/audits/8},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "fiftyone-embeddings-visualization security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
- name: "AdonaiVera"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/adonaivera-fiftyone-embeddings-visualization/audits/8"
identifiers:
- type: other
value: "skillstore:adonaivera-fiftyone-embeddings-visualization:audit:8"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
87
Content
72
Community
78
Spec Compliance
What You Can Build
Explore Dataset Structure
Visualize image clusters, review dense regions, and find isolated samples before labeling or quality review.
Diagnose Model Errors
Compare ground truth and prediction patterns in embedding space to locate confusing classes and likely mistakes.
Review Representation Quality
Compare CLIP, DINOv2, ResNet, or MobileNet embeddings with UMAP, t-SNE, or PCA views.
Try These Prompts
Visualize a Dataset
Use the FiftyOne embeddings visualization workflow for dataset my-dataset. Check for existing embeddings, create a 2D UMAP view if needed, and tell me how to open it in the app.
Find Outliers
Analyze dataset my-dataset for unusual images. Compute embeddings if needed, create an outlier-focused visualization, and explain where I should inspect isolated samples.
Compare Classes
Create an embedding visualization for my-dataset and guide me through coloring points by ground truth and predictions. Highlight signs of class overlap or label issues.
Compare Embedding Models
For my-dataset, compare CLIP and DINOv2 embedding visualizations. Reuse existing fields when available, choose suitable reduction methods, and summarize the visual differences.
Best Practices
- Discover available operators and schemas before choosing parameters.
- Reuse existing embedding fields when possible to avoid repeated computation.
- Start with a subset for very large datasets before processing every sample.
Avoid
- Do not filter samples by brain key when opening the Embeddings panel.
- Do not assume UMAP is available when umap-learn is not installed.
- Do not compute new embeddings when a suitable field already exists.
Frequently Asked Questions
What does this skill help me visualize?
It helps visualize image samples as 2D points based on model embeddings.
Does it require FiftyOne?
Yes. It requires a running FiftyOne MCP server and the FiftyOne App.
Which embedding models does it suggest?
It suggests CLIP, DINOv2, ResNet50, and MobileNet depending on the analysis goal.
Can it find outliers?
Yes. It can compute uniqueness scores and show isolated points in an embedding view.
Can it use existing embeddings?
Yes. The workflow checks for existing embedding fields before computing new ones.
What happens if UMAP is not installed?
The workflow can ask before installing umap-learn, or use t-SNE or PCA instead.
Developer Details
Author
AdonaiVeraLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
6eec4a59f63ff83440a84c18d1aef79743bc714e
Maintenance freshness
7/18/2026
Usage
5 downloads · 320 views
File structure
📄 SKILL.md