fiftyone-troubleshoot

fiftyone-troubleshoot is a skill for Claude Code from voxel51/fiftyone-skills. It costs 59 tokens per session (4,058 once invoked), scanned C, original, Apache-2.0.

A diagnostic process for common FiftyOne problems. FiftyOne is a tool for viewing and managing machine-learning datasets, including images and videos.

In plain words
What is it for?
Use it to investigate these recurring FiftyOne issues, review a proposed fix, and apply it only after approval.
Why use it?
It helps identify likely causes of missing datasets, app startup failures, database errors, video issues, notebook connection problems, or missing operators before applying a fix.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fiftyone plugin — 18 skills, 2 commands, 1 MCP server shipped together

Good fit Use it to investigate these recurring FiftyOne issues, review a proposed fix, and apply it only after approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/voxel51/fiftyone-skills/fiftyone-troubleshoot
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add voxel51/fiftyone-skills --skill fiftyone-troubleshoot
Clone the repo
git clone --depth 1 https://github.com/voxel51/fiftyone-skills

Made for: Claude Code.

Or install fiftyone, the plugin that ships this one along with the rest of its 18 skills, 2 commands, 1 MCP server.

Its marketplace also offers this one on its own, as the plugin fiftyone-troubleshoot/plugin install fiftyone-troubleshoot after adding the marketplace above.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fiftyone-troubleshoot

README.md
[![agentmods](https://agentmods.dev/badge/skills/voxel51/fiftyone-skills/fiftyone-troubleshoot/github.svg)](https://agentmods.dev/skills/voxel51/fiftyone-skills/fiftyone-troubleshoot)
Your own site
<a href="https://agentmods.dev/skills/voxel51/fiftyone-skills/fiftyone-troubleshoot"><img src="https://agentmods.dev/badge/skills/voxel51/fiftyone-skills/fiftyone-troubleshoot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fiftyone-troubleshoot

Your own site · 80×15
<a href="https://agentmods.dev/skills/voxel51/fiftyone-skills/fiftyone-troubleshoot"><img src="https://agentmods.dev/badge/skills/voxel51/fiftyone-skills/fiftyone-troubleshoot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,058 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.04058
Opus 5 $0.00030 $0.02029
Sonnet 5 $0.00012 $0.00812
Haiku 4.5 $0.00006 $0.00406

Measured 13d ago against content hash 75ef221b923f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

fiftyone-troubleshoot scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.fiftyone/var/ # only after user confirms
skills/fiftyone-troubleshoot/SKILL.md · 533 lines

How it starts

The opening of the file, as written. The whole thing — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FiftyOne Troubleshoot

Overview

Diagnose and fix common FiftyOne pain points. Match the user's symptom to the Issue Index, explain the root cause and proposed fix, get approval, then apply.

Shell commands in this skill are written for macOS/Linux. On Windows (non-WSL), adapt using PowerShell equivalents or use WSL.

Designed to grow: add new issues at the bottom as they are encountered.

Prerequisites

  • FiftyOne installed: pip install fiftyone
  • MCP server running (optional, for plugin-related fixes)

Key Directives

1. Always explain, propose, and confirm before acting

NEVER run a fix without first:

  1. Explaining what is wrong and why
  2. Describing what the fix will do
  3. Asking the user to confirm: "Should I apply this fix?"

Wait for explicit user confirmation before executing anything that modifies files, config, or data.

2. Never touch user datasets — FiftyOne is the source of truth

  • Except when given explicit and direct instructions by the user:
    • NEVER modify, edit, delete, or clone user datasets as part of troubleshooting
    • NEVER call fo.delete_dataset()
    • NEVER truncate, wipe, or alter dataset contents or sample fields to diagnose an issue
  • Use FiftyOne's read-only API to inspect state: fo.list_datasets(), fo.load_dataset(), len(dataset), dataset.get_field_schema() — these are safe
  • FiftyOne's state (datasets, fields, brain runs) is the ground truth; read it, never rewrite it to "fix" a problem

3. Never directly manipulate MongoDB

  • NEVER use pymongo, db.drop_collection(), or raw MongoDB shell commands
  • All data operations must go through the FiftyOne Python API

4. Never modify config or files silently

  • NEVER change database_uri, database_name, or any config file without showing what will change and getting approval
  • NEVER append to shell profiles (.zshrc, .bash_profile, virtualenv activate) without showing the exact line change and getting explicit user confirmation to apply

Read the full file on GitHub · 533 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 533 lines · 59 tokens per session scan C 75ef221b923f

Subscribe to this mod's changes

fiftyone-troubleshoot is a skill published in the GitHub repository voxel51/fiftyone-skills (39 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 4,058 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens