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.
npx skills add voxel51/fiftyone-skills --skill fiftyone-sdk-guidancegit clone --depth 1 https://github.com/voxel51/fiftyone-skillsWrote 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.
[](https://agentmods.dev/skills/voxel51/fiftyone-skills/fiftyone-sdk-guidance)<a href="https://agentmods.dev/skills/voxel51/fiftyone-skills/fiftyone-sdk-guidance"><img src="https://agentmods.dev/badge/skills/voxel51/fiftyone-skills/fiftyone-sdk-guidance/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.
<a href="https://agentmods.dev/skills/voxel51/fiftyone-skills/fiftyone-sdk-guidance"><img src="https://agentmods.dev/badge/skills/voxel51/fiftyone-skills/fiftyone-sdk-guidance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 12 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00122 | $0.03037 |
| Opus 5 | $0.00061 | $0.01519 |
| Sonnet 5 | $0.00024 | $0.00607 |
| Haiku 4.5 | $0.00012 | $0.00304 |
Grade A, and why
fiftyone-sdk-guidance scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FiftyOne SDK Guidance
Answers FiftyOne SDK and docs questions by searching live documentation and returning accurate, runnable Python code. Covers two scenarios: direct SDK questions and fallback guidance when no operator or skill exists for the user's goal.
Key Directives
ALWAYS follow these rules, no exceptions:
1. Always search docs first; never answer from training knowledge alone
search_fifty_one_knowledge_sources(query="How do I <user goal> in the FiftyOne Python SDK?")
FiftyOne's API changes frequently. Training knowledge may be outdated. Call search_fifty_one_knowledge_sources (the fiftyone-docs MCP tool) for every FiftyOne-specific question before answering. If it isn't available, see Directive 6 for the fallback order.
The query must be a complete natural-language sentence, not keywords. This tool does semantic retrieval, not keyword search; its own schema requires "a single, well-formed natural-language query" that "must be a complete sentence." query="filter confidence Python" retrieves worse matches than query="How do I filter detections by confidence threshold in the FiftyOne Python SDK?".
2. Return runnable Python code, not pseudocode, and cite your source
All code examples must be complete enough to run. Include imports. Use real FiftyOne API patterns from the search results, not invented method names. Cite the source_url of the result(s) you drew from so the user can verify against live docs.
3. For fallback scenarios, acknowledge the gap explicitly
If the user is attempting to perform an unsupported or limited feature in the FiftyOne Application or operators, state clearly that this is the case and provide a supported route using the Python SDK where available:
"There's no built-in operator for this; here's how to do it with the Python SDK instead."
4. If one search isn't enough, search again with a refined query
SDK questions may need at least 2–3 searches to find the right method, argument, or pattern. Search until you have a concrete answer or have concrete evidence that the feature is not available or included in the documentation.
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.
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.
- 12d ago First seen · 267 lines · 122 tokens per session scan A ee9cdc7db943
fiftyone-sdk-guidance is a skill published in the GitHub repository voxel51/fiftyone-skills (39 stars, last pushed today), licensed Apache-2.0. It adds 122 tokens to every session and 3,037 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
course
A Python helper that displays tutorials, group information, source-code links, and other resources for the python-office library in a terminal.
python-fast-skill
A beginner-friendly guide to core Python concepts, including syntax, data types, functions, classes, errors, files, packages, and concurrency.
triton-cuda-api
A reference for Triton CUDA's core programming functions and their parameters. It explains how to identify program blocks, load and store memory, reduce values, perform dot products, and use atomic updates.
triton-cuda-basics
A beginner guide to writing Triton kernels for CUDA GPUs. It explains how GPU programs split data into blocks and use memory and threads to run work in parallel.
triton-ascend-elementwise
An optimization guide for element-wise operations, where each output value depends on the matching input value. It covers operations such as ReLU, sigmoid, arithmetic, casting, clamping, and copying on Ascend devices.
jupyter-to-marimo
Convert a Jupyter notebook (.ipynb) to a marimo notebook (.py).