New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Inference And Results

by VectorSpaceLab in VectorSpaceLab/AREX-Skill

Use this sub-skill for Ultralytics YOLO predict workflows, source handling, streaming and batching, Results extraction, saving/plotting/cropping, and thread-safe inference.

AGPL-3.0Auto-check passedAI & LLM Engineering

Install Inference And Results

skills CLI
$ npx skills add VectorSpaceLab/AREX-Skill --skill inference-and-results -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install VectorSpaceLab/AREX-Skill inference-and-results --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/ultralytics/sub-skills/inference-and-results .claude/skills/inference-and-results && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
inference-and-results
GitHub stars
331
Token cost
~1.4k tokens
SKILL.md length
534 words
Files
5 (incl. scripts, references)
Skills in repo
157
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Use this sub-skill for Ultralytics YOLO predict workflows, source handling, streaming and batching, Results extraction, saving/plotting/cropping, and thread-safe inference.

  • Works in 6 steps: Pick the entry point: Python from… → Use an explicit local model path when… → Pass predictor overrides as keyword… → …
  • Tasks that involve Computer vision
  • SKILL.md covers Route elsewhere, Start Here, Common Entry Points and Result Routing Checklist, plus 3 more sections
  • Runs Python scripts from its folder

What it does

Inference And Results is an agent skill from VectorSpaceLab/AREX-Skill. Use this sub-skill for Ultralytics YOLO predict workflows, source handling, streaming and batching, Results extraction, saving/plotting/cropping, and thread-safe inference.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/api-reference.md`, `references/troubleshooting.md` and `references/workflows.md`).

It sits in AI & LLM Engineering, covering Computer vision and Data visualization. It works with Python. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Computer vision
  • Tasks that involve Data visualization

Example prompts

  • “/inference-and-results”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Pick the entry point: Python from ultralytics import YOLO for application code, or CLI yolo predict model=... source=... for one-off…
  2. Use an explicit local model path when possible. Names such as yolo26n.pt, yolo26n-seg.pt, or yolo26n-cls.pt may trigger downloads if the…
  3. Pass predictor overrides as keyword arguments in Python or arg=value pairs in CLI, for example imgsz=640, conf=0.25, device=cpu…
  4. Use stream=True for videos, webcams, RTSP/RTMP/TCP streams, screenshots, very large directories, and long source lists; iterate the…
  5. Branch on task-specific Results fields before access. Classification has probs and no boxes; semantic segmentation has semantic_mask and…
  6. Use result.cpu(), result.numpy(), or result.to(...) before handing tensors to non-Torch post-processing or JSON/CSV/dataframe conversion.

What it can do on your machine

Read from SKILL.md and the folder at commit ac3fe1a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Inference And Results loads about 1.4k tokens when it runs, and up to ~6.4k if it reads all its reference files. Until then it costs about 49 tokens; SKILL.md has 534 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its AGPL-3.0 licence (© VectorSpaceLab). 534 words, ~1,384 tokens.

Download SKILL.mdSave it as .claude/skills/inference-and-results/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
inference-and-results
description
Use this sub-skill for Ultralytics YOLO predict workflows, source handling, streaming and batching, Results extraction, saving/plotting/cropping, and thread-safe inference.
disable-model-invocation
true
metadata.disco-role
operating
license
AGPL 3.0

Inference and Results

Use this sub-skill when a task asks an agent to run Ultralytics inference or consume prediction outputs. It covers Python YOLO(...)(source), model.predict(source=...), CLI yolo predict, memory-safe streaming, batch/source choices, task-specific Results extraction, plotting/saving/cropping, and concurrent inference safety.

Route elsewhere

  • Dataset YAMLs, label formats, config overrides, and path validation belong in ../data-and-configuration/.
  • Training, validation metrics, callbacks for train/val, and checkpoint selection belong in ../training-and-validation/.
  • Model family/task selection across YOLO, YOLOWorld, YOLOE, SAM, FastSAM, NAS, and RTDETR belongs in ../model-families-and-tasks/.
  • Exported model formats, ONNX/OpenCV Runtime deployment, and benchmark/deploy tradeoffs belong in ../export-and-deployment/.
  • Tracking IDs, tracker configs, and solution apps belong in ../tracking-and-solutions/.
  • Repository contribution, testing, and maintenance workflows belong in ../repo-development/.

Start Here

  1. Pick the entry point: Python from ultralytics import YOLO for application code, or CLI yolo predict model=... source=... for one-off prediction runs.
  2. Use an explicit local model path when possible. Names such as yolo26n.pt, yolo26n-seg.pt, or yolo26n-cls.pt may trigger downloads if the weights are not present.
  3. Pass predictor overrides as keyword arguments in Python or arg=value pairs in CLI, for example imgsz=640, conf=0.25, device=cpu, save=True, save_txt=True, project=runs/predict, name=exp.
  4. Use stream=True for videos, webcams, RTSP/RTMP/TCP streams, screenshots, very large directories, and long source lists; iterate the generator immediately.
  5. Branch on task-specific Results fields before access. Classification has probs and no boxes; semantic segmentation has semantic_mask and no instance boxes/masks.
  6. Use result.cpu(), result.numpy(), or result.to(...) before handing tensors to non-Torch post-processing or JSON/CSV/dataframe conversion.

Common Entry Points

python
from ultralytics import YOLO

model = YOLO("weights.pt")
results = model.predict(source="image.jpg", imgsz=640, conf=0.25, device="cpu")
for result in results:
    print(result.path, result.speed, result.summary(normalize=True))
python
from ultralytics import YOLO

model = YOLO("weights.pt")
for result in model("video.mp4", stream=True, imgsz=640):
    if result.boxes is not None:
        boxes = result.boxes.xyxy.cpu().tolist()
bash
yolo predict model=weights.pt source=image.jpg imgsz=640 conf=0.25 save=True

The CLI syntax is yolo TASK MODE arg=value; TASK is optional for many models, but MODE is required. Prefer yolo predict model=... source=... unless a task-specific prefix is needed, such as yolo segment predict model=... source=....

Result Routing Checklist

  • Detect: read result.boxes only after if result.boxes is not None.
  • Segment: read both result.boxes and result.masks; retina_masks=True requests masks scaled to the original image shape.
  • Semantic: read result.semantic_mask.data; do not expect result.boxes, result.masks.xy, or per-instance polygons.
  • Classify: read result.probs.top1, top1conf, top5, and top5conf; do not call crop/box code.
  • Pose: read result.boxes plus result.keypoints.xy, xyn, and optional conf.
  • OBB: read result.obb.xywhr or xyxyxyxy; result.obb.xyxy is the enclosing axis-aligned rectangle, not the rotated box.
Show full SKILL.md (178 more words)Show less

Save and Visualization Rules

  • result.plot() returns an annotated image array; by default it is suitable for OpenCV-style BGR handling, while plot(pil=True) returns a PIL image.
  • result.save(filename="out.jpg") writes the annotated image and creates missing parent directories.
  • result.save_txt(path, save_conf=True) supports detection, segmentation, pose, OBB, and classification text outputs, but not semantic segmentation.
  • result.save_crop(save_dir=...) supports box-based detection/segmentation/pose, but not classification, OBB, or semantic segmentation.
  • CLI save=True, save_txt=True, save_conf=True, and save_crop=True create output files under the predictor save directory; set project, name, and exist_ok=True when deterministic output paths matter.
  • Avoid show=True on headless systems; use save=True or result.plot() and encode/display with a terminal or notebook-aware tool instead.

Thread-Safe Inference

Ultralytics predictors use an internal lock during stream_inference, but application-level threading should still avoid sharing mutable model state across threads unless access is serialized. The safest pattern is one YOLO instance per worker thread or process. If memory forces shared-model use, wrap the shared inference function with ultralytics.utils.ThreadingLocked and expect serialized throughput.

References

  • Prediction workflows and source handling: references/workflows.md
  • Results extraction contract: references/api-reference.md
  • Failure diagnosis and fixes: references/troubleshooting.md
  • Download-free result schema helper: scripts/inspect_results_contract.py

© VectorSpaceLab, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in skills/repositories/repo-skills/ultralytics/sub-skills/inference-and-results of VectorSpaceLab/AREX-Skill.

  • SKILL.md
  • references/api-reference.md
  • references/troubleshooting.md
  • references/workflows.md
  • scripts/inspect_results_contract.py

Open the folder on GitHubat commit ac3fe1a

Compare with similar skills

Inference And Results next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Inference And Results compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Inference And Results this skillVectorSpaceLab/AREX-Skill331—~1.4kAutomated safety check: PassAGPL-3.0
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k8 repos~3.3kAutomated safety check: PassMIT
CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs13k7 repos~1.7kAutomated safety check: PassMIT
LLaVA Vision-Language ModelOrchestra-Research/AI-Research-SKILLs13k6 repos~2kAutomated safety check: PassMIT
Hugging Face Vision Trainerhuggingface/skills11k1 repos~7.5kAutomated safety check: PassApache-2.0
Segmentation Sam2SharpAI/DeepCamera3.1k—~594Automated safety check: PassMIT

Similar skills

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 8 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed

  • CLIP Image-Text Matching

    Orchestra-Research/AI-Research-SKILLs

    Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

    13k GitHub starsUsed in 7 repos~1.7k tokens
    AI & LLM EngineeringAuto-check passed

  • LLaVA Vision-Language Model

    Orchestra-Research/AI-Research-SKILLs

    Guide to LLaVA for image chat, visual question answering and captioning, with model sizes, CLI and Gradio usage and multi-turn conversation code.

    13k GitHub starsUsed in 6 repos~2k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Vision Trainer

    huggingface/skills

    Official

    Trains and fine-tunes object detection, image classification and SAM or SAM2 segmentation models on Hugging Face Jobs cloud GPUs and saves the results to the Hub.

    11k GitHub starsUsed in 1 repo~7.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Segmentation Sam2

    SharpAI/DeepCamera

    Interactive click-to-segment using Segment Anything 2 — AI-assisted labeling for Annotation Studio

    3.1k GitHub stars~594 tokensUpdated 24 days ago
    AI & LLM EngineeringAuto-check passed

  • Yolo Detection 2026 Coral Tpu Win Wsl

    SharpAI/DeepCamera

    Google Coral Edge TPU — real-time object detection natively via Windows WSL

    3.1k GitHub stars~1.1k tokensUpdated 24 days ago
    AI & LLM EngineeringAuto-check passed

More from VectorSpaceLab/AREX-Skill

All 157 skills in this repo

  • Agent Lightning

    VectorSpaceLab/AREX-Skill

    Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…

    331 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Agent Tools

    VectorSpaceLab/AREX-Skill

    A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…

    331 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Agents And Awel

    VectorSpaceLab/AREX-Skill

    Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.

    331 GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Agents And Middleware

    VectorSpaceLab/AREX-Skill

    Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…

    331 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Agents Workflows

    VectorSpaceLab/AREX-Skill

    A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.

    331 GitHub stars~500 tokensUpdated 1 mo ago
    Auto-check passed

  • Alphafold3

    VectorSpaceLab/AREX-Skill

    A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.

    331 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Inference And Results

What does Inference And Results do?

Use this sub-skill for Ultralytics YOLO predict workflows, source handling, streaming and batching, Results extraction, saving/plotting/cropping, and thread-safe inference. Inference And Results is an agent skill from VectorSpaceLab/AREX-Skill. Use this sub-skill for Ultralytics YOLO predict workflows, source handling, streaming and batching, Results extraction, saving/plotting/cropping, and thread-safe inference.

When should I use Inference And Results?

Inference And Results fits situations like: tasks that involve Computer vision; tasks that involve Data visualization.

How do I install Inference And Results in Claude Code?

Run `npx skills add VectorSpaceLab/AREX-Skill --skill inference-and-results -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/ultralytics/sub-skills/inference-and-results in VectorSpaceLab/AREX-Skill) into .claude/skills/inference-and-results in your project. Claude Code loads it when a task matches its description.

How do I install Inference And Results in Codex?

Run `npx skills add VectorSpaceLab/AREX-Skill --skill inference-and-results -a codex`. Or copy the skill folder (skills/repositories/repo-skills/ultralytics/sub-skills/inference-and-results in VectorSpaceLab/AREX-Skill) into .agents/skills/inference-and-results in your project. Codex loads it when a task matches its description.

Can I use Inference And Results in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VectorSpaceLab/AREX-Skill --skill inference-and-results -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/inference-and-results, .gemini/skills/inference-and-results, .github/skills/inference-and-results and .opencode/skills/inference-and-results in your project.

What does Inference And Results need to run?

Going by SKILL.md and its folder, Inference And Results needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Inference And Results access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Inference And Results safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Inference And Results use?

Inference And Results is published under the AGPL-3.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Inference And Results use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5k tokens, read only when the agent opens those files.

What are the alternatives to Inference And Results?

Skills that share tags, products or a category with Inference And Results: Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars), LLaVA Vision-Language Model (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Hugging Face Vision Trainer (huggingface/skills, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Inference And Results?

VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 331 GitHub stars. The repository holds 157 skills in this directory. The repository was last updated on September 3, 2026.

Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.