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

Official agent skill

TAO Detection KPI Analysis

by NVIDIA in NVIDIA/skills

Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.

OfficialApache-2.0Auto-check: notesAI & LLM Engineering

Install TAO Detection KPI Analysis

skills CLI
$ npx skills add NVIDIA/skills --skill tao-analyze-detection-kpi -a claude-code

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

GitHub CLI
$ gh skill install NVIDIA/skills tao-analyze-detection-kpi --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/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tao-analyze-detection-kpi .claude/skills/tao-analyze-detection-kpi && 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
tao-analyze-detection-kpi
GitHub stars
3.6k
Token cost
~2.7k tokens
SKILL.md length
1,173 words
Files
10 (incl. scripts, references, assets)
Skills in repo
390
Repo updated
First seen
Licence
Apache-2.0

At a glance

Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.

  • Works in 4 steps: Verify Docker access → Resolve and pull the data-services image… → Validate the spec → …
  • An object detection workflow needs per-class mAP after inference
  • SKILL.md covers Inputs, Quick Start, Generate A Spec and Preflight, plus 3 more sections
  • Runs Python scripts from its folder; calls docker and python3

What it does

Object detection predictions are scored against ground truth by running the container's analytics kpi_analyze command with an absolute path to a YAML spec. For each class it computes true and false positives and negatives, precision, recall, accuracy and average precision at a fixed IoU threshold, and writes the results to kpi_calc.csv in the results directory. It does not run inference, so inference annotations must already exist.

The spec needs an input format of KITTI or COCO in uppercase, a list of KPI sources each with an image directory, ground truth annotation path and inference annotation path, a class-mapping YAML whose values are lists of aliases, and a results directory. Optional fields set the IoU threshold (default 0.5), the confidence threshold, the number of recall points and the minimum box width to ignore. A bundled default spec and example mapping carry the recommended values, and a verify script checks a spec.

Several pitfalls are called out: a bare string in the class mapping silently zeroes every metric, a confidence threshold of 0.0 is only safe on the pinned container build, and using 11 or 101 recall points or a different ignore width gives numbers that are not comparable with the reference pipeline. The skill ships benchmark and eval files and allows only the Read and Bash tools.

When your agent uses it

  • An object detection workflow needs per-class mAP after inference
  • Scoring predictions against ground truth annotations in KITTI or COCO format
  • Checking a KPI analyze spec before running it in the TAO container

Example prompts

  • “Run KPI analysis on my detection predictions in ./inference_out against the ground truth in ./labels.”
  • “Compute per-class mAP for the COCO annotations and write the CSV to ./results.”
  • “Check my kpi_analyze.yaml for mistakes before I run it.”

Requirements

  • Docker with nvidia-container-toolkit
  • The TAO data-services container pinned in versions.yaml
  • Inference annotations produced by an earlier detection step
  • Compatibility (from SKILL.md): Requires docker, nvidia-container-toolkit, and the TAO data-services container pinned in versions.yaml.
  • Pre-approved tools (allowed-tools): Read, Bash

Workflow steps

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

  1. Verify Docker access
  2. Resolve and pull the data-services image if needed
  3. Validate the spec
  4. Confirm RUN_ROOT contains the spec, every image_dir, both annotation paths per source, the mapping file, and the results directory. Mount…

What it can do on your machine

Read from SKILL.md and the folder at commit 14a98ae. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

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

    Shell commands in SKILL.md call:

    • docker
    • python3

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

  • Network

    No URLs in SKILL.md. Its commands use docker, which can reach the network depending on how they are called.

    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.

  • Compatibility

    Requires docker, nvidia-container-toolkit, and the TAO data-services container pinned in versions.yaml.

    From compatibility in the SKILL.md frontmatter.

Context cost

TAO Detection KPI Analysis loads about 2.7k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 106 tokens; SKILL.md has 1,173 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~106
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.8k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Bash

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 NVIDIA/skills at commit 14a98ae, republished under its Apache-2.0 licence (© NVIDIA). 1,173 words, ~2,655 tokens.

Download SKILL.mdSave it as .claude/skills/tao-analyze-detection-kpi/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
tao-analyze-detection-kpi
description
Run TAO Data Services KPI analysis for object detection, comparing inference annotations against ground truth to compute per-class TP/FP/FN/TN, precision, recall, accuracy, and AP at a fixed IoU. Use when an object detection workflow needs per-class mAP reported after inference, or when the user asks to "run KPI analyze", "compute detection mAP", or "score my OD predictions against ground truth".
allowed-tools
Read, Bash
compatibility
Requires docker, nvidia-container-toolkit, and the TAO data-services container pinned in versions.yaml.
license
Apache-2.0
metadata.author
NVIDIA Corporation
metadata.version
0.1.0
tags
tao, data, kpi, object-detection, mAP, analytics

TAO Analyze Detection KPI

Use this skill to run TAO Data Services KPI analysis for object detection. The skill compares inference annotations against ground truth over one or more KPI sources and writes a per-class metrics CSV. It does not run inference; an upstream step must produce the inference annotations first.

The container entrypoint is:

bash
analytics kpi_analyze -e /absolute/path/to/kpi_analyze.yaml

Inputs

The user provides either a finished spec or the paths to fill into the template.

Required spec fields:

FieldMeaning
data.input_formatKITTI or COCO. Uppercase — see Pitfalls.
data.kpi_sourcesList of sources. Each entry requires image_dir, ground_truth_ann_path, and inference_ann_path; all three are asserted at startup.
data.mappingPath to a class-mapping YAML: a list of single-key dicts whose value is a LIST of aliases. See assets/example_mapping.yaml — a bare string here silently zeroes every metric.
results_dirOutput directory for kpi_calc.csv.

Common optional fields. The Default column is what TAO DS uses when the field is absent; assets/default_kpi_analyze.yaml already carries the recommended value for each, so filling the template needs none of them changed:

FieldDefaultMeaning
kpi.iou_threshold0.5IoU at or above which a prediction counts as a true positive.
kpi.conf_threshold0.5Predictions below this are dropped. The template uses 0.0, which keeps the whole PR curve so a threshold can be swept afterwards without re-running inference. On the pinned image that is safe: unmatched ground truth carries a -1.0 sentinel and lands in FN at any threshold. On a build predating that fix, 0.0 scored every missed box as a true positive — TP became the ground-truth count and FN was always 0 — so use a small positive value there.
kpi.num_recall_points11Recall points for the interpolated PR curve. The template keeps 11 (VOC-style), matching the reference ITS pipeline. 101 selects COCO-standard sampling and reports different numbers for the same detections.
kpi.ignore_sqwidth0Boxes narrower than this are ignored. The template uses 40, matching the reference ITS pipeline, which never counted boxes below that. 0 scores small objects the reference excluded, so the two are not comparable.
kpi.filterfalseEnable source filtering.
kpi.is_internalfalseWhen true, drops every class except person and appends a Summary row.
visualize.platformlocallocal writes a PR-curve plot into results_dir; wandb logs a run and table instead.
visualize.tagnullTag recorded on every row.

For a Grounding DINO loop, inference_ann_path is the labels/ directory TAO inference writes under {results_dir}/inference/labels/, and input_format is KITTI.

The default template is assets/default_kpi_analyze.yaml.

Quick Start

Run from the tao-skill-bank repo root.

Write the spec into the results directory. The run does not retain it, so a completed run otherwise cannot tell you which settings produced kpi_calc.csv. Keeping them together makes the result reproducible from the run alone.

bash
RESULTS_DIR=/absolute/path/for/this/run          # results_dir in the spec
SPEC="$RESULTS_DIR/kpi_analyze.yaml"        # spec lives beside its outputs
RUN_ROOT=/absolute/path/that/contains/images/annotations/and/results

python3 skills/data/tao-analyze-detection-kpi/scripts/verify_kpi_analyze_spec.py \
  --spec "$SPEC"

DS_IMAGE=nvcr.io/nvidia/tao/tao-toolkit:7.2.0-data-services  # versions-key: images.tao_toolkit.data_services

docker run --rm --gpus all --shm-size=8g --network=host \
  -v "$RUN_ROOT:$RUN_ROOT" \
  -w "$RUN_ROOT" \
  "$DS_IMAGE" \
  analytics kpi_analyze -e "$SPEC"

Pass --gpus all even though the analysis itself is CPU-only. The TAO launcher calls nvidia-smi -L unconditionally before dispatching any subtask, so a container started without GPU access dies with FileNotFoundError: 'nvidia-smi' before kpi_analyze runs.

Do not pass --user $(id -u):$(id -g); some TAO DS images call getpass.getuser() at startup and fail when the UID is not in /etc/passwd.

Generate A Spec

If the user provides paths instead of a ready spec, copy the template and fill in the nulls. Every tuning value it already carries is the one this stage wants — change one only deliberately.

bash
cp skills/data/tao-analyze-detection-kpi/assets/default_kpi_analyze.yaml "$SPEC"

Fill data.kpi_sources (one entry per source), data.mapping and results_dir, all as absolute paths, then validate:

bash
python3 skills/data/tao-analyze-detection-kpi/scripts/verify_kpi_analyze_spec.py --spec "$SPEC"
yaml
data:
  input_format: KITTI
  kpi_sources:
  - image_dir: /absolute/path/kpi/images               # no trailing slash
    ground_truth_ann_path: /absolute/path/kpi/labels
    inference_ann_path: /absolute/path/results/inference/labels
  mapping: /absolute/path/mapping.yaml
results_dir: /absolute/path/results/analyze_kpi

The template is the only place a default value lives, so nothing can disagree with it. verify reports the three settings that change what the numbers mean — conf_threshold, num_recall_points, ignore_sqwidth — so the spec that ran is recoverable from its output.

Preflight

  1. Verify Docker access:
bash
docker info > /dev/null
  1. Resolve and pull the data-services image if needed:
bash
DS_IMAGE=nvcr.io/nvidia/tao/tao-toolkit:7.2.0-data-services  # versions-key: images.tao_toolkit.data_services
docker image inspect "$DS_IMAGE" > /dev/null || docker pull "$DS_IMAGE"
  1. Validate the spec:
bash
python3 skills/data/tao-analyze-detection-kpi/scripts/verify_kpi_analyze_spec.py --spec "$SPEC"
  1. Confirm RUN_ROOT contains the spec, every image_dir, both annotation paths per source, the mapping file, and the results directory. Mount RUN_ROOT to the same absolute path inside Docker.

Outputs

ArtifactLocation
Per-class metrics CSVresults_dir/kpi_calc.csv
PR curve plotresults_dir/ (only when visualize.platform: local)

kpi_calc.csv columns: Sequence Name, TP, FP, FN, TN, Pr, Re, Acc, AP — one row per sequence per class. A per-class result table and the aggregate mAP are also printed to stdout; capture the log if the caller needs the mAP value, since it is not written to the CSV.

Show full SKILL.md (471 more words)Show less

Pitfalls

Ground truth may be 15- or 16-field KITTI. The parser names 15 columns for ground truth and 16 for predictions, but reads with index_col=False, so a trailing conf_score on a GT file is truncated rather than shifted. Feeding GT straight from tooling that writes a score column is fine — verified byte-identical results either way. The ParserWarning about "length of header or names does not match length of data" describes exactly that truncation and is not a sign of corruption.

input_format is uppercase here. analytics kpi_analyze accepts only KITTI or COCO. This differs from gap_analysis object_detection, which takes lowercase kitti / coco. Passing lowercase to this action fails to construct the data object.

Sequence Name is derived from the path, not configured. It is image_dir.split('/')[-2] — the second-to-last component of image_dir. A trailing slash or a flat image directory shifts which component is picked, so two sources can collide under one name. Lay out image_dir so that component is the sequence identifier you want.

data.mapping values are LISTS of aliases, not strings. This is the single most destructive thing to get wrong: the file is a YAML list of single-key dicts whose value is a list of source names that fold into that canonical class.

yaml
- bicycle:
    - Bicycle
    - Motorcycle
    - bicycle
    - twowheeler
- car:
    - car
    - Heavy Truck
    - Vehicle

construct_category_map stores the value verbatim (cat_map[k] = v), so writing - car: car — a bare string — yields a value that downstream code iterates character by character. Class matching then fails for every box, and the run still exits 0: the result is TP=0, FN=0, every prediction counted a false positive, and mAP: 0.0, with no error and no warning.

The tell is a perfect-looking run with all-zero metrics. Sanity-check by scoring a ground-truth set against a copy of itself — with a correct mapping that returns TP = every box and mAP: 1.0; anything else means the mapping, not the model.

data.mapping is required. The Hydra schema marks it mandatory even though the underlying category-map builder can derive classes from the label directory when it is absent. Supply the YAML.

Two different conf_threshold defaults. The dataclass default is 0.5, the shipped spec template uses 0.0. Whichever you rely on, set it explicitly — an unset value silently changes which predictions are scored.

is_internal: true is destructive to the report. It drops every class except person and appends a Summary row. Leave it false unless you specifically want the internal person-only KPI.

Troubleshooting

<key> not found in kpi_sources: every source entry needs all three of image_dir, ground_truth_ann_path, inference_ann_path.

Paths not found inside Docker: use a RUN_ROOT mount where host and container paths are identical, and confirm the images and annotation directories are under that mount.

Empty or all-zero metrics: usually conf_threshold above the model's score range, or an input_format that does not match the annotations on disk.

wandb errors or hangs: set visualize.platform: local to write a PR-curve plot instead of logging to wandb.

© NVIDIA, Apache-2.0. 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 9 other files (scripts, references, assets) in skills/tao-analyze-detection-kpi of NVIDIA/skills.

  • SKILL.md
  • BENCHMARK.md
  • assets/default_kpi_analyze.yaml
  • assets/example_mapping.yaml
  • config/skillspector-baseline.yaml
  • evals/evals.json
  • references/skill_info.yaml
  • scripts/verify_kpi_analyze_spec.py
  • skill-card.md
  • skill.oms.sig

Open the folder on GitHubat commit 14a98ae

Compare with similar skills

TAO Detection KPI Analysis 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.

TAO Detection KPI Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
TAO Detection KPI Analysis this skillNVIDIA/skills3.6k—~2.7kAutomated safety check: NotesApache-2.0
Setup Workshop Nemoclawbrevdev/workshop-build-an-agent146—~5.2kAutomated safety check: PassApache-2.0
Matlab Use Visual Inspectionmatlab/matlab-agentic-toolkit1.1k—~3.1kAutomated safety check: PassCustom licence
Yolo Detection 2026SharpAI/DeepCamera3.1k—~1.5kAutomated safety check: PassMIT
Yolo Detection 2026 OpenvinoSharpAI/DeepCamera3.1k—~1.3kAutomated safety check: PassMIT
Dstack Prototypingdstackai/dstack2.3k—~1.6kAutomated safety check: PassMPL-2.0

Similar skills

  • Setup Workshop Nemoclaw

    brevdev/workshop-build-an-agent

    Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands.

    146 GitHub stars~5.2k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

  • Matlab Use Visual Inspection

    matlab/matlab-agentic-toolkit

    Build machine vision inspection systems with MATLAB Visual Inspection Toolbox.

    1.1k GitHub stars~3.1k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Yolo Detection 2026

    SharpAI/DeepCamera

    YOLO 2026 — state-of-the-art real-time object detection. An agent skill from SharpAI/DeepCamera.

    3.1k GitHub stars~1.5k tokensUpdated 23 days ago
    AI & LLM EngineeringAuto-check passed

  • Yolo Detection 2026 Openvino

    SharpAI/DeepCamera

    OpenVINO — real-time object detection via Docker (NCS2, Intel GPU, CPU)

    3.1k GitHub stars~1.3k tokensUpdated 23 days ago
    AI & LLM EngineeringAuto-check passed

  • Dstack Prototyping

    dstackai/dstack

    Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.

    2.3k GitHub stars~1.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Nemotron Customizer Airgap

    NVIDIA-NeMo/Nemotron

    Prepare, validate, build, and use Nemotron Customizer airgap image bundles for offline clusters.

    2.1k GitHub stars~1.2k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

More from NVIDIA/skills

All 390 skills in this repo

  • Vss Deploy Detection Tracking 2D

    NVIDIA/skills

    Official

    A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.

    3.6k GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check passed

  • HSB IP Def File Tool

    NVIDIA/skills

    Official

    Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.

    3.6k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Isaac Sim Mission Control Showcase

    NVIDIA/skills

    Official

    Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server.

    3.6k GitHub stars~4.8k tokensUpdated today
    Auto-check passed

  • Defect Image Generation with Cosmos AnomalyGen

    NVIDIA/skills

    Official

    Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.

    3.6k GitHub stars~5k tokensUpdated today
    Auto-check: notes

  • Physical AI Video Augmentation on OSMO

    NVIDIA/skills

    Official

    Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.

    3.6k GitHub stars~4.7k tokensUpdated today
    Auto-check: notes

  • TAO Object Detection Gap Analysis

    NVIDIA/skills

    Official

    Runs TAO Data Services gap analysis that compares ground-truth and predicted boxes to find weak images by per-class recall, precision and AP50.

    3.6k GitHub stars~1.8k tokensUpdated today
    Auto-check: notes

Works with

Categories

Questions about TAO Detection KPI Analysis

What does TAO Detection KPI Analysis do?

Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV. Object detection predictions are scored against ground truth by running the container's analytics kpi_analyze command with an absolute path to a YAML spec.csv in the results directory.

When should I use TAO Detection KPI Analysis?

TAO Detection KPI Analysis fits situations like: an object detection workflow needs per-class mAP after inference; scoring predictions against ground truth annotations in KITTI or COCO format; checking a KPI analyze spec before running it in the TAO container.

How do I install TAO Detection KPI Analysis in Claude Code?

Run `npx skills add NVIDIA/skills --skill tao-analyze-detection-kpi -a claude-code`. Or copy the skill folder (skills/tao-analyze-detection-kpi in NVIDIA/skills) into .claude/skills/tao-analyze-detection-kpi in your project. Claude Code loads it when a task matches its description.

How do I install TAO Detection KPI Analysis in Codex?

Run `npx skills add NVIDIA/skills --skill tao-analyze-detection-kpi -a codex`. Or copy the skill folder (skills/tao-analyze-detection-kpi in NVIDIA/skills) into .agents/skills/tao-analyze-detection-kpi in your project. Codex loads it when a task matches its description.

Can I use TAO Detection KPI Analysis 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 NVIDIA/skills --skill tao-analyze-detection-kpi -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tao-analyze-detection-kpi, .gemini/skills/tao-analyze-detection-kpi, .github/skills/tao-analyze-detection-kpi and .opencode/skills/tao-analyze-detection-kpi in your project.

What does TAO Detection KPI Analysis need to run?

Going by SKILL.md and its folder, TAO Detection KPI Analysis needs Python for the scripts in its folder and the command-line tools its instructions call (docker and python3). Our summary lists: Docker with nvidia-container-toolkit; The TAO data-services container pinned in versions.yaml; Inference annotations produced by an earlier detection step. Its frontmatter pre-approves these tools: Read, Bash. Compatibility (from SKILL.md): Requires docker, nvidia-container-toolkit, and the TAO data-services container pinned in versions.yaml..

Does TAO Detection KPI Analysis access the network?

SKILL.md contains no URLs. Its commands use docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is TAO Detection KPI Analysis safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. 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 TAO Detection KPI Analysis use?

TAO Detection KPI Analysis is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does TAO Detection KPI Analysis use?

About 2.7k tokens (SKILL.md is roughly 11k 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 140 tokens, read only when the agent opens those files.

What are the alternatives to TAO Detection KPI Analysis?

Skills that share tags, products or a category with TAO Detection KPI Analysis: Setup Workshop Nemoclaw (brevdev/workshop-build-an-agent, 146 stars), Matlab Use Visual Inspection (matlab/matlab-agentic-toolkit, 1.1k stars), Yolo Detection 2026 (SharpAI/DeepCamera, 3.1k stars) and Yolo Detection 2026 Openvino (SharpAI/DeepCamera, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains TAO Detection KPI Analysis?

NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,555 GitHub stars. The repository holds 390 skills in this directory. The repository was last updated on October 9, 2026.

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