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 NVIDIA-TAO/tao-skill-bank --skill tao-analyze-detection-kpigit clone --depth 1 https://github.com/NVIDIA-TAO/tao-skill-bankWrote 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/nvidia-tao/tao-skill-bank/tao-analyze-detection-kpi)<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-analyze-detection-kpi"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-analyze-detection-kpi/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/nvidia-tao/tao-skill-bank/tao-analyze-detection-kpi"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-analyze-detection-kpi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, 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 Privilege Escalation · line 83 Potential security issue detected. Manual review is recommended.Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- high Privilege Escalation · line 94 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Anti-Refusal · line 195 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium MCP Rug Pull · line 83 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 141 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00094 | $0.02694 |
| Opus 5 | $0.00047 | $0.01347 |
| Sonnet 5 | $0.00019 | $0.00539 |
| Haiku 4.5 | $0.00009 | $0.00269 |
Grade A, and why
tao-analyze-detection-kpi 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 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.
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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
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:
| Field | Meaning |
|---|---|
data.input_format |
KITTI or COCO. Uppercase — see Pitfalls. |
data.kpi_sources |
List of sources. Each entry requires image_dir, ground_truth_ann_path, and inference_ann_path; all three are asserted at startup. |
data.mapping |
Path 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_dir |
Output 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:
| Field | Default | Meaning |
|---|---|---|
kpi.iou_threshold |
0.5 |
IoU at or above which a prediction counts as a true positive. |
kpi.conf_threshold |
0.5 |
Predictions 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_points |
11 |
Recall 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_sqwidth |
0 |
Boxes 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.filter |
false |
Enable source filtering. |
kpi.is_internal |
false |
When true, drops every class except person and appends a Summary row. |
visualize.platform |
local |
local writes a PR-curve plot into results_dir; wandb logs a run and table instead. |
visualize.tag |
null |
Tag recorded on every row. |
What ships with it
6 files 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.
- 13d ago First seen · 216 lines · 94 tokens per session scan A 01163a5e8bf7
tao-analyze-detection-kpi is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 94 tokens to every session and 2,694 once invoked, about $0.0005 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
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
docetl
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…
yolo-detection-2026-coral-tpu-macos
Google Coral Edge TPU — real-time object detection natively (macOS / Linux).
yolo-detection-2026-openvino
OpenVINO — real-time object detection via Docker (NCS2, Intel GPU, CPU).
yolo-detection-2026
YOLO 2026 — state-of-the-art real-time object detection.