What is tao-run-deft-object-detection?

An iterative workflow for improving NVIDIA TAO Grounding DINO object-detection models with smart data augmentation. It evaluates a baseline, finds weak image examples, prepares training data, retrains, and repeats for a set number of iterations.

Use it to analyse per-class detection gaps, mine similar images with SigLIP embeddings, stage ODVG training data, and run repeated Grounding DINO training.

It coordinates the full loop from measuring detection gaps to finding additional data and retraining. A saved state lets the workflow track progress and resume safely.

tao-run-deft-object-detection — Skill for Claude Code by NVIDIA-TAO

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 NVIDIA-TAO/tao-skill-bank --skill tao-run-deft-object-detection

Clone the repo

git clone --depth 1 https://github.com/NVIDIA-TAO/tao-skill-bank

Made for: Claude Code.

Or install tao-skills, the plugin that ships this one along with the rest of its 76 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-run-deft-object-detection/github.svg)](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-run-deft-object-detection)

Your own site

<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-run-deft-object-detection"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-run-deft-object-detection/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-run-deft-object-detection"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-run-deft-object-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,122 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

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 →

medium Excessive Agency · line 111
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00196	$0.03122
Opus 5	$0.00098	$0.01561
Sonnet 5	$0.00039	$0.00624
Haiku 4.5	$0.00020	$0.00312

Measured 12d ago against content hash c04537331f15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tao-run-deft-object-detection 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.

The scan reads SKILL.md. This mod also ships 23 executable files (scripts/apply_spec_overrides.py, scripts/audit_deft_run.py, scripts/await_stage.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/applications/tao-run-deft-object-detection/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: tao-run-deft-object-detection

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery).

Execution Contract

Treat this as a disk-backed state machine, not as a prose recipe.

Preserve every explicit user value. epoch 1 means train.num_epochs=1; a spec value or documented default applies only when the user did not supply that parameter. Show the source of every run parameter (user, spec, or default) in the Pre-Flight Summary.
After the user approves the Summary, initialize deft_state.json once with scripts/init_deft_state.py. Never hand-author or reinitialize it on resume.
Run every bundled or inline host-Python command through scripts/deft_python.sh. On startup, after context compaction, before every stage, and before any completion claim, run:
```
<skill_root>/scripts/deft_python.sh \
  <skill_root>/scripts/audit_deft_run.py --results-dir "${RESULTS_DIR}"
```
If it prints DEFT_RUN_STATUS=INVALID, stop and repair the listed disk inconsistency; do not launch another stage. Read the path printed as read_before_action before continuing.
Invoke the mapped underlying skill after reading the DEFT overlay. Do not replace a missing or unread stage reference, or a failed skill call, with guessed shell commands, inline Python, a different output tree, or fabricated data.
Commit every stage with scripts/commit_stage.py; it verifies artifacts, updates deft_state.json, appends exactly one ordered loop_log.jsonl event, and rolls back if its audit fails.

Claim the loop complete only when this exits zero:

<skill_root>/scripts/deft_python.sh \
  <skill_root>/scripts/audit_deft_run.py \
  --results-dir "${RESULTS_DIR}" --require-complete

Context Discipline

Load references just in time. Run the audit, read only its read_before_action file and the current stage's named section, then act. Never preload all references.
Redirect verbose train, inference, and Docker output to files. Inspect at most the final 40 lines or a one-line artifact check; never print a full spec, state file, or loop log into the conversation.
A Skill-tool call loads stage instructions; it does not start a background orchestrator. Continue the documented stage in the parent immediately after it returns.

Read the full file on GitHub · 175 lines

Files

What ships with it

47 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.

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.

12d ago First seen · 175 lines · 196 tokens per session scan A c04537331f15

Subscribe to this mod's changes

tao-run-deft-object-detection is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 196 tokens to every session and 3,122 once invoked, about $0.0010 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.

Data and AI Scientific application deft grounding-dino mining object-detection workflow

fair-esm2

Embed proteins with Meta AI's ESM-2 (fair-esm package). Use this skill when: (1) Extracting per-residue or per-sequence embeddings for downstream ML, (2) Masked-LM likelihood / mutation effect scoring, (3) Contact prediction from a sequence.

UnicomAI/wanwu · 66 tokens

evo2

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…

UnicomAI/wanwu · 83 tokens

openfold3

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation.

UnicomAI/wanwu · 60 tokens

boltz

Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al. 2025, github.com/jwohlwend/boltz). Reach for this skill to validate designed binders against a target, to co-fold a protein with a SMILES or CCD ligand, or to get an open-source AlphaFold3 alternative…

UnicomAI/wanwu · 88 tokens

scgpt

Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill when: (1) Producing cell embeddings from an AnnData for clustering/integration, (2) Zero-shot or fine-tuned cell-type annotation, (3) Gene-level representation for perturbation/GRN tasks. For…

UnicomAI/wanwu · 89 tokens

solublempnn

Inverse-fold a backbone with SolubleMPNN — ProteinMPNN retrained on a soluble-PDB subset (Dauparas et al. 2022) — for sequences biased toward cytosolic expression and reduced aggregation. Reach for this skill when designs from vanilla ProteinMPNN are aggregating or going to inclusion bodies, when redesigning a…

UnicomAI/wanwu · 96 tokens