tao-run-deft-object-detection

67 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.

By NVIDIA/skills (GitHub) · coding · 3,933 stars · scanned at commit 2630133

Run the full DEFT smart-data-augmentation loop for NVIDIA TAO Grounding DINO object detection: zero-shot baseline inference, KPI analysis, per-class gap analysis, SigLIP embedding of weak images, unique-neighbor mining against a source pool, ODVG dataset staging, and retraining — repeated for a fixed number of iterations. Also prepares the source pool the loop mines from, as a separate run: Co-DETR pseudo-labeling, folding to the target classes, KITTI→COCO→ODVG conversion, and embedding. Use fo…

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.

Found in 14 places.

skills/tao-run-deft-object-detection/SKILL.md, line 41<skill_root>/scripts/deft_python.sh \
skills/tao-run-deft-object-detection/SKILL.md, line 51<skill_root>/scripts/deft_python.sh \
skills/tao-run-deft-object-detection/references/preflight.md, line 12<skill_root>/scripts/deft_python.sh -c "import pandas,numpy,matplotlib,pyarrow,PIL,yaml"

Show 11 more

skills/tao-run-deft-object-detection/references/preflight.md, line 314EXTRA_MOUNTS=$(<skill_root>/scripts/deft_python.sh -c 'import json,sys
skills/tao-run-deft-object-detection/scripts/commit_stage.py, line 423proc = subprocess.run(
skills/tao-run-deft-object-detection/scripts/emit_default_spec.py, line 80result = subprocess.run(cmd, capture_output=True, text=True)
skills/tao-run-deft-object-detection/scripts/emit_default_spec.py, line 101result = subprocess.run(cmd, capture_output=True, text=True)
skills/tao-run-deft-object-detection/scripts/fetch_gdino_checkpoint.py, line 92result = subprocess.run(cmd, capture_output=True, text=True)
skills/tao-run-deft-object-detection/scripts/tests/test_state_machine.sh, line 820proc = subprocess.run([sys.executable, REAL] + sys.argv[1:], capture_output=True, text=True)
skills/tao-run-deft-object-detection/scripts/tests/test_state_machine.sh, line 1095proc = subprocess.run([sys.executable, sys.argv[1], '--results-dir', sys.argv[2], '--json'],
skills/tao-run-deft-object-detection/scripts/tests/test_state_machine.sh, line 3245subprocess.run([sys.executable, f"{sys.argv[1]}/summarize_kpi.py",
skills/tao-run-deft-object-detection/scripts/tests/test_state_machine.sh, line 3264subprocess.run([sys.executable, f"{sys.argv[1]}/summarize_kpi.py",
skills/tao-run-deft-object-detection/scripts/tests/test_state_machine.sh, line 3278proc = subprocess.run([sys.executable, f"{sys.argv[1]}/summarize_kpi.py",
skills/tao-run-deft-object-detection/scripts/tests/test_state_machine.sh, line 3286proc = subprocess.run([sys.executable, f"{sys.argv[1]}/summarize_kpi.py",

Reads your saved credentials, such as SSH keys or .env files

This is disclosed by the author in the skill's SKILL.md or README.

Found in 4 places.

skills/tao-run-deft-object-detection/config/skillspector-baseline.yaml, line 21reason: "Reviewed FP (#67): documented infrastructure path reference (e.g. ~/.docker/config.json, ~/.ssh keys) appearing in documentation or example config; the
skills/tao-run-deft-object-detection/config/skillspector-baseline.yaml, line 24reason: "Reviewed FP (#67): documented infrastructure path reference (e.g. ~/.docker/config.json, ~/.ssh keys) appearing in documentation or example config; the
skills/tao-run-deft-object-detection/config/skillspector-baseline.yaml, line 27reason: "Reviewed FP (#67): documented infrastructure path reference (e.g. ~/.docker/config.json, ~/.ssh keys) appearing in documentation or example config; the

Show 1 more

skills/tao-run-deft-object-detection/config/skillspector-baseline.yaml, line 30reason: "Reviewed FP (#67): documented infrastructure path reference (e.g. ~/.docker/config.json, ~/.ssh keys) appearing in documentation or example config; the

Downloads and installs other software

The author does not mention this.

Found in 1 place.

skills/tao-run-deft-object-detection/scripts/fetch_codetr_checkpoint.py, line 15not installable on a clean box without a virtual environment -- ``pip install --user``

Connects to the internet

The author does not mention this.

Found in 5 places.

skills/tao-run-deft-object-detection/scripts/fetch_codetr_checkpoint.py, line 46import urllib.request
skills/tao-run-deft-object-detection/scripts/fetch_codetr_checkpoint.py, line 115with urllib.request.urlopen(url, timeout=120) as response: # nosec B310 - https endpoint from skill configuration
skills/tao-run-deft-object-detection/scripts/fetch_gdino_checkpoint.py, line 78def fetch(dest: Path, version: str) -> Path:

Show 2 more

skills/tao-run-deft-object-detection/scripts/fetch_gdino_checkpoint.py, line 162checkpoint = fetch(dest, args.version)
skills/tao-run-deft-object-detection/scripts/tests/test_state_machine.sh, line 2979mod.urllib.request.urlopen = lambda *_a, **_k: _DiesMidTransfer()

Safer alternatives

Low-risk skills in the same category (coding) that look related. Check that one does what you need.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'tao-run-deft-object-detection' ] || [ -L ~/.agents/skills/'tao-run-deft-object-detection' ]; then echo 'A skill folder named tao-run-deft-object-detection already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/NVIDIA/skills' "$d" && git -C "$d" checkout --quiet '2630133f22e357f2005886567a39eddcc1b520e2' -- 'skills/tao-run-deft-object-detection' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/tao-run-deft-object-detection' ~/.agents/skills/'tao-run-deft-object-detection' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'tao-run-deft-object-detection' ~/.claude/skills/'tao-run-deft-object-detection' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for NVIDIA/skills shows the score of its lowest-scoring skill.

SkillTrust badge for NVIDIA/skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/NVIDIA/skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/NVIDIA/skills/)

Score history

Date	Version	Score
2026-11-11	`2630133`	67
2026-11-08	`fce3cca`	67
2026-11-07	`fce3cca`	67