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-validate-recipe-transfergit 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-validate-recipe-transfer)<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-validate-recipe-transfer"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-validate-recipe-transfer/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-validate-recipe-transfer"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-validate-recipe-transfer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00179 | $0.03680 |
| Opus 5 | $0.00089 | $0.01840 |
| Sonnet 5 | $0.00036 | $0.00736 |
| Haiku 4.5 | $0.00018 | $0.00368 |
Grade A, and why
tao-validate-recipe-transfer 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CV Recipe Transfer
Port published CV work onto customer data without inheriting the silent bugs that make the resulting numbers meaningless.
The core idea
This work splits into two phases with fundamentally different epistemic status:
- Phase A (Port) — get the official code running faithfully. There is external ground truth here: the authors' released checkpoint and reported number.
- Phase B (Transfer) — move the recipe onto customer data. There is no external ground truth. The paper's number stops being meaningful the moment the dataset changes.
Everything verifiable must be verified in Phase A, because the safety net disappears at the boundary. Once you are in Phase B, an implementation bug and a genuine domain mismatch produce identical symptoms: a mediocre number with a clean-looking loss curve.
Two consequences that drive everything below:
- Never skip the Phase A gate to "save time." It costs hours and it is the only thing that licenses trust in every number that follows.
- Stop treating the paper's number as the target once the dataset changes. The target is beat the strongest cheap baseline on the customer's own test set, measured at a deliberately chosen operating point.
Mode selection
Read the request and pick a mode. Say which one you picked and why.
Post-mortem mode — a run already happened and the result was wrong, disappointing, or
suspiciously good. Go to references/postmortem.md. Do not start by rerunning anything.
Walk the checks in likelihood order and find the gate that was skipped.
Forward mode — no run yet, or starting over. Work Phase 0 → A → G → T → R → E below.
Audit mode — a pipeline exists and works, someone wants it checked before it goes to a customer. Run the Phase A gate and the Phase G report against the existing artifacts, then the parity and leakage scripts. Skip the porting work.
If the request is ambiguous, ask which of the three it is before doing anything expensive.
What ships with it
14 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.
- assets/status.example.json 1.7 KB
- evals/evals.json 7.6 KB
- references/failure-atlas.md 4.2 KB
- references/port-gate.md 6.7 KB
- references/postmortem.md 9.3 KB
- references/recipe_spec.yaml 4.1 KB
- references/recipe-fields.md 6.8 KB
- references/stacks.md 4.2 KB
- references/verification-ladder.md 4.6 KB
- scripts/domain_gap_report.py 14 KB runs code
- scripts/preprocess_parity.py 16 KB runs code
- scripts/render_status.py 6.8 KB runs code
- scripts/split_leakage_check.py 8.2 KB runs code
- skill-card.md 3.1 KB
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 · 333 lines · 179 tokens per session scan A 7a475af4c76b
tao-validate-recipe-transfer is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed yesterday), licensed Apache-2.0. It adds 179 tokens to every session and 3,680 once invoked, about $0.0009 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
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
ai-research-reproduction
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted…
analyze-project
Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation patterns without modifying code or…
deep-learning
Use when training or debugging a neural net in PyTorch — the forward/loss/backward/step loop and its silent bugs, mixed precision (AMP), AdamW/LR schedules, DDP/FSDP/ZeRO, checkpoints and seeds. NOT LoRA/QLoRA on a pretrained LLM (that is finetuning), NOT tabular sklearn/XGBoost (that is machine-learning), NOT…
huawei-cloud-cloudrobo-model-workflow
Model development orchestration Skill covering asset query, model training, inference deployment, and real-robot evaluation in any combination. Supports full end-to-end pipeline or partial stages (e.g., train+deploy only, deploy+eval only). When user requirements involve two or more stages, prefer this Skill over…
ipsae
Binder design ranking using ipSAE (interprotein Score from Aligned Errors). Use this skill when: (1) Ranking binder designs for experimental testing, (2) Filtering BindCraft or RFdiffusion outputs, (3) Comparing AF2/AF3/Boltz predictions, (4) Predicting binding success rates, (5) Need better ranking than ipTM or iPAE.…