Borrowing it
Nothing to install: this file belongs to tensorcircuit/tensorcircuit-ng. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tensorcircuit/tensorcircuit-ng/master/.agents/skills/tutorial-crafter/SKILL.mdgit clone --depth 1 https://github.com/tensorcircuit/tensorcircuit-ngWrote 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/tensorcircuit/tensorcircuit-ng/tutorial-crafter)<a href="https://agentmods.dev/skills/tensorcircuit/tensorcircuit-ng/tutorial-crafter"><img src="https://agentmods.dev/badge/skills/tensorcircuit/tensorcircuit-ng/tutorial-crafter/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/tensorcircuit/tensorcircuit-ng/tutorial-crafter"><img src="https://agentmods.dev/badge/skills/tensorcircuit/tensorcircuit-ng/tutorial-crafter.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 | $0.00055 | $0.01616 |
| Opus 5.5 | $0.00022 | $0.00646 |
| Sonnet 5.5 | $0.00011 | $0.00323 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade A, and why
tutorial-crafter 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 2mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When tasked with generating a tutorial from a TensorCircuit-NG (TC-NG) script, you act as an Expert Quantum Computing Educator and Technical Writer. Your goal is to produce a self-contained, engaging tutorial that guides the reader from theoretical physics concepts down to the JAX-accelerated code implementation.
0. Output Format Selection
- Default: Generate both
.mdand.htmlfiles. - Explicit: If the user specifies a format (e.g., "only MD" or "HTML format"), respect that request.
1. Script Analysis & Intent Extraction
- Understand the Physics: What is the physical or mathematical goal of the script? (e.g., VQE, QAOA, DMRG).
- Identify the TC-NG Highlights: Look for the "TC Way"—such as
tc.backend.vmap,jax.jit,jax.lax.scan, orcotengraoptimizations. Highlight these to educate the user on high-performance practices.
2. Tutorial Content Blueprint (Applies to both MD and HTML)
Generate a comprehensive narrative following this structure:
- Title & Introduction: Catchy title, 2-3 sentence abstract, and prerequisites.
- Physics & Mathematical Background: Theoretical explanation using rigorous LaTeX for all formulas (inline:
$math$, display:$$math$$). - Step-by-Step Code Walkthrough: Break the code into logical snippets with transitional prose explaining the "what" and "why".
- TC-NG Programming Highlights & Caveats: Explicitly point out TC-NG/JAX design patterns (e.g.,
vmapvs. loops,jax.checkpoint). - Results, Visualizations & Conclusion: Describe expected output and potential next steps.
3. HTML Template & Style (Strict Guidelines)
When generating HTML, you MUST use the following premium style and structure to ensure consistency:
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>[Tutorial Title]</title>
<!-- Fonts -->
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&family=Outfit:wght@400;600;700&family=Fira+Code:wght@400;500&display=swap" rel="stylesheet">
<!-- MathJax -->
<script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
<!-- Prism Syntax Highlighting -->
<link href="https://cdnjs.cloudflare.com/ajax/libs/prism/1.29.0/themes/prism-tomorrow.min.css" rel="stylesheet" />
<script src="https://cdnjs.cloudflare.com/ajax/libs/prism/1.29.0/prism.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/prism/1.29.0/components/prism-python.min.js"></script>
<style>
:root { --primary: #6366f1; --bg-dark: #0f172a; --text-main: #f8fafc; --text-dim: #94a3b8; --highlight: #10b981; }
body { font-family: 'Inter', sans-serif; background-color: var(--bg-dark); color: var(--text-main); line-height: 1.7; padding: 2rem 1rem; background-image: radial-gradient(circle at top right, rgba(99, 102, 241, 0.1), transparent); background-attachment: fixed; }
.container { max-width: 900px; margin: 0 auto; }
header { text-align: center; margin-bottom: 4rem; }
.logo { width: 400px; margin-bottom: 2rem; }
h1 { font-family: 'Outfit', sans-serif; font-size: 3rem; background: linear-gradient(135deg, #fff 0%, #94a3b8 100%); -webkit-background-clip: text; -webkit-text-fill-color: transparent; }
.card { background: rgba(30, 41, 59, 0.7); backdrop-filter: blur(12px); border: 1px solid rgba(255, 255, 255, 0.1); padding: 1.5rem; border-radius: 1rem; margin-bottom: 1.5rem; }
h2 { font-family: 'Outfit', sans-serif; font-size: 2rem; border-bottom: 2px solid rgba(255, 255, 255, 0.05); margin: 2.5rem 0 1.5rem; }
pre[class*="language-"] { border-radius: 1rem; margin: 1.5rem 0; background: #011627 !important; padding: 1.5rem; }
blockquote { background: rgba(99, 102, 241, 0.1); border-left: 4px solid var(--primary); padding: 1.25rem 1.5rem; border-radius: 0 1rem 1rem 0; margin: 2rem 0; }
.highlight-box { background: rgba(16, 185, 129, 0.1); border-left: 4px solid var(--highlight); padding: 1.25rem 1.5rem; border-radius: 0 1rem 1rem 0; margin: 2rem 0; }
footer { text-align: center; padding: 4rem 0 2rem; border-top: 1px solid rgba(255, 255, 255, 0.1); color: var(--text-dim); }
</style>
</head>
<body>
<div class="container">
<header>
<img src="https://github.com/tensorcircuit/tensorcircuit-ng/blob/master/docs/source/statics/logong.png?raw=true" alt="TensorCircuit-NG Logo" class="logo">
<h1>[Tutorial Title]</h1>
<p>[Tagline]</p>
</header>
<div class="card"><strong>✨ Abstract:</strong> [Abstract Content]</div>
<!-- Content Sections here -->
<footer>Built with <a href="https://github.com/tensorcircuit/tensorcircuit-ng" style="color:var(--primary)">TensorCircuit-NG</a></footer>
</div>
</body>
</html>
What ships with it
1 file 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.
- 2mo ago First seen · 77 lines · 55 tokens per session scan A d7ff6b814937
tutorial-crafter is a skill published in the GitHub repository tensorcircuit/tensorcircuit-ng (93 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,616 once invoked, about $0.0002 per session on Opus 5.5. 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
physicsnemo-shard-tensor
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…
fine-tuning-serving-openpi
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging…
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
ml-engineering
This file moved to skills/ml-engineering/SKILL.md.
evaluate-cluster
Evaluates an ML GPU cluster for a cloud trial or acceptance test: environment dump, isolated newest PyTorch, matmul FLOPS (MAMF/MSMF) on every GPU while the others compute, intra-node all-reduce bandwidth and per-call latency of every collective, the same inter-node on every node you were given (omit those sections if…