菜单
Transforms a raw TensorCircuit-NG script into a comprehensive, self-contained, and narrative-driven tutorial in Markdown and/or HTML. It acts as an expert technical writer, blending physics/math background, step-by-step code walkthroughs, and HPC programming highlights.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Analyzes and refactors TensorCircuit-NG code to achieve peak time and memory performance. It enforces advanced JAX vectorization, intelligent JIT staging, optimal tensor network contraction, and memory-efficient autodiff strategies.
Tune tensor-network contraction path search and slicing for TensorCircuit-NG workloads, especially OMECO and cotengra hyperparameters, memory targets, total FLOPs/write, slice counts, and large-circuit amplitude or expectation contractions.
Review TensorCircuit-NG code diffs for correctness, performance, backend agnosticity, and minimal high-quality fixes.
Performs a comprehensive sanity check on the codebase to reduce entropy, increase readability, and improve maintainability. Identifies issues with imports, comments, dead code, DRY violations, exception handling, magic numbers/secrets, docstrings, duplicated implementations, and test sufficiency.
Maintain TensorCircuit-NG development memory in `.agents/memory/`. Use `update` mode to save durable lessons from the current session into the right memory file, and use `dream` mode to scan and refactor the whole memory set for lower redundancy, clearer taxonomy, and better long-term usefulness.
Autonomously reproduces quantum computing arXiv papers using TensorCircuit-NG. It creates standardized repository structures, generates meta.yaml, writes and runs JAX-accelerated code, and strictly enforces code quality (black/pylint) before saving final figures.
| name | tutorial-crafter |
| description | Transforms a raw TensorCircuit-NG script into a comprehensive, self-contained, and narrative-driven tutorial in Markdown and/or HTML. It acts as an expert technical writer, blending physics/math background, step-by-step code walkthroughs, and HPC programming highlights. |
| allowed-tools | Bash, Read, Write |
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.
.md and .html files.tc.backend.vmap, jax.jit, jax.lax.scan, or cotengra optimizations. Highlight these to educate the user on high-performance practices.Generate a comprehensive narrative following this structure:
$math$, display: $$math$$).vmap vs. loops, jax.checkpoint).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>
.md as [original_name]_tutorial.md in the same directory as the original script..html as [original_name]_tutorial.html in the same directory as the original script.