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 agentmods add skills/tensorcircuit/tensorcircuit-ng/demo-generatornpx skills add tensorcircuit/tensorcircuit-ng --skill demo-generatorgit 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/demo-generator)<a href="https://agentmods.dev/skills/tensorcircuit/tensorcircuit-ng/demo-generator"><img src="https://agentmods.dev/badge/skills/tensorcircuit/tensorcircuit-ng/demo-generator.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00048 | $0.00968 |
| Opus 5 | $0.00024 | $0.00484 |
| Sonnet 5 | $0.00010 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
demo-generator 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 6d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When tasked with creating a Streamlit demo from a TensorCircuit-NG (TC-NG) script, you act as a Creative Full-Stack Quantum Scientist. Your goal is to build an app that doesn't just "run the script," but makes the underlying physics alive, interactive, and surprising for an audience. Use your imagination to create a 'wow' effect.
0. App Metadata & Docstring
The generated [original_name]_app.py MUST begin with a standardized docstring:
"""
Streamlit Interactive Demo: [App Title]
Origin: Based on [path/to/original_script.py]
Usage: streamlit run [original_name]_app.py
Description: [Brief 1-sentence description of the interactivity and goal]
"""
1. Intent & Interactivity Extraction
- Identify Controllable Parameters: What variables in the script are "fun" to change? (e.g., lattice size $L$, bias $\theta$, noise rate $p$, number of qubits $N$).
- Identify Visual "Hooks": What is the most impressive result? (e.g., a 3D phase transition 'volcano', a real-time circuit animation, or a statevector magnitude heatmap).
- Be Imaginative & Surprising: Don't just settle for standard line plots. If the physics allows, create 3D surfaces, interactive phase diagrams, or evolving probability landscapes that make the user say "Wow."
- Plan the Story: How should the user interact with it? (e.g., "Adjust the temperature and watch the magnetization landscape buckle").
2. Standardized App Structure
The generated [original_name]_app.py should follow this professional blueprint:
A. Global Styling & Branding
- Use
st.set_page_configwith a wide layout and a custom title. - Integrate the official TensorCircuit-NG logo from:
https://github.com/tensorcircuit/tensorcircuit-ng/blob/master/docs/source/statics/logong.png?raw=true. - Apply custom CSS for a premium "Dark/Glassmorphism" look if possible.
B. Sidebar Controls
- Put all simulation parameters in the
st.sidebar. - Use
st.sidebar.slider,num_input, orselectbox. - Use clear labels and helpful tooltips for each parameter.
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.
- 6d ago First seen · 59 lines · 48 tokens per session scan A 53515150fb95
demo-generator is a skill published in the GitHub repository tensorcircuit/tensorcircuit-ng (89 stars, last pushed 4d ago), licensed Apache-2.0. It adds 48 tokens to every session and 968 once invoked, about $0.0002 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
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…
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…
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…
start-experiment
Start the autoresearch optimization loop for a specific model + lane. Resolves the hierarchical program.md (root → model → lane), asks the user for hardware (local TPU VM or GKE cluster of a specified TPU type + topology), discovers available clusters from .env/, checks occupancy with USERPREFIX-aware attribution…
stop-experiment
Stop the autoresearch optimization loop cleanly. Disarms the launch-armed process watcher, cancels pending wakeups, reaps orphan workloads on the project's cluster pool, files any missing experiment pages, runs lint, and appends a clean-shutdown marker to wiki/log.md. Invoke at the end of an autoresearch session.
create-experiment
Bootstrap a new model family for the autoresearch loop. Creates the folder structure under wiki/experiments/, scaffolds the model-level program.md from a template (asking the user about lanes, sizes, hardware targets, sequence length, and architecture invariants), optionally creates lane-level program.md stubs, and…