Borrowing it
Nothing to install: this file belongs to xi-zhao/OpenQuantum. 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/xi-zhao/OpenQuantum/main/.agents/skills/quantum-ground-state/SKILL.mdgit clone --depth 1 https://github.com/xi-zhao/OpenQuantumWrote 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/xi-zhao/openquantum/quantum-ground-state)<a href="https://agentmods.dev/skills/xi-zhao/openquantum/quantum-ground-state"><img src="https://agentmods.dev/badge/skills/xi-zhao/openquantum/quantum-ground-state.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.00943 |
| Opus 5 | $0.00051 | $0.00472 |
| Sonnet 5 | $0.00021 | $0.00189 |
| Haiku 4.5 | $0.00010 | $0.00094 |
Grade A, and why
quantum-ground-state 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 2d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quantum Ground State
能力边界
这个 Skill 只支持一个窄而可验证的科学主张：对用户提供的二量子位实 Pauli 和，在固定
hamming-weight=1 扇区内计算基态能量。执行方法固定为无噪 statevector VQE，并用独立的
实对称 2×2 闭式对角化提供参考。
把输入 Hamiltonian 当作用户提供的问题定义，不从名称或标签推断分子来源。 完整边界见 references/SCOPE.md，数值约定见 references/NUMERICAL-CONVENTIONS.md。
执行工作流
- 按 inputs/request.schema.json 检查结构，并由 solver 再做语义 preflight。
- 明确拒绝 QAOA、Pauli
Y、复系数、错误单位、其他粒子扇区、更多量子位、shots 和噪声。 - 普通用户请求调用原生 Tool
solve_and_validate_ground_state；它在一次确定性调用内生成六类事实并运行独立 Validator。 - facts-only 求解和已物化 Result Package 重验是内部 solver/Validator 接口，不增加到模型可见 Tool surface。
- 组合 Tool 自己的
provenance.complete必须保持not_checked；不得伪造 Session、路径或摘要让它通过。 - OpenQuantum 的可信 Host Plugin 从真实 Session/Tool 身份进入内部 Scientific Result Adapter；
Materializer 使用
ctx.fs物化、重读和校验 Result Package，Validator 只对重读后的结构化 证据产生 observations，central Acceptance Builder 再汇聚 Acceptance Profile、observations 和 provenance 推导科学结论。 - 需要评分或复现时，分别生成 Score Report 或 Reproduction Report；不得从运行完成推导它们。
本地事实求解命令：
node scripts/solve.mjs <request.json> <new-output-directory>
目标目录中任何同名 Artifact 已存在时必须拒绝覆盖。
产物合同
problem-spechamiltonian-manifestexact-referenceground-state-resultconvergence-traceresource-estimate
六类 Artifact 都是 additionalProperties: false 的 JSON 事实对象。不要在其中增加：
status、score、acceptance或“已复现”结论；- Model 的主观置信度；
- 没有来源链的分子/化学主张；
- API key、凭证、绝对路径或 Harness 身份。
科学验收规则
权威规则位于
acceptance-profiles/supplied-pauli-statevector-v1.json。
1.6 mHa 只适用于这个 Profile，不是所有体系的普适标准。必须同时检查作用域、canonical digest、
Hermiticity、扇区不变性、精确参考重算、归一化、期望值回放、变分下界、收敛和 provenance。
若 optimizer 未收敛，solver 仍可产生有限事实，但 Validator 必须使必需的 vqe.converged 检查失败；
不得把它包装成科学成功。
解释要求
对用户解释时明确区分：这是“给定 Hamiltonian 的扇区基态”，不是完整的分子 Hamiltonian/FCI 工作流。 Model 可以解释 Result/Report，但不能修改中央 Acceptance Builder 基于 Validator observations、Profile 和 来源链推导的结论。
What ships with it
42 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.
- acceptance-profiles/supplied-pauli-statevector-v1.json 5.3 KB
- agents/openai.yaml 387 B
- artifacts/convergence-trace.schema.json 2.5 KB
- artifacts/exact-reference.schema.json 1.7 KB
- artifacts/ground-state-result.schema.json 2.3 KB
- artifacts/hamiltonian-manifest.schema.json 3.0 KB
- artifacts/problem-spec.schema.json 2.9 KB
- artifacts/resource-estimate.schema.json 1.3 KB
- capability.yaml 4.0 KB
- core/contracts.mjs 11 KB runs code
- evals/fixtures/identity-shift.json 217 B
- evals/fixtures/invalid/qaoa.json 150 B
- evals/fixtures/invalid/sector-leakage.json 192 B
- evals/fixtures/invalid/wrong-unit.json 169 B
- evals/fixtures/invalid/y-pauli.json 159 B
- evals/fixtures/low-budget.json 297 B
- evals/fixtures/requests/diagonal.json 1017 B
- evals/fixtures/requests/protocol-fixture.json 1.3 KB
- evals/fixtures/requests/xx-coupled.json 1012 B
- evals/fixtures/term-permutation.json 228 B
- evals/run-evals.mjs 8.7 KB runs code
- evals/suite.json 1.8 KB
- evidence/eval-report-v1.json 1.4 KB
- evidence/validator-report-v1.json 1011 B
- inputs/request.schema.json 4.1 KB
- LICENSE 1.1 KB
- NOTICE 644 B
- README.md 3.5 KB
- references/NUMERICAL-CONVENTIONS.md 2.3 KB
- references/SCOPE.md 1.4 KB
- reproduction-profiles/independent-statevector-v1.json 1.4 KB
- scripts/lib/canonicalize.mjs 9.4 KB runs code
- scripts/lib/deterministic-optimizer.mjs 4.5 KB runs code
- scripts/lib/domain-error.mjs 327 B runs code
- scripts/lib/exact-sector-reference.mjs 1012 B runs code
- scripts/lib/pauli-statevector.mjs 4.7 KB runs code
- scripts/solve.mjs 8.4 KB runs code
- test/solver.test.mjs 16 KB runs code
- test/validator.test.mjs 15 KB runs code
- validators/lib/independent-science.mjs 15 KB runs code
- validators/result-validation-bundle.schema.json 3.2 KB
- validators/validate-result.mjs 33 KB runs code
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.
- 2d ago Changed d611358c2fad
- 8d ago First seen · 70 lines · 103 tokens per session scan A 2ee1416308cb
quantum-ground-state is a skill published in the GitHub repository xi-zhao/OpenQuantum (48 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 943 once invoked, about $0.0005 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
academic-research
Search academic papers, scholarly articles, and research publications through SandBase. Use when asked for literature review, academic citations, scholarly research, paper discovery, or scientific evidence gathering.
academic-trend-research
Research emerging academic trends by combining scholarly databases, web sources, and news to identify rising research areas, breakthrough papers, and shifting scientific consensus. Ideal for R&D teams tracking frontier science.
alexandria
Reach for this when a research question needs cited sources across academic papers, public domain books, legal records, government archives, security advisories, news, or developer documentation. Alexandria is an MCP server backed by 152 public digital libraries; use it whenever an answer should point at real…
memory-search-mcp
Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.
ml-experiment-review
Use this skill when reviewing an ML experiment, benchmark, ablation, or training run.
noodle-biomedical-literature-discovery
Find, inspect, compare, and traverse public biomedical research literature. Use for PubMed or scholarly paper search, publication details, PMID/DOI/PMCID lookup, related papers, citation paths, semantic literature neighborhoods, corpus coverage, or questions asking what research exists about a gene, variant…