Name: huangcl
Author: ZhangXin8069

Imported from ZhangXin8069/PyQCD (refer/huangcl/AGENTS.md). Install upstream with npx skills add ZhangXin8069/PyQCD --skill huangcl. Copyright stays with the author.

AGENTS.md — examples/huangcl

黄 CL 的 L24x72 系综数据 4 步分析流水线：CuPy GPU 计算（步骤 0–1）+ Chroma IOG 二进制分析（步骤 2、4）。

流水线步骤

步骤	目录	计算	分析
0	`00_contract/`	CuPy OPE（Clover F_{μν}、Wilson 线）+ 质子 2pt	—
1	`01_proton_contract/`	CuPy 质子 2pt 蒸馏	—
2	`02_ratio/`	—	3pt/2pt 比值 R(z)+jackknife、多参数拟合、Chroma IOG 3pt 提取
4	`04_proton_energy/`	—	IOG 2pt 质子有效能量、cosh meff + 平台拟合

（步骤 3 跳过——中间分析，无最终结果。）

目录模式

每步：00_code/（Python 脚本）、01_submit/（Slurm 模板 + multi.sh 任务生成）、02_input/（生成的逐组态输入）。模板用占位符（=NT=、=NX=、=CONF= 等）经 multi.sh sed 替换。数据路径指向集群（/public/...），仅集群可解析。

重复脚本：2pt_proton_Cg5gmu_L32x64_mom2_xdir_gpu.py 与 Calc_ope_unpol.py/Operator.py 同时存在于 examples/donghx/ 与 huangcl 的 00_contract/00_code/——huangcl 副本为本流水线所用版本，可能独立修改。

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Install huangcl and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "zhangxin8069-pyqcd-huangcl", "kind": "skill", "name": "huangcl", "description": "黄 CL 的 L24x72 系综数据 4 步分析流水线：CuPy GPU 计算（步骤 0–1）+ Chroma IOG 二进制分析（步骤 2、4）。", "publisher": "ZhangXin8069", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "黄 CL 的 L24x72 系综数据 4 步分析流水线：CuPy GPU 计算（步骤 0–1）+ Chroma IOG 二进制分析（步骤 2、4）。" ], "primary": false, "metadata": { "source": { "provider": "github-agents", "repository": "https://github.com/ZhangXin8069/PyQCD", "path": "refer/huangcl/AGENTS.md", "ref": "3a61844dbb154d0fdb148f6a6d772e9c83eda580", "url": "https://github.com/ZhangXin8069/PyQCD/blob/3a61844dbb154d0fdb148f6a6d772e9c83eda580/refer/huangcl/AGENTS.md", "key": "ZhangXin8069/PyQCD/refer/huangcl/AGENTS.md" } }, "instructions": "# AGENTS.md — examples/huangcl\n\n黄 CL 的 L24x72 系综数据 4 步分析流水线：CuPy GPU 计算（步骤 0–1）+ Chroma IOG 二进制分析（步骤 2、4）。\n\n## 流水线步骤\n\n| 步骤 | 目录 | 计算 | 分析 |\n|---|---|---|---|\n| 0 | `00_contract/` | CuPy OPE（Clover F_{μν}、Wilson 线）+ 质子 2pt | — |\n| 1 | `01_proton_contract/` | CuPy 质子 2pt 蒸馏 | — |\n| 2 | `02_ratio/` | — | 3pt/2pt 比值 R(z)+jackknife、多参数拟合、Chroma IOG 3pt 提取 |\n| 4 | `04_proton_energy/` | — | IOG 2pt 质子有效能量、cosh meff + 平台拟合 |\n\n（步骤 3 跳过——中间分析，无最终结果。）\n\n## 目录模式\n\n每步：`00_code/`（Python 脚本）、`01_submit/`（Slurm 模板 + `multi.sh` 任务生成）、`02_input/`（生成的逐组态输入）。模板用占位符（`=NT=`、`=NX=`、`=CONF=` 等）经 `multi.sh` sed 替换。数据路径指", "cost": { "context_tokens": 201 } }

huangcl

About

AGENTS.md — examples/huangcl

流水线步骤

目录模式

Use it

Install huangcl and it becomes one more candidate the router can pick - when it fits.

Manifest

Reviews