ZA_analysis
Manifest validModel training stage — end-to-end analysis, model training, and estimation for asset pricing and machine learning research. Ships one skill.
Z Research · Analysis Stage
模型训练与结论：端到端分析、模型训练、估计。资产定价 + 机器学习/深度学习研究工作流的一部分。
安装
dsh plugin --profile <你的profile> add zresearch-analysis
或从 npm：
npm install zresearch-analysis
用法
安装后，在 DSH 会话中按需触发（模型会根据任务自动加载对应 skill）：
- 文献综述：问「帮我做文献综述 / 找相关论文」
- 数据处理：问「帮我找数据 / 评估数据集」
- 模型训练：问「跑回归 / 训练 ML 模型 / 横截面收益预测」
- 写报告：问「写论文 / 起草章节」
- 做 PPT：问「做演讲 PPT / Beamer / job market talk」
skill 结构
skills/zresearch-analysis/
├── SKILL.md # 主 skill 定义
└── references/ # 角色定义 + 领域校准
├── agents/ # worker/critic 角色
└── domain/ # domain-profile(资产定价+ML/DL)
领域
面向实证资产定价 + ML/DL：因子模型、横截面收益预测、GMM/SDF、预测回归、机器学习、深度学习。领域校准见 references/domain/domain-profile.md。
License
MIT
Comments
Loading…
Similar plugins
by Z-Asset
Report stage — academic paper writing for asset pricing and machine learning research. Ships one skill.
★ 0
MIT
TypeScript
Sep 16, 2026
dsh plugin --profile web add @zasset/za-reportby Z-Asset
PPT stage — presentation generation (Beamer/Quarto) from the paper for asset pricing and machine learning research. Ships one skill.
★ 0
MIT
TypeScript
Sep 16, 2026
dsh plugin --profile web add @zasset/za-pptTraining attestation — reproducible, attributable, auditable off-site standardized training for asset pricing. Hard-gates four failure modes (half-refresh, hash mismatch, unknown-read-as-pass, master
★ 0
dsh plugin --profile web add @z-asset/attestby HaoyueQin
Reasoning-effort editing for third-party models in DeepSeek Harness: per-model thinking levels with a knowledge base + protocol inference, edited inside the official Models page card.
★ 47
↓ 1k/wk
MIT
TypeScript
Sep 30, 2026
dsh plugin --profile web add dsh-better-reasoning-effortAutomatic model-tier routing for DeepSeek Harness: one user instruction enters, one tier decision comes out — complex intent is planned on the strong tier and implemented on the cheap tier, simple int
★ 1
↓ 829/wk
Apache-2.0
TypeScript
dsh plugin --profile web add dsh-autotierby zhangzhenwen1
Auto-adjust model reasoning effort per task (off/low/high/max): task classification, [effort=...] markers, in-turn error escalation, DeepSeek peak-pricing-period capping with countdown notices, and ma
★ 0
↓ 61/wk
MIT
JavaScript
Aug 30, 2026
dsh plugin --profile web add dsh-task-effort