863683348/dsh-plugin-finance-data
Finance data toolkit for DeepSeek Harness agents: number/currency formatting (incl. Chinese wan/yi units), return & CAGR math, valuation and profitability ratios, PV/FV, risk metrics, and a data-quality checklist
PROJECT TOPICS
INSTALL REFERENCE
dsh plugin --profile web add github:863683348/dsh-plugin-finance-data
该命令指向仓库当前默认分支；尚无绑定当前 commit 的完整验证结果。
PROJECT README
A finance data toolkit for DeepSeek Harness agents: guaranteed-correct number formatting, return math, ratios, time value, and risk metrics. The model explains; the plugin does the arithmetic.
dsh plugin --profile <profile> add dsh-plugin-finance-dataRestart DSH. The finance_data tool is registered host-wide.
| action | purpose |
|---|---|
format |
Number/currency/percent formatting with thousands separators and Chinese 万/亿 units |
return |
Simple, log, and annualized (CAGR-style) returns |
ratio |
PE, PB, ROE, ROA, gross/net margin, debt-to-equity |
value |
Present value, future value, implied rate |
risk |
Mean, volatility, max drawdown, historical VaR(95), Sharpe from a return series |
checklist |
Data-quality checklist (source, as-of date, units, definitions) |
All optional, on the composition row's config:
| key | default | meaning |
|---|---|---|
personaSection |
true |
register the finance prompt-guidance section |
sectionOrder |
6 |
prompt section order (persona is 0, ascending) |
Pure logic (lib/finance.js) has zero DSH/Cordis imports and is unit-tested in isolation; lib/index.js is the thin Cordis plugin wiring the tool and the prompt section. No filesystem access — deterministic and side-effect free.
MIT
CLASSIFICATION EVIDENCE
系统优先读取 GitHub Topics，再与站内分类词典和词根规则比对。当前命中： data。
liustack
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
Anionex
为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
tong-io
TongFlow — multimodal workflow studio and engine (canvas + Python plugin engine) and dsh-tongflow, the DeepSeek Harness studio plugin