Communityv1.0.45

Privora · A股/港股/黄金/基金 多资产 量化分析 · 量化回测 · 模拟盘 · 实时告警 · 风险监控 · Python 策略 · AI Agent

Privora · AI Agent 投资工作流平台 — Bearer Token 即接入 /agent/skills/execute 通用 dispatcher,覆盖 A 股/港股/黄金/基金/财报数据 + Python 回测(含 sandbox)+ 模拟交易 + 组合归因(α/β TWR)+ 云端告警 + 流...

2.2kdownloads1starsGuangfuWu
View on ClawHubBack to Skills

Skill Details

Slug
privora-cn-quant
Latest Version
1.0.45
Author
GuangfuWu
Published
Mar 30, 2026
Updated
Jul 17, 2026
Total Versions
39

How to Install

  1. 1 on OpenClawdBots (takes under 60 seconds).
  2. 2Open your bot dashboard and go to the Skills tab.
  3. 3Switch to the ClawHub tab and search for Privora · A股/港股/黄金/基金 多资产 量化分析 · 量化回测 · 模拟盘 · 实时告警 · 风险监控 · Python 策略 · AI Agent.
  4. 4Click Install and the skill is deployed to your bot automatically.

Changelog — v1.0.45

v1.0.45 - Named-param flat calling convention for lg_agent_exec.sh (skillId key=value key:=json --json), replacing hand-assembled envelope JSON as the default call shape - the gateway auto-classifies flat keys into pathParams/query/body per each skill's path template + method, eliminating a class of 500s from params landing in the wrong envelope layer. Per-skill params are now discoverable: GET /agent/skills returns params + exampleInvocation for every skill, and lg_agent_list.sh describe <skillId> shows one skill's schema + example on demand. key=value is always a JSON string (protects leading zeros like stock_num=000135); key:=value parses as raw JSON (number/bool/array/object) and fails loud on parse error instead of silently degrading to a string; --json '<obj>' remains the escape hatch for array/nested bodies and can be mixed with flat keys in the same call. The old full-envelope invocation (single JSON-object argument) is 100% backward compatible and unaffected. SKILL.md slimmed down accordingly: flat-key form is now the primary Quick Start path, with the envelope form demoted to a compatibility appendix.