Description

多智能体金融分析平台，支持股票研究、市场预测、财报解读与量化回测策略构建，覆盖全球市场数据分析。

README (SKILL.md)

FinRobot 多智能体 (finrobot-multi-agent)

Name: Finrobot Multi Agent
Author: tangweigang-jpg

多智能体金融分析平台，支持股票研究、市场预测、财报解读与量化回测策略构建，覆盖全球市场数据分析。

Pipeline

data_collection -> data_storage -> factor_computation -> target_selection -> trading_execution -> visualization

Top Use Cases (14 total)

FMP API Equity Research Report Generator (`UC-101`)

Investors need comprehensive equity research reports that combine financial statement analysis, peer comparisons, and recent news to make informed inv Triggers: equity research, financial analysis report, FMP API

Multi-Agent Annual Report Generator (`UC-102`)

Financial analysts require automated generation of customized financial analysis reports that can interact with clients, gather requirements, and prod Triggers: annual report, financial report generation, multi-agent

OpenBB Financial Data Agent (`UC-104`)

Users need an intelligent agent interface to access OpenBB's comprehensive financial data capabilities including market data, fundamentals, and techni Triggers: openbb, financial data agent, market data

For all 14 use cases, see references/USE_CASES.md.

Execute trigger: When user intent matches intent_router.uc_entries[].positive_terms AND user uses action verb (run/execute/跑/执行/backtest/fetch/collect)

What I'll Ask You

Target market: A-share (default), HK, or crypto? (US stocks in ZVT are half-baked — stockus_nasdaq_AAPL exists but coverage is thin)
Data source / provider: eastmoney (free, no account), joinquant (account+paid), baostock (free, good history), akshare, or qmt (broker)?
Strategy type: MACD golden-cross, MA crossover, volume breakout, fundamental screen, or custom factor?
Time range: start_timestamp and end_timestamp for backtest period
Target entity IDs: specific stocks (stock_sh_600000) or index components (SZ1000)?

Semantic Locks (Fatal)

ID	Rule	On Violation
`SL-01`	Execute sell orders before buy orders in every trading cycle	halt
`SL-02`	Trading signals MUST use next-bar execution (no look-ahead)	halt
`SL-03`	Entity IDs MUST follow format entity_type_exchange_code	halt
`SL-04`	DataFrame index MUST be MultiIndex (entity_id, timestamp)	halt
`SL-05`	TradingSignal MUST have EXACTLY ONE of: position_pct, order_money, order_amount	halt
`SL-06`	filter_result column semantics: True=BUY, False=SELL, None/NaN=NO ACTION	halt
`SL-07`	Transformer MUST run BEFORE Accumulator in factor pipeline	halt
`SL-08`	MACD parameters locked: fast=12, slow=26, signal=9	halt

Full lock definitions: references/LOCKS.md

Top Anti-Patterns (14 total)

AP-MACRO-DATA-001: SEC EDGAR Rate Limit Violation
AP-MACRO-DATA-002: Temporal Knowledge Graph Look-Ahead Bias
AP-MACRO-DATA-003: Technical Indicator Look-Ahead Bias via Missing Shift

All 14 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-074. Evidence verify ratio = 11.5% and audit fail total = 36. Generated results may have uncaptured requirement gaps. Verify critical decisions against source files (LATEST.yaml / LATEST.jsonl).

Reference Files

File	Contents	When to Load
references/seed.yaml	V6+ 全量权威 (source-of-truth)	有行为/决策争议时必读
references/ANTI_PATTERNS.md	14 条跨项目反模式	开始实现前
references/WISDOM.md	跨项目精华借鉴	架构决策时
references/CONSTRAINTS.md	domain + fatal 约束	规则冲突时
references/USE_CASES.md	全量 KUC-* 业务场景	需要完整示例时
references/LOCKS.md	SL-* + preconditions + hints	生成回测/交易代码前
references/COMPONENTS.md	AST 组件地图（按 module 拆分）	查 API 时

Compiled by Doramagic crystal-compilation-v6.1 from finance-bp-074 blueprint at 2026-04-22T13:00:27.479397+00:00. See human_summary.md for non-technical overview.

Usage Guidance

This skill appears to be a substantial multi-agent finance blueprint, but its runtime expectations are not fully declared. Before installing or running: 1) Inspect SKILL.md and seed.yaml yourself — they expect Python 3.12+, the 'uv' package manager, and the zvt package. 2) Do not provide any secret API keys blindly; the skill references multiple data providers but does not declare required credentials. 3) Run it in a sandboxed environment (container or VM) so its pip installs and ~/.zvt writes cannot affect your primary system. 4) If you plan to use live trading features, verify the semantic locks (T+1, next-bar execution, MACD params) and confirm rate-limiting and legal/regulatory constraints (e.g., SEC EDGAR). 5) Ask the publisher for a clear install spec and an explicit list of required environment variables/credentials; absence of those is the main coherence problem. If you cannot verify these items, treat the skill cautiously (do not run it with real credentials or on your main workstation).

Capability Analysis

Type: OpenClaw Skill Name: finrobot-multi-agent Version: 0.3.3 The bundle is a comprehensive financial analysis platform (finrobot-multi-agent) that coordinates multiple AI agents for equity research, market forecasting, and backtesting. It includes extensive domain-specific constraints and 'semantic locks' in seed.yaml and SKILL.md to prevent common quantitative errors like look-ahead bias and SEC rate limit violations. While it contains a cryptographic vulnerability (unsalted SHA-256 hashing mentioned in finance-C-029/BD-029), the behavior is strictly aligned with its stated purpose and lacks evidence of intentional malice, data exfiltration, or harmful prompt injection.

Capability Tags

cryptorequires-oauth-tokenrequires-sensitive-credentials

Capability Assessment

⚠ Purpose & Capability

The name/description (financial multi-agent analysis, backtesting, report generation) matches the instruction content. However SKILL.md explicitly requires Python 3.12+, the 'uv' package manager, zvt package and data recorders (e.g., zvt.recorders.em.em_stock_kdata_recorder) and expects access to data providers (eastmoney/joinquant/akshare/OpenBB). None of those runtime requirements (binaries, packages, or config paths) are declared in the registry metadata, which is an incoherence: the skill will likely need local Python packages, writable data directories, and possibly API credentials to function.

⚠ Instruction Scope

The SKILL.md instructs the agent to reload seed.yaml, run precondition Python checks, and (on failure) run pip installs and recorder commands that touch the user's filesystem (~/.zvt) and may perform network calls to data providers. It also instructs agents to cite internal anti-patterns and re-read authoritative seed.yaml before decisions. These runtime instructions go beyond a passive text-only skill: they direct file reads, write-tests, package installs, and invocations of data recorders—which grant the agent broad I/O and network scope not reflected in the declared requirements.

ℹ Install Mechanism

There is no install spec in the registry (instruction-only), which reduces direct install risk. However SKILL.md's execution protocol and preconditions reference running python3 -m pip install zvt and running recorder commands; because these install steps are only described in prose (not declared in install spec), the agent may attempt to run package installs at runtime. That mismatch (no formal install recipe but prose telling the agent to install) is a behavioral risk and makes reproducible review harder.

⚠ Credentials

Registry metadata lists no required env vars or config paths, but SKILL.md references ZVT_HOME, and precondition checks read ~/.zvt and run zvt APIs. The skill also targets multiple external data providers (eastmoney, joinquant, FMP, OpenBB) that normally require API keys or accounts; no credentials are requested or described. The absence of declared credentials while the instructions imply access to providers and to local data directories is disproportionate and ambiguous.

ℹ Persistence & Privilege

The skill is not marked always:true and is user-invocable (normal). It does include protocols that instruct reading and writing user data directories and running package-install commands if preconditions fail. Autonomous invocation (disable-model-invocation: false) combined with the un-declared ability to perform installs and filesystem writes increases potential blast radius, but alone does not prove malicious intent.

Version History

v0.3.3

v0.3.3: bilingual metadata injected. H1 shows FinRobot 多智能体; tagline replaced with skill-specific Chinese hook; tags upgraded to Level 1-4.

v0.3.1

Remove install.sh — knowledge-only bundle. Host AI consumes directly from URL; no user-side installation needed. Fixes ClawHub suspicious flag.

v0.3.0

Doramagic crystal portfolio v0.3.0. Full 5-layer bp-009 standard. github.com/tangweigang-jpg/doramagic-skills

Metadata

Slug finrobot-multi-agent

Version 0.3.3

License MIT-0

All-time Installs 0

Active Installs 0

Total Versions 3

Frequently Asked Questions

What is Finrobot Multi Agent?

多智能体金融分析平台，支持股票研究、市场预测、财报解读与量化回测策略构建，覆盖全球市场数据分析。 It is an AI Agent Skill for Claude Code / OpenClaw, with 108 downloads so far.

How do I install Finrobot Multi Agent?

Run "/install finrobot-multi-agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Finrobot Multi Agent free?

Yes, Finrobot Multi Agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Finrobot Multi Agent support?

Finrobot Multi Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Finrobot Multi Agent?

It is built and maintained by Tang Weigang (@tangweigang-jpg); the current version is v0.3.3.

More Skills

Finrobot Multi Agent