Description

CZSC 缠论技术分析工具，支持 K 线生成、笔线段识别、分型信号提取与 A 股回测可视化。

README (SKILL.md)

缠论技术分析 (czsc-chan-theory)

Name: Czsc Chan Theory
Author: tangweigang-jpg

CZSC 缠论技术分析工具，支持 K 线生成、笔线段识别、分型信号提取与 A 股回测可视化。

Pipeline

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

Top Use Cases (10 total)

Sphinx Documentation Configuration (`UC-101`)

Configuring Sphinx documentation builder for the czsc project, ensuring proper Python path setup and Rust version priority Triggers: documentation, sphinx, configuration

CZSC Performance Benchmarking (`UC-102`)

Benchmarking CZSC analysis performance with varying K-line counts to measure initialization speed and memory usage Triggers: benchmark, performance, speed

Volatility Classification Signal (`UC-104`)

Classifying market volatility into three tiers (low/middle/high) based on recent K-line price ranges for signal generation Triggers: volatility, classification, signal

For all 10 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 (25 total)

AP-ZVT-183: 除权因子为 inf/NaN 时直接参与乘法导致复权静默失败
AP-ZVT-179: 第三方数据接口超限后异常被吞噬，数据静默缺失
AP-ZVT-183B: HFQ（后复权）与 QFQ（前复权）K 线表使用错误导致因子计算漂移

All 25 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-091. Evidence verify ratio = 60.4% and audit fail total = 13. 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	25 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-091 blueprint at 2026-04-22T13:00:38.716020+00:00. See human_summary.md for non-technical overview.

Usage Guidance

This skill appears to be a CZSC/ZVT backtesting documentation bundle rather than packaged code. Key things to consider before installing or running it: - Inconsistency: SKILL.md requires Python 3.12+ and an 'uv' package manager and references zvt, but the registry metadata lists no required binaries or install steps. Expect to manually install Python packages (e.g., zvt) in your environment. - Runtime actions: The skill's preconditions include python -c checks and may prompt pip install commands and touch ~/.zvt. Run these commands in a controlled environment (virtualenv/container) rather than your primary workstation. - No credentials requested: The skill does not ask for API keys or secrets, reducing exfil risk, but it can read/write local files and run Python commands—treat accordingly. - Licensing/source: The skill lists a Proprietary license and no homepage/source URL; lack of upstream provenance increases risk. Prefer code from known repositories or request an explicit install/spec that lists exact dependencies. - Recommendation: If you want to use it, run in an isolated environment, inspect seed.yaml and the referenced files yourself, and avoid running any suggested pip installs or scripts until you validate the packages and versions. If possible, ask the publisher for an explicit dependency/install manifest (requirements.txt / lock file) and a source/homepage.

Capability Analysis

Type: OpenClaw Skill Name: czsc-chan-theory Version: 0.3.3 The `czsc-chan-theory` bundle is a highly sophisticated financial analysis and backtesting tool for the A-share market. It incorporates a robust framework of 'semantic locks' and 'fatal constraints' (detailed in `seed.yaml` and `SKILL.md`) designed to enforce financial regulatory compliance (e.g., T+1 settlement) and prevent common quantitative errors like look-ahead bias and survivorship bias. The bundle includes extensive educational references to 'anti-patterns' in other quant projects and provides clear security guidance against hardcoding credentials, indicating a high-integrity tool intended for professional research without any evidence of malicious intent or data exfiltration.

Capability Tags

cryptorequires-oauth-tokenrequires-sensitive-credentials

Capability Assessment

⚠ Purpose & Capability

The name/description describe a CZSC chan-theory backtesting/analysis tool for A‑share (uses ZVT/ZVT-style pipeline). However the package metadata declares no required binaries/env vars/install steps while SKILL.md explicitly states compatibility requirements (Python 3.12+ and 'uv' package manager) and the seed.yaml execution_protocol expects verifying/installing Python packages (e.g., zvt). This mismatch between declared requirements and the runtime instructions is an incoherence that could surprise users (the skill will assume Python/ZVT presence though the registry metadata doesn't require them).

ℹ Instruction Scope

SKILL.md and seed.yaml include explicit runtime preconditions that run python -c checks, may prompt pip installs (PC-01), and read/write under a ZVT home directory (pc checks touch ~/.zvt). Those actions are reasonable for a backtest tool, but they let the agent run arbitrary Python commands and create files in the user's home. The instructions also require re-reading the large seed.yaml and other reference files before behavior—this gives the skill broad discretion to inspect workspace files. No instructions request secrets or remote exfil endpoints.

✓ Install Mechanism

This is an instruction-only skill with no install spec or downloaded code; nothing will be written by an automated install step. That lowers risk. However the SKILL.md expects the host/agent to perform package verification and may direct the user/agent to run pip install for dependencies (e.g., zvt) at runtime.

✓ Credentials

The skill declares no required environment variables, no credentials, and no config paths. The runtime preconditions reference ZVT_HOME (a common config path) and will check/read/write ~/.zvt if present; this is proportional for a backtesting tool but should be noted since the skill may create or modify that directory.

ℹ Persistence & Privilege

always:false and default autonomous invocation are set (normal). The seed.yaml execution_protocol instructs agents to re-read seed.yaml and to run preconditions before executing behavior; this does not force permanent installation of the skill but does give it an operational requirement before actions. There is no explicit request to modify other skills or global agent settings in the provided files.

Version History

v0.3.3

v0.3.3: bilingual metadata injected. H1 shows 缠论技术分析; 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 czsc-chan-theory

Version 0.3.3

License MIT-0

All-time Installs 0

Active Installs 0

Total Versions 3

Frequently Asked Questions

What is Czsc Chan Theory?

CZSC 缠论技术分析工具，支持 K 线生成、笔线段识别、分型信号提取与 A 股回测可视化。 It is an AI Agent Skill for Claude Code / OpenClaw, with 99 downloads so far.

How do I install Czsc Chan Theory?

Run "/install czsc-chan-theory" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Czsc Chan Theory free?

Yes, Czsc Chan Theory is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Czsc Chan Theory support?

Czsc Chan Theory is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Czsc Chan Theory?

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

More Skills

Czsc Chan Theory