Agent skill

Chanlun Pattern Recognition

Detects Chan theory price structures (fractals, strokes, pivots) and first, second and third buy and sell points from OHLCV bars using the czsc library, in Chinese.

MITAuto-check passedBusiness, Finance & HR

SKILL.md written in Chinese; this summary is our English description.

Install Chanlun Pattern Recognition

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill chanlun -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading chanlun --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent/src/skills/chanlun .claude/skills/chanlun && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "chanlun" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/chanlun into .claude/skills/chanlun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chanlun", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/chanlun

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill chanlun -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading chanlun --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agent/src/skills/chanlun .agents/skills/chanlun && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "chanlun" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/chanlun into .agents/skills/chanlun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chanlun", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill chanlun -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading chanlun --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agent/src/skills/chanlun .cursor/skills/chanlun && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "chanlun" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/chanlun into .cursor/skills/chanlun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chanlun", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/HKUDS/Vibe-Trading.git --path agent/src/skills/chanlun

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill chanlun -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading chanlun --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agent/src/skills/chanlun .gemini/skills/chanlun && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "chanlun" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/chanlun into .gemini/skills/chanlun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chanlun", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading chanlun

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill chanlun -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .github/skills && cp -r skills-src/agent/src/skills/chanlun .github/skills/chanlun && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "chanlun" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/chanlun into .github/skills/chanlun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chanlun", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill chanlun -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading chanlun --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agent/src/skills/chanlun .opencode/skills/chanlun && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "chanlun" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/chanlun into .opencode/skills/chanlun/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chanlun", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: chanlun
GitHub stars: 35k
Token cost: ~658 tokens
SKILL.md length: 147 words
Files: 8 (incl. references)
Skills in repo: 89
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Detects Chan theory price structures (fractals, strokes, pivots) and first, second and third buy and sell points from OHLCV bars using the czsc library, in Chinese.

Marking fractals, strokes and pivot zones on a price series
SKILL.md covers 用途, 核心概念, 买卖点体系 and 依赖安装, plus 5 more sections
Runs Python scripts from its folder; calls pip
Generating buy and sell point signals from candlestick data for a backtest

What it does

The skill follows the Chan theory chain: raw candlesticks, merging of contained bars, fractal detection, strokes, pivot zones and finally buy and sell points. A table defines fractals (a top where the middle bar is highest, a bottom where it is lowest), strokes between adjacent opposite fractals, and pivots made of at least three strokes. First, second and third buy and sell points are described, each with its own reference page, and the work applies to any market with OHLCV data, including A-shares, crypto and futures.

Implementation uses the `czsc` package, version 0.9.68 or newer, installed with `pip install czsc requests pandas`. It is pure Python with an optional Rust backend and supports incremental updates. The text lists signal functions from `czsc.signals.cxt`, including pattern classification for 3, 5, 7, 9 and 11 strokes, and sets a signal convention of 1 for long, -1 for short and 0 for flat. Input is a list of `RawBar` objects with fields such as time, frequency, prices and volume. An example signal engine script is bundled.

When your agent uses it

Marking fractals, strokes and pivot zones on a price series
Generating buy and sell point signals from candlestick data for a backtest
Classifying three-, five- or seven-stroke patterns across several timeframes

Example prompts

“Run chanlun analysis on the daily bars in data/btc_daily.csv and list the buy and sell points found.”
“用缠论识别这只股票的分型、笔和中枢，并说明最近一个三买信号。”
“Wrap the czsc signals into a signal engine that outputs 1, -1 or 0 for my backtester.”

Requirements

Python with `czsc`, `requests` and `pandas` installed
OHLCV bar data for the instrument

What it can do on your machine

Read from SKILL.md and the folder at commit b1f6ce7. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Chanlun Pattern Recognition loads about 658 tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 26 tokens; SKILL.md has 147 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~26
When it runs · the whole SKILL.md, loaded when a task matches: ~658
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/Vibe-Trading at commit b1f6ce7, republished under its MIT licence (© HKUDS). 147 words, ~658 tokens.

Download SKILL.mdSave it as .claude/skills/chanlun/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.

name: chanlun
description: 基于缠论（缠中说禅）的形态识别引擎，使用czsc库自动检测K线分型、笔、中枢，并生成一买/一卖/二买/二卖/三买/三卖等买卖点信号。支持多周期分析和形态分类（3/5/7/9/11笔形态）。
category: strategy

缠论形态识别

用途

基于缠中说禅理论的价格形态识别。缠论是一套完全基于价格结构的技术分析方法，核心链路：

原始K线 → 去包含处理 → 分型识别 → 笔检测 → 中枢构建 → 买卖点判定

适用于任何有 OHLCV 数据的市场（A股、加密货币、期货等）。

核心概念

概念	说明	详细文档
分型（FX）	顶分型：中间K线最高；底分型：中间K线最低	分型
笔（BI）	相邻顶底分型之间的一段走势，最小单元	笔
中枢（ZS）	至少3笔构成的价格重叠区域，趋势的核心	中枢

买卖点体系

买卖点	含义	详细文档
一买/一卖	趋势结束后的第一个反转信号（背驰点）	一买一卖
二买/二卖	一买/一卖后回调不破底/顶的确认信号	二买二卖
三买/三卖	中枢上移/下移后回调不进入前中枢的信号	三买三卖

依赖安装

bash

pip install czsc requests pandas

快速上手

python

from czsc import CZSC, RawBar, Freq
from datetime import datetime

# 准备 RawBar 列表（需按时间正序排列）
bars = [
    RawBar(symbol="BTC-USDT", id=0, dt=datetime(2026,1,1),
           freq=Freq.D, open=70000, close=71000,
           high=72000, low=69000, vol=1000, amount=71000000),
    # ... 更多K线
]

# 创建分析器，自动检测分型/笔/中枢
c = CZSC(bars)

# 访问结果
print(c.bi_list)    # 已完成的笔
print(c.bars_ubi)   # 未完成笔中的K线

可用信号函数（czsc.signals.cxt）

czsc 内置 43 个缠论信号函数，核心如下：

函数	说明	类型
`cxt_first_buy_V221126`	一买信号	买卖点
`cxt_first_sell_V221126`	一卖信号	买卖点
`cxt_second_bs_V230320`	均线辅助二买二卖	买卖点
`cxt_third_bs_V230318`	均线辅助三买三卖	买卖点
`cxt_third_buy_V230228`	笔三买辅助	买卖点
`cxt_double_zs_V230311`	两中枢组合判断BS1	中枢
`cxt_three_bi_V230618`	三笔形态分类	形态
`cxt_five_bi_V230619`	五笔形态分类	形态
`cxt_seven_bi_V230620`	七笔形态分类	形态
`cxt_nine_bi_V230621`	九笔形态分类	形态
`cxt_eleven_bi_V230622`	十一笔形态分类	形态
`cxt_bi_base_V230228`	BI基础信号（方向/转折）	基础
`cxt_bi_end_V230312`	MACD辅助笔结束	辅助
`cxt_range_oscillation_V230620`	区间震荡判断	辅助
`cxt_zhong_shu_gong_zhen_V221221`	大小级别中枢共振	中枢

信号约定

信号引擎输出：1=做多，-1=做空，0=观望
做多条件：一买信号或三笔向上盘背或五笔类一买
做空条件：一卖信号或三笔向下盘背或五笔类一卖
中枢辅助：价格在中枢下沿附近做多优势，上沿附近做空优势

数据格式

czsc 接受 List[RawBar]，每个 RawBar 包含：

字段	类型	说明
symbol	str	标的代码
id	int	序号（从0开始）
dt	datetime	时间
freq	Freq	频率：`Freq.F1/F5/F15/F30/F60/D/W/M`
open	float	开盘价
close	float	收盘价
high	float	最高价
low	float	最低价
vol	float	成交量
amount	float	成交额

实现方式

使用 czsc 库（v0.9.68+），基于纯 Python 实现（可选 Rust 加速后端）。支持增量更新，适合实时分析。

Files

SKILL.md and 7 other files (references) in agent/src/skills/chanlun of HKUDS/Vibe-Trading.

SKILL.md
example_signal_engine.py
references/买卖点/一买一卖.md
references/买卖点/三买三卖.md
references/买卖点/二买二卖.md
references/核心概念/中枢.md
references/核心概念/分型.md
references/核心概念/笔.md

Open the folder on GitHubat commit b1f6ce7

Compare with similar skills

Chanlun Pattern Recognition next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Chanlun Pattern Recognition compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Chanlun Pattern Recognition this skillHKUDS/Vibe-Trading	35k	—	~658	Automated safety check: Pass	MIT	yesterday
Tushare Datazillionare/zillionare	321	2 repos	~2.3k	Automated safety check: Pass	None	today
WorldQuant BRAIN Alpha ResearchQuantML-Research/wq-alpha-research	407	—	~4.9k	Automated safety check: Pass	None	3 mo ago
Polymarket Tennislivetennisapi/livetennisapi-mcp	152	—	~3k	Automated safety check: Pass	MIT	3 days ago
Tiger Brokers OpenAPI SDKqusong0627/QuantMind	1.7k	—	~1.4k	Automated safety check: Pass	Apache-2.0	today
Quant Blog Writingzillionare/zillionare	321	—	~895	Automated safety check: Pass	None	today

Similar skills

Tushare Data
zillionare/zillionare
面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求，转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。
321 GitHub starsUsed in 2 repos~2.3k tokens
Business, Finance & HRAuto-check passed
WorldQuant BRAIN Alpha Research
QuantML-Research/wq-alpha-research
Chinese-language playbook for WorldQuant BRAIN alphas: choose fields, write expressions, backtest, diagnose check failures, tune turnover, submit and build portfolios.
407 GitHub stars~4.9k tokensUpdated 3 mo ago
Business, Finance & HRAuto-check passed
Polymarket Tennis
livetennisapi/livetennisapi-mcp
Build observe-only Polymarket and Kalshi tennis market tooling on the polymarket-tennis Python package (MIT) plus the Live Tennis API free tier.
152 GitHub stars~3k tokensUpdated 3 days ago
Business, Finance & HRAuto-check passed
Tiger Brokers OpenAPI SDK
qusong0627/QuantMind
Covers the Tiger Brokers OpenAPI Python SDK for market data, stock, futures and options trading, push subscriptions, a CLI and an MCP server, defaulting to paper trading.
1.7k GitHub stars~1.4k tokensUpdated today
Business, Finance & HRAuto-check passed
Quant Blog Writing
zillionare/zillionare
撰写文笔精炼、富有深度的量化交易博文，论点清晰、证据确凿、叙事层次更加丰富。适用于量化交易博文、因子研究、回测复盘、数据源排查、市场微观结构、策略原理、风险控制、职业观察、量化人物故事等选题。文章将聚焦具体角度，提供详实的大纲、证据规划及成稿，力求内容兼具思想深度与诚实性，而非单纯口号式宣传；同时，通过人物经历、引言、贡献及行业背景的融入，让文章更具可读性和吸引力。
321 GitHub stars~895 tokensUpdated today
Business, Finance & HRAuto-check passed
Web3 Polymarket
Polymarket/agent-skills
Polymarket integration for prediction market trading on Polygon.
192 GitHub starsUsed in 1 repo~2k tokens
Backend & APIsAuto-check passed

Questions about Chanlun Pattern Recognition

What does Chanlun Pattern Recognition do?

Detects Chan theory price structures (fractals, strokes, pivots) and first, second and third buy and sell points from OHLCV bars using the czsc library, in Chinese. The skill follows the Chan theory chain: raw candlesticks, merging of contained bars, fractal detection, strokes, pivot zones and finally buy and sell points. A table defines fractals (a top where the middle bar is highest, a bottom where it is lowest), strokes between adjacent opposite fractals, and pivots made of at least three strokes.

When should I use Chanlun Pattern Recognition?

Chanlun Pattern Recognition fits situations like: marking fractals, strokes and pivot zones on a price series; generating buy and sell point signals from candlestick data for a backtest; classifying three-, five- or seven-stroke patterns across several timeframes.

How do I install Chanlun Pattern Recognition in Claude Code?

Run `npx skills add HKUDS/Vibe-Trading --skill chanlun -a claude-code`. Or copy the skill folder (agent/src/skills/chanlun in HKUDS/Vibe-Trading) into .claude/skills/chanlun in your project. Claude Code loads it when a task matches its description.

How do I install Chanlun Pattern Recognition in Codex?

Run `npx skills add HKUDS/Vibe-Trading --skill chanlun -a codex`. Or copy the skill folder (agent/src/skills/chanlun in HKUDS/Vibe-Trading) into .agents/skills/chanlun in your project. Codex loads it when a task matches its description.

Can I use Chanlun Pattern Recognition in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/Vibe-Trading --skill chanlun -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chanlun, .gemini/skills/chanlun, .github/skills/chanlun and .opencode/skills/chanlun in your project.

What does Chanlun Pattern Recognition need to run?

Going by SKILL.md and its folder, Chanlun Pattern Recognition needs Python for the scripts in its folder and the command-line tools its instructions call (pip). Our summary lists: Python with `czsc`, `requests` and `pandas` installed; OHLCV bar data for the instrument.

Does Chanlun Pattern Recognition access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Chanlun Pattern Recognition safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Chanlun Pattern Recognition use?

Chanlun Pattern Recognition is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Chanlun Pattern Recognition use?

About 658 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.

What are the alternatives to Chanlun Pattern Recognition?

Skills that share tags, products or a category with Chanlun Pattern Recognition: Tushare Data (zillionare/zillionare, 321 stars), WorldQuant BRAIN Alpha Research (QuantML-Research/wq-alpha-research, 407 stars), Polymarket Tennis (livetennisapi/livetennisapi-mcp, 152 stars) and Tiger Brokers OpenAPI SDK (qusong0627/QuantMind, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Chanlun Pattern Recognition?

HKUDS (a GitHub organization) maintains it in HKUDS/Vibe-Trading, which has 35,097 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 9, 2026.

Source: HKUDS/Vibe-Trading on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Chanlun Pattern Recognition

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

缠论形态识别

用途

核心概念

买卖点体系

依赖安装

快速上手

可用信号函数（czsc.signals.cxt）

信号约定

数据格式

实现方式

Files

Compare with similar skills

Similar skills

More from HKUDS/Vibe-Trading

Related

Questions about Chanlun Pattern Recognition