start-here

start-here is a skill for Claude Code, Codex from ZICXR/A-Stock-Skills. It costs 65 tokens per session (837 once invoked), scanned A, original, MIT.

An introductory guide to a small collection of tools for Chinese stock-market data, screening, technical analysis, alerts, reports, and trading journals.

In plain words
What is it for?
Use it to fetch market prices or historical charts, calculate indicators such as MACD or RSI, screen stocks, monitor watchlists, send alerts, or review trades.
Why use it?
It helps users choose the right tool and see practical examples without learning the whole collection first.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to fetch market prices or historical charts, calculate indicators such as MACD or RSI, screen stocks, monitor watchlists, send alerts, or review trades.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zicxr/a-stock-skills/00-start-here
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ZICXR/A-Stock-Skills --skill 00-start-here
Clone the repo
git clone --depth 1 https://github.com/ZICXR/A-Stock-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for start-here

README.md
[![agentmods](https://agentmods.dev/badge/skills/zicxr/a-stock-skills/00-start-here/github.svg)](https://agentmods.dev/skills/zicxr/a-stock-skills/00-start-here)
Your own site
<a href="https://agentmods.dev/skills/zicxr/a-stock-skills/00-start-here"><img src="https://agentmods.dev/badge/skills/zicxr/a-stock-skills/00-start-here/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for start-here

Your own site · 80×15
<a href="https://agentmods.dev/skills/zicxr/a-stock-skills/00-start-here"><img src="https://agentmods.dev/badge/skills/zicxr/a-stock-skills/00-start-here.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00837
Opus 5 $0.00032 $0.00418
Sonnet 5 $0.00013 $0.00167
Haiku 4.5 $0.00006 $0.00084

Measured 12d ago against content hash cf211a90a6d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

start-here scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (main.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/00-start-here/SKILL.md · 79 lines

What it actually says

🚀 start-here: 30 秒上手

A-Stock-Skills 只有 10 个 Skill

# Skill 解决什么问题
1 astock-data-source 拿实时行情 / K 线 (多源 fallback)
2 astock-cache K 线 parquet 缓存 (5 秒 vs 30 分钟)
3 astock-utils 代码转换 / 交易日历 / 工具函数
4 watchlist-monitor 监控自选股 + 涨跌幅告警
5 screener 全市场筛选 (PE / 涨幅 / MACD 等)
6 stock-technical-analysis MA / MACD / KDJ / RSI / BOLL
7 report 每日复盘 + 个股研报
8 alerter 钉钉 / 微信 / 飞书 推送
9 trade-journal 🆕 AI 建议 vs 实盘 复盘
10 start-here 🆕 本文档

🎯 5 个真实场景

场景 1: 拿一只股票的行情

python skills/01-infra/astock-data-source/main.py get-realtime --code 601991

场景 2: 拿 60 日 K 线 + 算 MACD

from skills.Stock_Analysis.stock_technical_analysis.main import calc_macd
from skills.Stock_Infrastructure.astock_data_source.main import get_kline

df = get_kline("601991", days=60)
macd = calc_macd(df)
print(macd.tail())

场景 3: 全市场筛选 PE<20 + 涨幅>5%

python skills/05-quant/screener/main.py screen --pe-max 20 --pct-change-min 5

场景 4: 监控自选股

# 1. 生成配置模板
python skills/02-data-collection/watchlist-monitor/main.py init

# 2. 编辑 watchlist.yaml
# 3. 启动监控
python skills/02-data-collection/watchlist-monitor/main.py monitor

场景 5: 复盘 AI 准不准

# 1. 记录今天的 AI 建议
python skills/02-data-collection/trade-journal/main.py record --code 601991 --signal "MACD金叉" --target_price 3.50

# 2. 30 天后比对
python skills/02-data-collection/trade-journal/main.py review

⚠️ 3 件必读

  1. 数据源问题: 住宅 IP 跑东财会被封, astock-data-source v2.0 已自动 fallback
  2. 缓存很重要: 第一次跑慢, 第二次快 100 倍 (用 astock-cache)
  3. AI 不可信, 除非复盘: 用 trade-journal 记录, 30 天后看胜率

🛡️ 免责声明

本项目所有数据来源于公开市场数据, 仅供学习研究使用, 不构成任何投资建议。投资有风险, 入市需谨慎。

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 79 lines · 65 tokens per session scan A cf211a90a6d1

Subscribe to this mod's changes

start-here is a skill published in the GitHub repository ZICXR/A-Stock-Skills (25 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 837 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.