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.
npx skills add FTShare-Lab/FTShare-skill --skill hk-candlesticksgit clone --depth 1 https://github.com/FTShare-Lab/FTShare-skillWrote 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.
[](https://agentmods.dev/skills/ftshare-lab/ftshare-skill/hk-candlesticks)<a href="https://agentmods.dev/skills/ftshare-lab/ftshare-skill/hk-candlesticks"><img src="https://agentmods.dev/badge/skills/ftshare-lab/ftshare-skill/hk-candlesticks/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.
<a href="https://agentmods.dev/skills/ftshare-lab/ftshare-skill/hk-candlesticks"><img src="https://agentmods.dev/badge/skills/ftshare-lab/ftshare-skill/hk-candlesticks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00106 | $0.01264 |
| Opus 5 | $0.00053 | $0.00632 |
| Sonnet 5 | $0.00021 | $0.00253 |
| Haiku 4.5 | $0.00011 | $0.00126 |
Grade A, and why
hk-candlesticks 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 6d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
查询港股 K 线（hk-candlesticks）
1. 接口描述
| 项目 | 说明 |
|---|---|
| 接口名称 | 查询港股 K 线 |
| 外部接口 | /api/v2/market/data/hk/hk-candlesticks |
| 请求方式 | GET |
| 适用场景 | 按港股代码查询日/月/季/年 K 线（来源：hkshareeodprices）；请求与响应中的代码均为 5 位数字 + .HK，服务端会转换为库内 4 位 Wind 代码查询 |
2. 请求参数
| 参数名 | 类型 | 是否必填 | 描述 | 取值示例 | 备注 |
|---|---|---|---|---|---|
| trade_code | string | 是 | 港股代码 | 00700.HK | 支持 700 或 00700.HK，响应中统一为 5 位 + .HK |
| interval_unit | string | 是 | K 线间隔单位 | day | 取值：day、month、quarter、year（kebab-case 序列化） |
| until_date | string | 是 | 结束日期 | 2026-03-24 | 格式 YYYY-MM-DD |
| since_date | string | 否 | 开始日期 | 2026-01-01 | 不传则从库中最早数据起至 until_date |
| adjust_kind | string | 否 | 复权类型 | forward | 默认 forward（前复权）；none 为不复权 |
| interval_value | int | 否 | 间隔数值 | 1 | 当前仅支持 1，其它值会报错 |
| limit | int | 否 | 返回条数上限 | 100 | 日 K 在 SQL 层下推；月/季/年在聚合后截取最近 N 根 |
3. 响应说明
返回值为 HkCandlesticksResponse：trade_code + K 线数组 items。
HkCandlesticksResponse 结构
| 字段名 | 类型 | 是否可为空 | 说明 | 单位 |
|---|---|---|---|---|
| trade_code | String | 否 | 规范化后的港股代码（5 位 + .HK） |
- |
| items | Array | 否 | K 线列表，按日期升序 | - |
HkCandlestick 结构（items 元素）
| 字段名 | 类型 | 是否可为空 | 说明 | 单位 |
|---|---|---|---|---|
| open | String | 否 | 开盘价 | 元 |
| high | String | 否 | 最高价 | 元 |
| low | String | 否 | 最低价 | 元 |
| close | String | 否 | 收盘价 | 元 |
| date | String | 否 | 交易日 | YYYY-MM-DD |
| turnover | String | 否 | 成交额 | 元 |
| volume | int64 | 否 | 成交量 | 股 |
时区说明
since_date / until_date 及响应中的 date 均为 港交所交易日历（UTC+8 / 东八区） 日期。若 Agent 所在系统时区非东八区，计算「今天」等相对日期时应先转为东八区再传参。Handler 内置了东八区容错：若传入 ISO 8601 含时区的字符串，会自动转为东八区后截取日期部分。
4. 调用方式
本 handler 与上级 FTShare-hk-data/run.py 配合使用：
python <RUN_PY> hk-candlesticks --trade-code 00700.HK --interval-unit day --until-date 2026-03-24 --since-date 2026-03-01 --limit 20
python <RUN_PY> hk-candlesticks --trade-code 00700.HK --interval-unit month --until-date 2026-03-24 --limit 12
What ships with it
1 file 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.
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.
- 6d ago First seen · 82 lines · 106 tokens per session scan A 81653eed109c
hk-candlesticks is a skill published in the GitHub repository FTShare-Lab/FTShare-skill (63 stars, last pushed 2d ago), licensed MIT. It adds 106 tokens to every session and 1,264 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
defeatbeta-earnings-analysis
Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage. Fast-turnaround format focusing on beat/miss analysis, key metrics, updated estimates, and revised thesis. Includes 1-3 summary tables and 8-12 charts. Use when…
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.
update-pypi-dates
Refresh tracked PyPI last-updated dates in awesome-quant README.md. Use when the user asks to update PyPI dates, refresh PyPI metadata, or run update-pypi-dates.
defeatbeta-earnings-preview
Build pre-earnings analysis with normalized baselines, weighted decision models, company-specific veto gates, scenario frameworks, catalysts, historical reactions, and options-implied moves. Use before a company reports quarterly earnings to prepare positioning notes or bilingual three-page PDF reports.
defeatbeta-analyst
Professional financial analysis using 60+ market data APIs. Use for: company fundamentals (revenue, margins, EPS, balance sheet), valuation (P/E, P/B, P/S, PEG, DCF, intrinsic value), profitability (ROE, ROA, ROIC), growth trends (YoY revenue/earnings/FCF), earnings transcripts (key data, changes, guidance), industry…