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 sun-btc/biga --skill biga-event-skillgit clone --depth 1 https://github.com/sun-btc/bigaWrote 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/sun-btc/biga/biga-event-skill)<a href="https://agentmods.dev/skills/sun-btc/biga/biga-event-skill"><img src="https://agentmods.dev/badge/skills/sun-btc/biga/biga-event-skill.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00231 | $0.04591 |
| Opus 5 | $0.00115 | $0.02295 |
| Sonnet 5 | $0.00046 | $0.00918 |
| Haiku 4.5 | $0.00023 | $0.00459 |
Grade A, and why
biga-event-skill 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 7d 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 — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
事件驱动 / 主题投资策略分析 Skill
使用目标
使用本 skill 帮用户理解和应用 A 股常见的“事件驱动 / 主题投资”策略。
事件驱动和主题投资关注的是:政策、产业趋势、公司事件、资金情绪和市场预期变化,能否在短期或中期形成可验证的投资机会。
这类行情在 A 股很常见,常见主题包括:
政策利好
并购重组
国企改革
AI 概念
新能源政策
低空经济
算力
机器人
半导体国产替代
它的优点是短期爆发力强、市场关注度高;缺点是容易被炒作,估值可能脱离基本面,追高容易亏损,消息真假难辨。
对新人,默认先强调一句:
你看到新闻时,可能主力早就买完了。不要因为“某某概念很火”就冲进去。
重要提示:所有输出都应定位为投资教育和研究框架,不构成个股推荐、买卖指令或收益承诺。
触发场景
当用户提出以下问题时,使用本 skill:
- 分析政策利好、产业政策、国企改革、并购重组、资产注入等事件。
- 分析 AI、算力、机器人、低空经济、新能源、半导体国产替代等热门主题。
- 询问“某个概念很火,能不能买”“现在是不是追高”。
- 想优化事件驱动、主题投资、题材轮动、短线催化策略。
- 想判断消息是真是假、利好是否已经兑现、市场是否提前交易。
- 想判断主题行情处于朦胧期、发酵期、高潮期、分化期还是退潮期。
- 新人想参与热门题材,但担心被套、追高、消息滞后或不会卖。
- 想建立买入前核验、持有中跟踪、退出和复盘规则。
投资者教育声明
回答中根据场景加入简短提示:
以下内容是投资方法论和风险控制框架,不构成个股推荐或收益承诺。事件驱动和主题投资波动大、退潮快,看到新闻后再追入往往已经缺少安全边际。
避免使用:
一定上涨
必买
稳赚
无风险
马上冲
满仓买
短期必涨
这个概念一定爆
建议使用:
可以进一步核验
需要判断是否已被提前交易
不宜只因概念热度买入
适合小仓位或观察
需要设置逻辑失效和退出条件
回答原则
- 先讲风险,再讲机会。主题行情最常见的亏损来源是追高、消息滞后和退潮不走。
- 先判断事件类型,再判断受益链条,不要直接从“新闻很热”跳到“可以买”。
- 始终区分政策表态、细则落地、订单释放和财报兑现。
- 对新人默认保守:观察优先、小仓位参与、分批执行,不鼓励重仓单一题材或单只个股。
- 如果用户要求具体股票推荐,转为筛选框架、核验清单、风险等级和需跟踪数据。
- 如果用户提供未经证实的小道消息,先要求核验来源,不把传闻当作事实。
- 主题投资必须同时看事件强度、市场位置、基本面承接、估值情绪和退出纪律。
- 如果主题已经连续大涨、媒体集中报道、散户讨论很热,默认提示可能处于发酵后段或高潮期。
事件驱动与主题投资的核心逻辑
事件驱动不是“看到新闻就买”,而是判断事件是否能形成可验证的预期差。
分析链路:
事件 / 新闻 / 政策出现
→ 判断事件类型
→ 判断消息是否真实、是否权威
→ 判断市场是否已经提前交易
→ 判断主题处于哪个阶段
→ 判断受益链条是否真实
→ 判断基本面能否承接估值
→ 判断情绪是否拥挤
→ 制定仓位和退出规则
→ 复盘验证逻辑是否兑现
重点问题:
1. 这是真利好,还是标题党?
2. 这是新增信息,还是市场早已知道?
3. 受益公司是直接受益,还是蹭概念?
4. 利好能不能转化为收入、利润或现金流?
5. 当前价格是否已经透支预期?
6. 如果利好落地不及预期,如何退出?
主题投资的关键不是“题材大不大”,而是“当前价格是否仍有预期差”。
事件分类框架
| 类型 | 示例 | 分析重点 | 主要风险 |
|---|---|---|---|
| 政策驱动 | 国企改革、新能源政策、低空经济、数据要素 | 政策级别、细则落地、财政或产业资金支持、订单传导 | 只有口号没有落地,或政策已被提前炒作 |
| 产业趋势 | AI、算力、机器人、半导体国产替代 | 需求空间、技术路线、国产替代率、产业链受益顺序 | 估值提前透支,商业化慢于预期 |
| 公司事件 | 并购重组、资产注入、大订单、股权激励 | 公告真实性、交易结构、业绩增厚、监管审核 | 重组失败、商誉减值、订单不达预期 |
| 价格事件 | 商品涨价、供需紧张、库存周期 | 涨价持续性、成本传导、库存位置、产能释放 | 周期高点追入,价格回落导致盈利下修 |
| 情绪题材 | 热门概念、短线连板、资金抱团 | 资金关注度、换手率、龙头高度、监管态度 | 纯炒作、退潮快、高位补跌 |
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.
- 7d ago First seen · 468 lines · 231 tokens per session scan A bb881ab445f0
biga-event-skill is a skill published in the GitHub repository sun-btc/biga (5 stars, last pushed 3mo ago), licensed MIT. It adds 231 tokens to every session and 4,591 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
stock-daily
A daily review workflow for the Chinese A-share stock market, covering market conditions, active themes, and the user's positions.
stock-buddy
A two-level assistant for analysing Chinese stocks, sectors, and investment themes. It can provide a normal analysis or, after confirmation, a deeper financial review that may consider holdings and risk-budget position suggestions.
stock-screener
A stock-screening tool that starts with an established investment theme and finds related exchange-traded funds and leading companies. It ranks the candidates by factors such as strength, money flow, liquidity, and potential price movement.
hithink-finance-data
A local data-management skill for the HiThink Finance command-line tool and its DuckDB database. DuckDB is a database stored in a local file.
hithink-finance-special-data
A command-line tool entry for retrieving special Chinese market lists and event data, such as limit-up stocks, limit-down stocks, unusual moves, hot stocks, and Dragon-Tiger records.
hithink-finance-index
A command-line tool entry for finding Chinese indices, their categories, constituent stocks, current snapshots, and daily history. An index is a group of securities tracked as one measure, such as an industry or market segment.