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-growth-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-growth-skill)<a href="https://agentmods.dev/skills/sun-btc/biga/biga-growth-skill"><img src="https://agentmods.dev/badge/skills/sun-btc/biga/biga-growth-skill/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/sun-btc/biga/biga-growth-skill"><img src="https://agentmods.dev/badge/skills/sun-btc/biga/biga-growth-skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00164 | $0.05575 |
| Opus 5 | $0.00082 | $0.02788 |
| Sonnet 5 | $0.00033 | $0.01115 |
| Haiku 4.5 | $0.00016 | $0.00558 |
Grade A, and why
biga-growth-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 9d 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 — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
成长投资策略分析 Skill
使用目标
使用本 skill 帮用户理解和应用“成长投资策略”。成长投资关注的是公司未来收入、利润、现金流和市场份额能否持续快速增长，而不是只看当前低估值或高分红。
成长投资适合有一定风险承受能力、能够接受较大波动、愿意持续跟踪行业和公司基本面的用户。对新人，应默认采用“行业 ETF 优先、小仓位参与、避免单票重仓”的保守框架。
重要提示：所有输出都应定位为投资教育和研究框架，不构成任何直接投资建议，不承诺收益，不替用户做买卖决策。
触发场景
当用户提出以下问题时，使用本 skill：
- 分析“成长投资”“成长股”“高成长行业”“行业 ETF”的投资策略。
- 询问 AI、半导体、新能源、创新药、军工、高端制造、软件、消费升级等赛道如何参与。
- 想用一笔资金配置成长股或成长行业 ETF。
- 要求比较两个或多个成长行业的机会和风险。
- 要求生成成长股筛选清单、研究框架、风险控制规则。
- 新人想参与成长股，但担心估值高、波动大、不会选股。
- 想判断某个成长逻辑是真成长、伪成长还是主题炒作。
- 想建立买入前假设、持有中跟踪、降仓或退出规则。
回答原则
- 先讲风险，再讲机会。成长资产常见问题是估值高、波动大、预期交易充分，一旦业绩不及预期可能深跌。
- 对新人优先建议行业 ETF 或小仓位参与，不鼓励重仓单一成长股。
- 不直接输出“必买”“一定涨”“满仓”等结论。
- 如果用户要求具体股票推荐，转为研究框架、筛选条件、风险等级和需核验数据清单。
- 如果用户提供资金规模，应给出仓位区间示例；如果未提供，应使用比例而不是绝对金额。
- 如果用户未说明市场区域，使用通用框架；若明显是 A 股场景，应补充 A 股特有风险。
- 成长投资分析必须同时看增长速度、增长质量、估值匹配和风险控制，不能只讲“空间大”。
成长投资的核心逻辑
成长投资主要看以下问题：
- 公司所处行业是否有足够大的市场空间。
- 公司收入能否保持较快增长。
- 利润能否随规模扩大持续释放。
- 毛利率、净利率、现金流是否能支撑增长质量。
- 研发投入、技术壁垒、客户粘性、品牌或渠道是否形成竞争优势。
- 当前估值是否已经透支未来增长。
- 行业政策、技术周期、供需周期是否支持未来增长。
成长投资不是“买热门概念”，而是买未来增长兑现的概率。概念只能带来想象空间，业绩兑现和现金流改善才决定长期回报。
常见成长行业与观察指标
| 行业 | 成长逻辑 | 关键观察指标 | 主要风险 |
|---|---|---|---|
| 半导体 | 国产替代、AI 算力、汽车电子、先进制造 | 下游需求、库存周期、资本开支、制程/设备/材料突破、客户验证 | 周期波动、估值高、技术迭代失败、库存去化慢 |
| 人工智能 | 算力、模型、应用软件、数据基础设施 | 商业化收入、算力需求、用户留存、推理成本、生态壁垒 | 估值过热、商业模式不清晰、竞争加剧 |
| 新能源 | 能源转型、储能、电动车、光伏/风电升级 | 装机量、渗透率、产能利用率、价格走势、技术路线 | 产能过剩、价格战、政策变化、技术替代 |
| 医药创新 | 创新药、医疗器械、老龄化需求 | 管线进度、临床数据、获批节奏、医保谈判、销售放量 | 研发失败、审批不确定、集采降价、现金流压力 |
| 军工 | 国防现代化、装备升级、订单周期 | 订单、交付、产能、型号放量、资产质量 | 订单节奏不透明、估值波动、业绩确认慢 |
| 高端制造 | 产业升级、自动化、机器人、工业软件 | 订单、客户结构、毛利率、进口替代率、规模效应 | 下游资本开支下降、竞争加剧、回款压力 |
| 软件 | 云化、订阅制、企业数字化、AI 应用 | ARR/MRR、续费率、客户留存、销售费用率、利润率改善 | 获客成本高、增长放缓、产品同质化 |
| 消费升级 | 品牌化、渠道升级、品质需求 | 同店增长、复购率、客单价、品牌心智、渠道效率 | 需求疲软、库存、品牌老化、估值回落 |
标的类型选择
1. 个股
适合能够持续研究财报、行业周期、竞争格局和估值的用户。
优点：
- 弹性大。
- 如果判断正确，收益潜力高。
缺点：
- 波动很大。
- 单一公司可能遇到业绩暴雷、技术失败、管理问题或估值杀跌。
- 对研究能力要求高。
2. 行业 ETF
适合新人或没有能力深入研究单只股票的用户。
优点：
- 分散单一公司风险。
- 操作简单，适合表达行业观点。
- 更适合小仓位、分批参与成长赛道。
缺点：
- 仍然会承受行业整体波动。
- 行业过热时 ETF 也可能大幅回撤。
- ETF 成分股质量参差不齐。
- 若指数高度集中，可能并没有真正分散风险。
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.
- 9d ago First seen · 498 lines · 164 tokens per session scan A f5baaaabd94e
biga-growth-skill is a skill published in the GitHub repository sun-btc/biga (5 stars, last pushed 3mo ago), licensed MIT. It adds 164 tokens to every session and 5,575 once invoked, about $0.0008 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-research
A workflow guide for preparing neutral, reproducible research data from Chinese market data. Reproducible means another person can repeat the same steps and obtain comparable results.