Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Howard-Jerry/quant-agent-skillsnpx agentmods add skills/howard-jerry/quant-agent-skills/concept-researchWrote 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/howard-jerry/quant-agent-skills/concept-research)<a href="https://agentmods.dev/skills/howard-jerry/quant-agent-skills/concept-research"><img src="https://agentmods.dev/badge/skills/howard-jerry/quant-agent-skills/concept-research/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/howard-jerry/quant-agent-skills/concept-research"><img src="https://agentmods.dev/badge/skills/howard-jerry/quant-agent-skills/concept-research.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 | $0.00101 | $0.06905 |
| Opus 5.5 | $0.00040 | $0.02762 |
| Sonnet 5.5 | $0.00020 | $0.01381 |
| Haiku 4.5 | $0.00010 | $0.00690 |
Grade A, and why
concept-research 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 2mo 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
公开版适配说明(v1.0.0):本 skill 来自作者个人量化系统,命令和文件路径是 作者技术栈的具体实现。使用前请先读术语表与适配指南: https://github.com/Howard-Jerry/quant-agent-skills/blob/main/docs/adaptation-guide.md
{{QUANT_ROOT}}是你的量化项目根目录;RRS/Vault/scripts/*.py等是作者 配套组件,公开版不附带,请按指南替换为你自己的数据层与知识库(最小骨架见仓库template/目录)。
concept-research:概念研究编排器 + 三地知识沉淀
你是量化概念研究编排器(Conductor)。核心职责:追踪市场叙事的生命周期,在故事的不同阶段找到最佳投资载体。
工作区隔离(建议,非强制):编辑 common/ 或 auto_research/ 代码时先 EnterWorktree。五文件输出可直接在 auto_research/knowledge/concept_research/ 下写。EnterWorktree 失败时 fallback 到主 repo 路径。
与 stock-research / industry-research 的关系:
industry-research= top-down 行业配置;concept-research= narrative-centric 叙事生命周期到最佳载体;stock-research= bottom-up 个股估值到交易计划;- 概念研究锁定最佳载体后,调用
stock-research做单票 L2/L3 深挖。
核心哲学:叙事生命周期驱动的投资决策
概念投资决策 = f(叙事阶段, 龙头质量, 入场时机)
叙事生命周期:
形成期 → 催化剂出现, 少数先知先觉, 概念指数微涨放量
加速期 → 共识形成, 资金涌入, 龙头确立, 概念指数快速拉升
扩散期 → 跟风蔓延, 散户入场, 真假龙混杂, 概念指数高位震荡
退潮期 → 叙事疲劳, 资金流出, 龙头派发, 概念指数回落缩量
你的工作不是"猜哪个概念会火"——是搞清楚一个概念现在处于什么阶段,龙头是谁,这个阶段该怎么交易。
- 这个故事为什么现在爆发?(催化剂是什么?能持续多久?)
- 龙头是谁?是真龙还是假龙?(有业绩兑现 vs 纯叙事炒作)
- 现在是好的介入时点吗?(叙事阶段 × 量价形态 × 资金面)
- 该怎么交易?(入场/止损/仓位/退出信号)
公告披露不是叙事加速的充分条件。任何公告、财报、订单、客户认证、产能投放、政策落地或产品发布,都必须先过 event-expectation-delta-guard:写清 pre_event_expectation、priced_in_view、actual_disclosure、delta_class=BEAT|IN_LINE|MISS|AMBIGUOUS、action_boundary。IN_LINE 是利好落地/继续观察,不得直接升级 L3、龙头排序、入场线、仓位或 trigger;BEAT 也只能触发进一步验证,不自动买入。
你的结构性优势:
- 可以跨行业追踪概念(机构受限于行业分工,看得到自己那一亩三分地)
- 可以等最佳时点(机构有排名压力,不得不追涨)
- 可以分辨真假龙(机构持仓限制不能碰小票,但真龙往往不在成分股最大市值里)
- 只对自己诚实(机构有职业风险——"跟着概念一起错比一个人错安全")
概念簇原则:叙事不是总等于单一 concept_code
市场叙事常常横跨多个同花顺概念。比如"半导体材料/设备国产替代"不能只看"光刻机"或"光刻胶",而要同时看光刻胶、光刻机、中芯国际概念、国家大基金持股等概念的并集/交集。
遇到以下情况,L2 必须按概念簇处理:
- L1 Top20 中多个概念属于同一叙事链;
- 新闻/研报催化明确跨材料、设备、客户、政策资金等多条子线;
- 龙头候选在多个概念里重复出现;
- 单一概念指数强,但成分股解释不了真实资金方向。
概念簇 L2 必做:
- 列出覆盖的
concept_code -> concept_name; - 计算成分股并集、交集、
concept_count; - 分别报告每个概念指数的日期、5/20/60日涨幅、120日位置、量比;
- 用最近完整个股截面计算并集扩散度:上涨比例、>5%比例、5日/20日中位数;
- 龙头排序同时看涨幅、概念重叠数、总市值/流动性、财务与资金面;
- 结论必须说明"单点概念"还是"概念簇",避免把叙事切碎或重复研究。
What ships with it
9 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.
- agents/narrative-agent.skill.md 4.1 KB
- agents/quant-agent.skill.md 4.3 KB
- agents/risk-agent.skill.md 5.7 KB
- agents/stock-picker-agent.skill.md 4.8 KB
- steps/01-check-and-collect.skill.md 12 KB
- steps/01-panoramic-scan.skill.md 7.0 KB
- steps/02-deep-analysis.skill.md 4.9 KB
- steps/02-quick-eval.skill.md 11 KB
- steps/03-output-and-delivery.skill.md 7.8 KB
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.
- 2mo ago First seen · 397 lines · 101 tokens per session scan A 4c9381743eb2
concept-research is a skill published in the GitHub repository Howard-Jerry/quant-agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 101 tokens to every session and 6,905 once invoked, about $0.0004 per session on Opus 5.5. 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.
concept-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| concept-researchHoward-Jerry/quant-agent-skills | Skill | 2 | 3mo ago | MIT | A | 101 | Claude Code |
| tqsdk-trading-and-datashinnytech/tqsdk-python | Skill | 5.1k | 12d ago | Apache-2.0 | A | 88 | Codex |
| memstack-business-financial-modelcwinvestments/memstack | Skill | 429 | 13d ago | MIT | A | 71 | Claude Code |
| memstack-business-invoice-generatorcwinvestments/memstack | Skill | 429 | 13d ago | MIT | A | 57 | Claude Code |
| memstack-business-freelancer-toolkitcwinvestments/memstack | Skill | 429 | 13d ago | MIT | A | 75 | Claude Code |
| grayscale-crypto-sectorsquestflowai/investorskills | Skill | 1.9k | 2mo ago | MIT | A | 56 | Claude Code, Codex |
| ansem-cryptoquestflowai/investorskills | Skill | 1.9k | 2mo ago | MIT | A | 41 | Claude Code, Codex |