concept-research

concept-research is a skill for Claude Code from Howard-Jerry/quant-agent-skills. It costs 101 tokens per session (6,905 once invoked), scanned A, original, MIT.

A research workflow for tracking the life cycle of an investment theme and identifying the companies or other assets best connected to it. It separates broad industry research, theme-based research, and analysis of individual stocks.

In plain words
What is it for?
Use it to scan themes, assess catalysts and leaders, judge the theme’s stage, and hand a selected company to a separate stock-research process.
Why use it?
It helps distinguish a developing market story from an overheated or fading one before choosing what to investigate further.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/concept_radar.py # 默认 top 20.

Good fit Use it to scan themes, assess catalysts and leaders, judge the theme’s stage, and hand a selected company to a separate stock-research process.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Howard-Jerry/quant-agent-skills
agentmods
npx agentmods add skills/howard-jerry/quant-agent-skills/concept-research

Made for: Claude Code.

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 concept-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/howard-jerry/quant-agent-skills/concept-research/github.svg)](https://agentmods.dev/skills/howard-jerry/quant-agent-skills/concept-research)
Your own site
<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.

agentmods 80×15 button for concept-research

Your own site · 80×15
<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>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,905 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 $0.00101 $0.06905
Opus 5.5 $0.00040 $0.02762
Sonnet 5.5 $0.00020 $0.01381
Haiku 4.5 $0.00010 $0.00690

Measured 2mo ago against content hash 4c9381743eb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

concept-research/SKILL.md · 397 lines

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。

  1. 这个故事为什么现在爆发?(催化剂是什么?能持续多久?)
  2. 龙头是谁?是真龙还是假龙?(有业绩兑现 vs 纯叙事炒作)
  3. 现在是好的介入时点吗?(叙事阶段 × 量价形态 × 资金面)
  4. 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:

  1. 列出覆盖的 concept_code -> concept_name;
  2. 计算成分股并集、交集、concept_count;
  3. 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;
  4. 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;
  5. 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;
  6. 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。

Read the full file on GitHub · 397 lines

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. 2mo ago First seen · 397 lines · 101 tokens per session scan A 4c9381743eb2

Subscribe to this mod's changes

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.

Related

concept-research compared with skills from other repositories

concept-research next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
concept-researchHoward-Jerry/quant-agent-skillsSkill23mo agoMITA101Claude Code
tqsdk-trading-and-datashinnytech/tqsdk-pythonSkill5.1k12d agoApache-2.0A88Codex
memstack-business-financial-modelcwinvestments/memstackSkill42913d agoMITA71Claude Code
memstack-business-invoice-generatorcwinvestments/memstackSkill42913d agoMITA57Claude Code
memstack-business-freelancer-toolkitcwinvestments/memstackSkill42913d agoMITA75Claude Code
grayscale-crypto-sectorsquestflowai/investorskillsSkill1.9k2mo agoMITA56Claude Code, Codex
ansem-cryptoquestflowai/investorskillsSkill1.9k2mo agoMITA41Claude Code, Codex