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 redfox-data/redfox-community-dsh --skill investor-distillergit clone --depth 1 https://github.com/redfox-data/redfox-community-dshWrote 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/redfox-data/redfox-community-dsh/investor-distiller)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/investor-distiller"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/investor-distiller/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/redfox-data/redfox-community-dsh/investor-distiller"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/investor-distiller.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 | $0.00113 | $0.05071 |
| Opus 5 | $0.00056 | $0.02535 |
| Sonnet 5 | $0.00023 | $0.01014 |
| Haiku 4.5 | $0.00011 | $0.00507 |
Grade A, and why
investor-distiller 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 3d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
公众号投资博主蒸馏器
免责声明：本工具仅供学习研究使用，蒸馏产物为风格模拟参考，不构成任何投资建议。 所有生成内容必须标注「AI 风格模拟，不构成投资建议」。
📝 简介
自动化的公众号投资博主风格蒸馏工具。输入公众号微信号和文章数量，自动采集文章并提取七维DNA投资风格画像，输出结构化的交易体系、市场判断、表达风格等完整分析报告。
✨ 功能特性
| 功能模块 | 能力描述 | 核心价值 |
|---|---|---|
| 文章自动采集 | 通过微信号批量拉取公众号历史文章，支持 20/60/100 篇三档 | 无需手动整理，一键获取完整素材 |
| 七维DNA蒸馏 | 提取交易体系、市场判断、表达风格、内容深度、互动特征、热点图谱、人设基因 | 结构化画像，可复用可对比 |
| 双层特征提取 | 表层（术语/个股频次）+ 思维层（分析工具/论证模式/语气量化） | 不仅像博主说的话，更像博主的思考 |
| 质量校验闭环 | 三维度评分（个股/风格/体系），≥80% 准出，双层审计 | 画像准确性有保障 |
| 风格化模拟 | 基于画像生成风格一致的个股/市场分析，含数据来源标注与免责声明 | 可复现博主风格的分析输出 |
⚠️ 蒸馏质量铁律
必须从raw全文逐篇提取，禁止依赖任何clean/NER中间层。
蒸馏准确性直接决定画像质量。经验表明，clean阶段的个股NER提取管线会遗漏大量信息（如一篇提及6只股票的文章可能只提取0-2只），导致画像基于不完整数据构建。因此：
- raw全文原则：所有提取（个股/短语/板块/风格）必须直接遍历raw文章正文，不经过任何预处理过滤
- 词典+别名匹配：个股提取使用完整词典（含口语化别名，如"上证指数"→"上证/大盘/沪指/A股"），确保宽松但准确
- 文章级板块计数：板块关注度按文章级别计数（每篇只计一次），比词频更准确反映博主真实关注方向
- 领域专用短语：使用投资领域专用关键词列表提取关键短语，比通用句子频次统计更精准
- 校验闭环：蒸馏完成后必须执行准确性校验（
--validate），≥80%方可准出
七维DNA蒸馏结构
| # | 维度 | 回答什么 | 关键字段 |
|---|---|---|---|
| 1 | 交易体系 | TA怎么交易？ | 核心模式、选股逻辑、买卖信号、仓位管理 |
| 2 | 市场判断 | TA怎么看市场？ | 交易流派、板块偏好、持仓周期、多空条件 |
| 3 | 表达风格 | TA怎么写/说？ | 文章结构、标志性表达、标题/开头/结尾模式、语气 |
| 4 | 内容深度 | TA写多少？ | 平均字数、信息密度、复盘详细度、预判明确度 |
| 5 | 互动特征 | TA怎么互动？ | 读者互动、战绩展示、争议处理、免责声明 |
| 6 | 热点图谱 | TA关注什么？ | 核心赛道、龙头记忆、常用指标、资金面关注 |
| 7 | 人设基因 | TA是谁？ | 投资经历、哲学演变、里程碑事件、师承/影响源 |
蒸馏维度分支
蒸馏前需先判断博主属于长线还是短线交易者，再按对应维度侧重提取：
| 维度 | 长线 | 短线 |
|---|---|---|
| 投资哲学 | 价值投资/波段交易 | 龙头战法/情绪周期/题材驱动 |
| 核心能力 | 生意本质 + 估值 + 护城河 | 热点捕捉 + 情绪周期 + 量价关系 + 板块轮动 |
| 分析周期 | 年级别（10年持有视角） | 日级别（隔日~2周） |
| 数据驱动 | 财务报表 + 行业数据 | 盘面数据 + 资金流向 + 消息面 |
双层提取框架
蒸馏不仅提取「用了什么词」（表层），更要提取「怎么思考」（思维层）。二者缺一不可：
表层特征（自动量化，脚本产出）：
- 个股/板块/术语/短语 频次统计
- 标题/开头/结尾 模式识别
- 字数/发布频率/免责声明 基础统计
思维层特征（脚本检测+AI深度分析）：
| 分析维度 | 脚本检测内容 | AI深度补充 |
|---|---|---|
| 核心分析工具 | 宏观经济/产业链/财报/技术面/资金面/情绪/政策 8类思维框架评分 | 提炼博主独有的分析链条（如"事件→产业拆解→A股影响"） |
| 论证链模式 | 事件驱动/数据驱动/逻辑推演/类比推理/产业链分析/逆向思维 6类模式 | 还原博主典型论证步骤和推导逻辑 |
| 语气量化 | 感叹句/疑问句/第一人称/口语化 四类标记篇均数值，自动分类 | 判断文风温度（高/中/低），提炼情感表达策略 |
| 数据引用密度 | 每千字数据引用次数，自动分类（数据驱动型/主观判断型） | 分析数据引用场景和方式 |
| 跨市场视角 | 美股/港股/A股/商品 四大市场引用检测 | 判断是否全球视角、多市场联动还是单一市场 |
| 信息密度 | 投资内容占比评估（干货型 vs 水文型） | 区分深度分析和浅层评论 |
What ships with it
6 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.
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.
- 3d ago Changed c312616bfefe
- 12d ago First seen · 369 lines · 113 tokens per session scan A b3dbf4a1f860
investor-distiller is a skill published in the GitHub repository redfox-data/redfox-community-dsh (5 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 5,071 once invoked, about $0.0006 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
ito-baskets
Read-only Itô basket and prediction-market data skill. Index the live basket catalog, compare a basket against user-supplied research or a watchlist, build a source-grounded market brief, or draft a non-executable planning worksheet. Use when a user asks to browse or index Itô baskets, compare a basket against notes…
dsh-hooks-authoring
Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.
web-artifact-designer
A design workflow for producing self-contained HTML or SVG files that open directly in a browser. It covers visual work such as posters, infographics, landing pages, charts, banners, cards, and interface mockups.
customer-billing-ops
Operate customer billing workflows such as subscriptions, refunds, churn triage, billing-portal recovery, and plan analysis using connected billing tools like Stripe. Use when the user needs to help a customer, inspect subscription state, or manage revenue-impacting billing operations.
cost-aware-llm-pipeline
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching. Use when LLM spend needs to come down, or when routing tasks across model tiers and budgets.
prediction-market-oracle-research
Research prediction markets as data sources or oracle signals for products, agents, dashboards, and corporate decision intelligence. Use for source-grounded analysis of market-implied probabilities, caveats, and integration patterns without investment advice. Use when evaluating prediction markets as a data source or…