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 stock-analysisgit 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/stock-analysis)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/stock-analysis"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/stock-analysis.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 | $0.00185 | $0.02670 |
| Opus 5 | $0.00093 | $0.01335 |
| Sonnet 5 | $0.00037 | $0.00534 |
| Haiku 4.5 | $0.00018 | $0.00267 |
Grade A, and why
stock-analysis 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 5d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
股票分析专家-公众号股票大V蒸馏
⚠️ 免责声明：本工具仅供学习研究使用，所有生成内容均为 AI 风格模拟，不构成任何投资建议。 盘面数据必须实时采集，禁止 LLM 编造涨跌停、资金流向等数据。
📝 简介
将5位公众号股票投资大V的200+篇文章蒸馏为结构化风格画像（六维DNA：交易体系/市场判断/表达风格/内容深度/互动特征/热点图谱），通过 AI Agent 实现多模式风格化分析。盘面数据通过 WebSearch 实时采集并逐数值标注来源，生成内容经质量审计（表层+思维层双重校验）后准出。
✨ 功能特性
| 功能模块 | 能力描述 | 核心价值 |
|---|---|---|
| 多V并行对比 | 5位大V风格化分析同一标的/板块，输出共识与分歧 | 多视角交叉验证，避免单一偏见 |
| 每日复盘 | 按指定大V风格生成当日盘面复盘文章 | 风格化视角理解市场情绪与操作逻辑 |
| 板块漏斗 | 大V分析框架下四层筛选：赛道→龙头→确定性→操作 | 产业链逻辑穿透市场热点 |
| 短线选股 | 从公众号热文提取个股提及频率，按交易类型筛选 | 大V关注度量化选股 |
| 组合复盘 | 检索大V对各标的历史观点，按交易框架评估持仓 | 风格化持仓诊断与风险评估 |
| 财报点评 | 按大V风格解读公司财报，多维度分析基本面 | 基本面专业解读风格化输出 |
🔑 鉴权
前往 redfox.hk 注册获取 API Key，通过以下方式配置：
# 环境变量
export X_API_KEY="ak_你的密钥"
# 或配置文件 ~/.qoder/apis/redfox.json
{"api_key": "ak_你的密钥"}
API Key 用于：
- queryWorkList（文章同步）：按次扣费，每位大V同步扣 1 次积分
- record/save（调用记录上报）：仅用于统计，不扣费
快速开始
自然语言直接描述需求，Agent 自动识别模式：
| 场景 | 触发示例 |
|---|---|
| 单大V分析 | "用猫笔刀的风格分析宁德时代" |
| 多V对比 | "用5位大V的风格分别分析茅台" |
| 板块分析 | "共同分析航天板块" |
| 短线选股 | "用财躺平的风格筛选半导体短线" |
| 组合复盘 | "用投资明见的风格复盘我的持仓：中国卫星、航发动力" |
| 财报点评 | "点评贵州茅台最新财报" |
| 每日复盘 | "用猫笔刀的风格写一篇今日复盘" |
| 观点跟踪 | "查下财躺平对中国卫星的观点" |
预置大V画像
profiles/ 目录下每位大V一份 JSON 画像，开箱即用：
| 大V | 交易类型 | 核心风格 |
|---|---|---|
| 财躺平 | 短线+趋势 | 宏观趋势+逆向思维，道法自然哲学，"老粉都知道" |
| 猫笔刀 | 短线 | 多资产视角+周期推理，幽默随性，"今晚舅酱" |
| 格兰投研 | 长线 | 产业链深度研报型，数据驱动，"产业景气决定一切" |
| 投资明见 | 长线 | 纯技术面趋势跟踪，指数为核心，"趋势是最好的朋友" |
| 终身黑白 | 长线 | 深度价值投资，护城河+安全边际，"慢慢变富" |
执行流程
Phase -1：增量文章同步（触发时询问）
当日首次触发时必须先询问用户是否同步大V最新文章（每位扣 1 次积分）。
三种选择：跳过 / 部分同步（指定大V）/ 全部同步（5位，完成后必须进入 Phase 5 补充蒸馏）。
python3 "$SKILL_PATH/scripts/analyze.py" --author "财躺平" --mode sync
Phase 0：环境准备 + AI 偏见自查
python3 "$SKILL_PATH/scripts/analyze.py" --check-env
检查依赖和画像就绪后，按以下标准评估信息丰富度并写入生成内容开头：
| 等级 | 特征 | 应对策略 |
|---|---|---|
| A 级（信息充裕） | 画像高置信、盘面完整 | 反面检验：大V看多时，聪明人为什么看空？ |
| B 级（信息适中） | 画像中置信、部分数据缺失 | 每个推算数据标注置信度 |
| C 级（信息稀缺） | 画像低置信、数据缺失 | 第一性原理提问，不拼凑"看起来完整"的报告 |
What ships with it
18 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.
- assets/article_template.md 1.9 KB
- profiles/投资明见_profile.json 5.1 KB
- profiles/格兰投研_profile.json 5.7 KB
- profiles/猫笔刀_profile.json 5.9 KB
- profiles/终身黑白_profile.json 6.1 KB
- profiles/财躺平_profile.json 8.3 KB
- README.en.md 5.3 KB
- README.md 4.7 KB
- references/质量准出标准.md 6.5 KB
- scripts/analyze.py 25 KB runs code
- scripts/common.py 13 KB runs code
- scripts/earnings.py 11 KB runs code
- scripts/fetch_market_data.py 6.4 KB runs code
- scripts/portfolio.py 11 KB runs code
- scripts/quality_audit.py 25 KB runs code
- scripts/stock_screen.py 14 KB runs code
- scripts/sync_articles.py 11 KB runs code
- scripts/validate_profile.py 12 KB runs code
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.
- 5d ago First seen · 203 lines · 185 tokens per session scan A edacd930853c
stock-analysis is a skill published in the GitHub repository redfox-data/redfox-community-dsh (5 stars, last pushed yesterday), licensed MIT. It adds 185 tokens to every session and 2,670 once invoked, about $0.0009 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 2026-09-03.
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…