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 pseudo-longinus/quant-buddy-skills --skill quant-buddy-skillgit clone --depth 1 https://github.com/pseudo-longinus/quant-buddy-skillsWrote 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/pseudo-longinus/quant-buddy-skills/quant-buddy-skill)<a href="https://agentmods.dev/skills/pseudo-longinus/quant-buddy-skills/quant-buddy-skill"><img src="https://agentmods.dev/badge/skills/pseudo-longinus/quant-buddy-skills/quant-buddy-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/pseudo-longinus/quant-buddy-skills/quant-buddy-skill"><img src="https://agentmods.dev/badge/skills/pseudo-longinus/quant-buddy-skills/quant-buddy-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 | $0.00622 | $0.22678 |
| Opus 5.5 | $0.00249 | $0.09071 |
| Sonnet 5.5 | $0.00124 | $0.04536 |
| Haiku 4.5 | $0.00062 | $0.02268 |
Grade C, and why
quant-buddy-skill scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$TMPDIR" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **许可例外（csv 解析）**：当 `fast_query` 返回 `mode:"csv"` + `csv_url`（数据点 > 500 的正常交付）时，调用 `python scripts/fetch_fastquery_csv.py "<csv_url>"` 下载并解析该 csv 属于**许可路径**——这是消费工具返回的 OSS 产物（平台无等价原生解析工具），不算"包装原生工具"。历史分钟长表使用 `scripts/fet How it starts
The opening of the file, as written. The whole thing — 727 lines — stays where its author put it; the contents beside it link to each section on GitHub.
筛选正确性与交付恢复
涉及选股、TopN、确认后的过滤条件时，先阅读 研究合同与恢复。研究与页面状态分开记录；缺数据或结果为空仍交付可读研究页，不得把未验证写成零命中。
观照量化投研
WebAgent 宿主交付约定优先：宿主要求金融问题统一“完整问答＋活页”时，所有金融问题先实际 route，再由 QBS 查询验证并发送非终止首答，同轮继续 QBV。包括具体字段、概念解释和“601137 最近如何？”，不依赖建页关键词。Worker 的 QBS_DEFAULT_PAGE_REQUESTED=1 由脚本自动继承；本文件及 leaf workflow 的“只回答/结束/不建页”默认仅适用于独立 QBS。明确不要网页/只回复文字、已有页面只读解读、文件托管与纯维护按各自规则处理。详见 宿主默认建页。
建页意图持续保留：普通“个股分析”与“综合分析”使用同一分类器；附加日期窗口、指标或展示要求不套固定快页。已有显式 QBV/活页意图时传 page_requested:true，查数结束不清除它；非终止首答后执行交接下一步，直至页面与回复验收通过或实际恢复后报告具体阻断。取数 success 不代表页面已交付，详见 先答后建页。
首屏优先：先读本文件前部的「平台工具参数速查」「硬规则」和「场景路由」。简单行情、窗口序列、最近报告期、固定区间收益、K 线图等高频任务命中 Fast Path 时，无需继续整本通读。
本地交付必须复用工具返回的真实路径；不得加 sandbox: 或猜测 Skill 安装目录。排名表逐列核对数据 ID、单位和日期；比值列不能抄到 PE 列。参见 全局执行规则。
个股画像与综合分析的内容合同见 workflows/stock-profile.md：默认交付五个数据章节与综合观察，用户明确要求简短或限定字段时才缩减。读取 Skill 后必须继续读取匹配工作流、实际查询并回复；“将读取文档/准备查询”不是业务交付，不可作为最终答案。明确不要网页只取消建页，不取消上述查询和完整分析。
常见请求的默认口径
- 中文股票全市场排名、未指定市场的涨幅前N热力图，默认 A 股并在首答声明；行业分组默认申万一级，颜色保留股票原涨跌幅、面积或数量明确含义。用户指定其他市场时遵从，不因为这些可披露默认值就停止澄清。
- 已给出“白酒股”等行业范围的刷新看板，先核验平台对应板块及成分，默认 PE TTM、PB；按
quant-standard.md查询并给出实际行情、成交量、估值首答，再按answer-first.md继续 QBV。刷新意图不允许先注册公式包，也不能只回复看板设计。不要先要求用户列股票名单。精确板块不存在或确有同名歧义时才澄清，不用几只龙头冒充全部行业。 - 常见单均线回测可采用 quant-standard 的披露默认值继续执行；用户明确不要网页时不建页。
平台工具参数速查（高频踩坑，先看这一段）
下表是 LLM 最容易写错的三个 schema。任何调用前先核对，不要凭"看起来合理"猜参数名。
| 工具 | ✅ 正确参数 | ❌ 模型常见错误（已被 call.py 自动归一化或拦截，但仍应避免） |
|---|---|---|
confirmDataMulti |
{"data_desc": "市盈率 TTM,股息率"} — 逗号分隔字符串 |
{"queries": [...]} / {"query": "..."} / {"names": [...]} |
runMultiFormulaBatchStream 公式中引用 session 中间变量 |
必须用双引号包裹：排序値 = "A股股息率〔估値数据〕" * "条件合并" |
裸变量名相乘："A股股息率…" * 条件合并 ← 平台直接报错 |
readData |
{"ids": ["69fe…<24位hex>"], "mode": "last_column_full"} — 必须是 runMultiFormulaBatchStream 返回的 data_id 字段（hex） |
传中文变量名 {"ids": ["Top10股息"]} / 用错参数名 {"index_title": "..."} / {"variable_names": [...]} / 传 expression_id 而非 data_id（两者相邻易混，传错会返回 "error": "IndexInfo {id}"） |
What ships with it
60 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.
- CHANGELOG.md 125 KB
- config.json 145 B
- presets/assets_db/future.yaml 12 KB
- presets/assets_db/index.yaml 28 KB
- presets/assets_db/stock_a.yaml 245 KB
- presets/assets_db/stock_hk.yaml 129 KB
- presets/assets_db/stock_us.yaml 40 KB
- presets/cases_index.yaml 26 KB
- presets/data_catalog.yaml 15 KB
- presets/dimensions.yaml 165 KB
- presets/functions.yaml 14 KB
- presets/index_info_catalog/a_share_financials.yaml 113 KB
- presets/index_info_catalog/a_share_option_iv.yaml 384 B
- presets/index_info_catalog/a_share_trading_labels.yaml 6.3 KB
- presets/index_info_catalog/cn_future_option_market_data.yaml 3.0 KB
- presets/index_info_catalog/global_classification.yaml 297 B
- presets/index_info_catalog/global_financials.yaml 134 KB
- presets/index_info_catalog/macro_indicators.yaml 13 KB
- presets/index_info_catalog/macro_strategy.yaml 11 KB
- presets/index_info_catalog/manifest.yaml 1.0 KB
- presets/index_info_catalog/README.md 1.7 KB
- presets/index_info_catalog/us_option_market_data.yaml 4.2 KB
- presets/sectors.yaml 41 KB
- presets/themes.yaml 17 KB
- recipes/download-data.md 2.8 KB
- recipes/event-study-formulas.md 2.2 KB
- recipes/formula-package.md 6.8 KB
- recipes/ic-factor-templates.md 3.1 KB
- recipes/industry-aggregation.md 12 KB
- recipes/ma-crossover-backtest.md 3.8 KB
- recipes/render-chart.md 5.5 KB
- recipes/tool-call-checklist.md 5.2 KB
- recipes/topn-gainers.md 1.7 KB
- recipes/upload-custom-data.md 3.1 KB
- recipes/value-pe-strategy.md 3.4 KB
- references/continuous-futures.md 6.5 KB
- references/environment.md 2.2 KB
- references/minute-data-coverage.md 9.6 KB
- references/ru-billing.md 1.7 KB
- references/scripts-audit.md 4.8 KB
- references/troubleshooting.md 12 KB
- scripts/answer_first.py 2.3 KB runs code
- scripts/answer_structure.py 5.4 KB runs code
- scripts/call.py 97 KB runs code
- scripts/companion_manager.py 29 KB runs code
- scripts/event_study_local.py 11 KB runs code
- scripts/executor.py 64 KB runs code
- scripts/fetch_fastquery_csv.py 15 KB runs code
- scripts/fetch_minute_range_csv.py 3.2 KB runs code
- scripts/formula_execution_contract.py 2.8 KB runs code
- scripts/formula_package.py 19 KB runs code
- scripts/live_page_routing.py 83 KB runs code
- scripts/minute_range_contract.py 6.3 KB runs code
- scripts/minute_range_csv.py 7.0 KB runs code
- scripts/profile_answer.py 3.8 KB runs code
- scripts/qbv_computation_capsule.py 38 KB runs code
- scripts/quant_api.py 52 KB runs code
- scripts/read_data_evidence.py 8.7 KB runs code
- scripts/resample_minute_bars.py 7.0 KB runs code
- scripts/research_contract.py 32 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.
- today Changed · +6 lines · +21 tokens per session cb1b93d1559a
- 4d ago Changed 28e3bb70e1f9
- 6d ago Changed · +2 lines · +7 tokens per session cb8121afb436
- 13d ago Changed · +5 lines · +35 tokens per session 1a09b4c57707
- 15d ago Changed · +1 lines · +29 tokens per session e4c8cc17f60b
- 17d ago Changed · +9 lines 29ef854fe0fa
- 19d ago Changed 37e5324b7c88
- 20d ago Changed f30e5ff19a94
- 24d ago Changed b6fec449aee4
- 27d ago First seen · 704 lines · 530 tokens per session scan C 32953933832d
quant-buddy-skill is a skill published in the GitHub repository pseudo-longinus/quant-buddy-skills (197 stars, last pushed today), licensed MIT. It adds 622 tokens to every session and 22,678 once invoked, about $0.0025 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
joinquant-skill
Generate accurate, runnable quantitative strategy code for the JoinQuant (聚宽) platform. Use this skill when the user asks to write a stock/ETF/futures backtest, paper-trading, or live-trading strategy on JoinQuant — the skill provides progressive-disclosure access to the complete JoinQuant API knowledge base (14…
alpha-evaluate
A multi-step workflow for testing an investment factor, meaning a measurable stock signal, against market data. It examines predictive relationship, grouped returns, risk-adjusted results, consistency, and robustness.
alpha-backtest
A strategy backtesting workflow that tests factor-based stock portfolios on historical data. Backtesting means simulating how a strategy would have performed in the past.
alpha-mine
An automated process for proposing and testing stock-market formulas, called factors, that combine price or trading data with mathematical operations. It screens the candidates using measures such as IC, which compares a factor with later returns.
alpha-autopilot
An automated research loop for investment factors, which are measurable signals used to select or compare stocks. It finds candidates, tests them, records successful ones, monitors active factors, and retires those that weaken.
alpha-signal
A daily trading-signal generator that reads active investment factors, scores current market data, and produces a target portfolio. Factors are measurable rules used to rank investments.