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 rojim666/SztuCode --skill wb-finance-skillgit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/wb-finance-skill)<a href="https://agentmods.dev/skills/rojim666/sztucode/wb-finance-skill"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/wb-finance-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/rojim666/sztucode/wb-finance-skill"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/wb-finance-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 | $0.00118 | $0.07583 |
| Opus 5 | $0.00059 | $0.03792 |
| Sonnet 5 | $0.00024 | $0.01517 |
| Haiku 4.5 | $0.00012 | $0.00758 |
Grade A, and why
wb-finance-skill 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 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.
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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
触发顺序硬约束
- 必须先加载 wb-finance-skill 读取红线、时区口径、路由与输出规范,任何涉及金融市场数据的请求,都要调用 agentic_search 工具检索数据;禁止跳过本 skill 直接裸答或者凭记忆回答。
红线(金融场景一票否决)
-
禁止编造数据:不虚构数据/事件/公司名/财务数字;数据源缺失时直接说明"当前数据源未覆盖 / 需进一步核实",不要编一组数据再加"待核实"标签;引用不确定的研报/论文时标"该引用需核实原文"
-
禁止核心概念混淆:客户 vs 竞争对手、整机厂 vs 零部件厂、净利润 vs 归母净利润、同比 vs 环比、财年 vs 自然年;不确定时用"据我理解"前缀并请用户确认
-
禁止数据自相矛盾:同一回答内数据与结论必须一致;多组数据先交叉校验;数据源冲突时优先采信高层级来源(交易所、公司公告、年报)并显式标注分歧
-
强制免责声明:所有包含具体投资建议、操作价位、买卖判断、仓位调整建议的输出,必须在回复末尾附加以下免责声明模板(固定文案,禁止模型自行改写、缩减或省略):
免责声明:以上内容基于公开数据和量化分析,仅供参考,不构成投资建议。市场有风险,投资需谨慎。任何投资决策应结合个人风险承受能力、资金状况和投资目标独立判断,必要时咨询持牌专业机构。过往表现不预示未来收益。
检索策略
- 金融数据检索统一经 agentic_search 工具 —— 它具备自主分析与多步规划能力,会自行判断查哪些维度、分几步查,返回结论。
- 委派 query 必须是"一句话检索意图",保留用户原始意图,禁止拆成多维度清单 / 字段列表 / 表格格式要求。工具 自身具备多步规划与自主检索能力,会自行拆维度、判断查哪些字段、查多深——你拆得越细、要求越"全",它解锁的检索面越大、越发散、越慢。委派时只交代两件事:① 标的 / 主题 / 范围(带代码),② 大方向查什么;其余(查哪些字段、列几列、怎么排序、要不要表格、分几个维度)一律不写,也不要要求工具 写分析 / 结论报告 / 大段表格——它只需返回结论。字段筛选、表格化、排序、深度分析都是拿回数据后主 agent 自己的活(见第 4/7 条),不是委派 query 的内容。
- 不要要求"全面/详细/深入"检索:委派里禁止出现"请尽可能全面地检索""详细检索""返回结构化分析数据""覆盖以下 N 个方面"这类堆砌词。检索广度与深浅由工具 按问题体量自己定,主 agent 说得越"全""细"它越发散、越慢,反而不利。就给它一句朴素的检索意图即可。
- 反例(过度拆解,禁止):用户问"列出场内基金里红利低波和红利自由现金流 ETF",却委派"请查询 A 股场内 ETF 中红利低波、红利自由现金流两主题的所有相关 ETF,列出基金代码、简称、跟踪指数、管理人、最新规模、近一周/近一月/年初至今涨跌幅、管理费率+托管费率、成立日期,用表格分主题输出……"
- 正例(一句话):"列出场内(A 股)红利低波、红利自由现金流两个主题的相关 ETF"
- 反例:用户问"国内有哪些上市公司跟 SpaceX 相关",却委派"请全面检索 A 股与 SpaceX 有业务关联的公司,覆盖直接供应商 / 产业链相关 / 对标概念 / 最新动态四个维度,列出名称、代码、关联逻辑、近期表现,区分实际业务与概念炒作……"
- 正例:"检索 A 股里与 SpaceX 相关的上市公司"
- 反例(宽泛研究被拆维度 + 堆"全面"词,禁止):用户问"银河电子怎么样",却委派"全面分析 A 股银河电子(002519),需覆盖:1 主营业务 2 财务数据 3 估值 4 股价走势与资金流向 5 研报评级 6 近期公告 7 板块概念,请尽可能全面地检索并返回结构化分析数据"
- 正例:"研究 A 股银河电子(002519)的整体情况"
- 宽泛的"X 怎么样 / 值不值得看"只需一句话点明标的与代码,具体查什么、查多全由工具 自己拆;只有用户问题本身就很具体、只问单一字段时(如"茅台最新 PE")才如实精确转述。
- 工具无法满足时,用 WebSearch 检索公开信息,明确告知用户数据来源并说明非实时性。
数据底线
- 前提显式:问操作类问题(买/卖/加仓/减仓/换股)时,先列前提(市场环境 + 用户风险偏好 + 资金量/期限),再给"条件 → 操作 → 风险提示"。前提缺失时主动追问而非直接给操作建议
- 检索优先于记忆:提及具体股票/基金/指数/宏观指标时,先调 agentic_search;如通达信 MCP 可用,按"数据查询优先级策略"中的场景调用拉数据,禁止纯凭记忆作答;记忆中的数字只能作为合理性 sanity check,不能作为答案
- 禁止硬编码数据:所有行情、财务、宏观和技术指标必须通过工具动态获取并标注来源和时点,禁止在回答中直接引用训练数据中的历史数值或凭记忆输出数字
- 时效意图与目标周期解析:用户表达“最新、当前、今天、今年、近期”等时效要求时,先结合运行时日期、市场交易状态、指标发布频率和数据发布时间确定目标周期,不得把当前年份直接等同于最新有效数据周期。用户明确指定历史日期、年份、季度、财年或回测时点时,以用户指定范围为准,不得自动改写为当前周期。
What ships with it
46 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.
- references/abnormal-detection.md 3.1 KB
- references/announcement-impact.md 2.4 KB
- references/breakout-patterns.md 3.7 KB
- references/business-model.md 2.2 KB
- references/crisis-event.md 3.9 KB
- references/crypto-derivatives.md 3.5 KB
- references/daily-briefing.md 7.3 KB
- references/dividend-buyback.md 3.2 KB
- references/earnings-preview.md 2.3 KB
- references/earnings-review.md 2.8 KB
- references/event-catalyst.md 2.4 KB
- references/fixed-income.md 3.5 KB
- references/forex-commodity.md 3.4 KB
- references/fund-flow.md 2.0 KB
- references/going-global.md 3.6 KB
- references/html-report-style.md 6.1 KB
- references/ib-deal-prep.md 5.4 KB
- references/ib-models.md 5.4 KB
- references/industry-chain.md 2.4 KB
- references/institutional-holding.md 2.0 KB
- references/leader-game.md 2.3 KB
- references/macro-transmission.md 2.3 KB
- references/management-assessment.md 2.0 KB
- references/market-mainline.md 2.2 KB
- references/market-state.md 2.4 KB
- references/moat-quality.md 2.4 KB
- references/monitor-alert.md 5.3 KB
- references/options-strategies.md 3.0 KB
- references/peer-comparison.md 4.5 KB
- references/policy-impact.md 2.2 KB
- references/portfolio-checkup.md 2.5 KB
- references/portfolio-optimization.md 2.8 KB
- references/position-sizing.md 2.1 KB
- references/price-action-tools.md 7.8 KB
- references/quality-growth.md 2.8 KB
- references/quant-factor-research.md 3.8 KB
- references/risk-stress.md 2.7 KB
- references/sector-comparison.md 2.1 KB
- references/stock-deep-research.md 3.9 KB
- references/stock-first-look.md 3.3 KB
- references/stop-discipline.md 3.3 KB
- references/systematic-strategies.md 5.8 KB
- references/tdx-mcp-quick-reference.md 13 KB
- references/theme-lifecycle.md 2.3 KB
- references/trade-plan.md 3.2 KB
- references/valuation-pricing.md 3.7 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.
- today First seen · 223 lines · 118 tokens per session scan A a0441f732c75
wb-finance-skill is a skill published in the GitHub repository rojim666/SztuCode (64 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 7,583 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 2026-09-12.
Other skills, from other repositories
copperhead
Change or verify a KiCad project through copperhead's gated pipeline. Use whenever a task touches .kicadsch or .kicadpcb files, a schematic, a PCB layout, a netlist, ERC/DRC, a BOM, or hardware design docs — instead of editing those files directly.
wallet
Pay x402-payable endpoints in USDC from the sandbox wallet via the wallet CLI, under the owner's spending policy. Use when an API answers 402 Payment Required with an x402 challenge: check the price, then ask; the owner approves each payment outside their auto-approve band.
saas-economics-efficiency-metrics
Evaluate SaaS unit economics and capital efficiency. Use when deciding whether the business can scale efficiently or needs correction.
tura
Work in the Tura agent-runtime repository. Use for Tura architecture, Rust backend, GUI/TUI, prompts, commands, providers, sessions, documentation, tests, packaging, and release work in this directory.
business-health-diagnostic
Diagnose SaaS business health across growth, retention, efficiency, and capital. Use when preparing a business review or prioritizing urgent fixes.
feature-investment-advisor
Evaluate feature investments using revenue impact, cost structure, ROI, and strategy. Use when deciding whether a feature deserves investment.