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 vivy-yi/finance-skills --skill insight-validationgit clone --depth 1 https://github.com/vivy-yi/finance-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/vivy-yi/finance-skills/insight-validation)<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/insight-validation"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/insight-validation/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/vivy-yi/finance-skills/insight-validation"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/insight-validation.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 | $0.00091 | $0.02179 |
| Opus 5 | $0.00046 | $0.01090 |
| Sonnet 5 | $0.00018 | $0.00436 |
| Haiku 4.5 | $0.00009 | $0.00218 |
Grade A, and why
insight-validation 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 10d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
加载上下文
首次使用时: 读取 ../../CLAUDE.md 获取场景级配置(验证标准/置信度分级/使用限制)。
/insight-validation — 洞察验证
Examples
→ 示例:用户说"业务说降价能提升销量,但我算了下利润会下降,帮我验证一下",系统应调用本技能,执行价格弹性分析和利润敏感性验证。
→ 示例:用户说"之前给的那个成本优化建议被业务挑战了,帮我补充更多数据支撑",系统应调用本技能,补充数据验证和敏感性分析。
→ 示例:用户说"供应商涨价的真正原因是什么,帮我从公开信息和市场数据验证",系统应调用本技能,执行外部数据交叉验证。
第一步:获取待验证洞察
洞察清单:
□ 待验证洞察数量:[X] 条
□ 来源报告:[报告名称/日期]
□ 洞察列表:
| # | 洞察标题 | 洞察描述 | 类型 | 原置信度 |
|---|---------|---------|------|---------|
| 1 | [标题] | [描述] | [模式/异常/机会] | [高/中/低] |
| 2 | [标题] | [描述] | [模式/异常/机会] | [高/中/低] |
第二步:数据准确性验证
数据来源核实:
□ 洞察 1 数据核实:
→ 引用数据点:[X]
→ 数据来源:[系统/报告名称]
→ 数据时间:[YYYY-MM-DD]
→ 数据核实结果:[✅ 确认 / ⚠️ 存疑 / 🔴 错误]
→ 核实说明:[描述]
□ 洞察 2 数据核实:
→ ...
计算准确性检验:
□ 洞察 1 计算验证:
→ 引用计算:[描述,如"YoY = (本期 - 上期) / 上期 × 100%"]
→ 原计算值:[X]%
→ 重新计算值:[X]%
→ 计算准确性:[✅ 正确 / 🔴 错误,差异 [X]%]
→ 修正后数值:[X]%(如错误)
数据时效性检查:
□ 洞察数据时效性:
→ 数据最新时间:[YYYY-MM-DD]
→ 距今时长:[X] 天
→ 时效性评估:[✅ 有效(<[X]天)/ ⚠️ 需更新(>[X]天)]
第三步:逻辑合理性验证
逻辑推演检验:
□ 洞察 1 逻辑检验:
→ 结论推导逻辑:[描述]
→ 逻辑链完整性:[✅ 完整 / ⚠️ 部分缺失 / 🔴 逻辑错误]
→ 关键假设:[列出]
→ 假设检验:[✅ 成立 / ⚠️ 存疑 / 🔴 不成立]
→ 逻辑漏洞:[描述(如有)]
□ 洞察 1 因果 vs 相关检验:
→ 是否混淆相关性与因果性:[是/否]
→ 说明:[因果关系成立/仅相关/无法判断]
跨洞察一致性检验:
□ 洞察间一致性:
→ 洞察 1 与洞察 2 是否存在矛盾:[✅ 一致 / ⚠️ 部分矛盾]
→ 说明:[描述]
□ 与已知事实的一致性:
→ 洞察是否符合已知的业务事实:[✅ 符合 / 🔴 矛盾]
→ 说明:[描述]
第四步:业务可操作性评估
可操作性评级:
□ 可操作性维度:
→ 明确性:行动建议是否清晰 [1-5 分]
→ 可执行性:建议在现有资源下是否可执行 [1-5 分]
→ 可衡量性:执行效果是否可量化追踪 [1-5 分]
→ 时效性:执行时机是否恰当 [1-5 分]
□ 综合可操作性评分:[X]/5
→ 4.0-5.0:[✅ 强可操作] — 可直接转化为行动
→ 3.0-3.9:[⚠️ 中等可操作] — 需细化后执行
→ < 3.0:[🔴 弱可操作] — 建议重塑或搁置
执行障碍分析:
□ 洞察 1 执行障碍:
→ 资源障碍:[有/无] — [描述]
→ 组织障碍:[有/无] — [描述,如跨部门协调]
→ 技术障碍:[有/无] — [描述]
→ 优先级障碍:[有/无] — [描述]
→ 综合评估:[✅ 可执行 / ⚠️ 需解决 X 个障碍 / 🔴 存在重大障碍]
第五步:置信度重新评估
综合置信度评估:
□ 置信度调整因素:
→ 数据准确性:[提升/不变/降低]
→ 逻辑合理性:[提升/不变/降低]
→ 可操作性:[提升/不变/降低]
→ 样本量/覆盖度:[提升/不变/降低]
□ 置信度最终定级:
→ 初始置信度:[高/中/低]
→ 调整后置信度:[高/中/低]
→ 调整原因:[描述]
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.
- 10d ago First seen · 221 lines · 91 tokens per session scan A 1107791c86a4
insight-validation is a skill published in the GitHub repository vivy-yi/finance-skills (27 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 2,179 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
infographics
Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
figma-implement-design
Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a…
datavis
Comprehensive data visualization toolkit for creating beautiful, mathematically elegant visualizations with D3.js, Chart.js, and custom SVG. Use when (1) building interactive data visualizations, (2) designing color palettes for charts, (3) choosing scales and visual encodings, (4) creating data pipelines from…
spec-kit-vibe-compat
Compatibility router for /speckit. workflows into /vibe-first Codex execution.
detecting-data-anomalies
Investigate outliers, rare events, spikes, and suspicious records in datasets. Use as an explicit anomaly-analysis helper when you want concrete anomaly-detection workflow guidance, not generic data validation or end-to-end ML ownership.