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 survey-analysisgit 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/survey-analysis)<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/survey-analysis"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/survey-analysis/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/survey-analysis"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/survey-analysis.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 | $0.00094 | $0.02276 |
| Opus 5 | $0.00047 | $0.01138 |
| Sonnet 5 | $0.00019 | $0.00455 |
| Haiku 4.5 | $0.00009 | $0.00228 |
Grade A, and why
survey-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 11d 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 — 256 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(调研标准/历史基准/NPS 定义)。
/survey-analysis — 调研分析
Examples
→ 示例:用户说"帮我们分析一下这次客户满意度调查的结果,找出关键发现",系统应调用本技能,执行调查数据分析和洞察生成。
→ 示例:用户说"员工调研显示跨部门协作评分下降,需要深入分析原因",系统应调用本技能,结合财务数据做关联分析。
→ 示例:用户说"竞争对手在做客户 NPS 对标调研,我们需要做一份",系统应调用本技能,制定 NPS 调研框架和分析方法。
第一步:确认调研设计
调研背景:
□ 调研类型:[客户调研/员工满意度/市场研究/NPS/产品反馈]
□ 调研目的:[描述]
□ 目标人群:[客户/员工/目标市场用户]
□ 调研期间:[YYYY-MM-DD 至 YYYY-MM-DD]
调研方法选择:
□ 方法对比:
→ 问卷调查:适合大样本、量化分析、成本低
→ 深度访谈:适合探索性研究、样本少但深度高
→ 焦点小组:适合群体意见碰撞、定性为主
→ 实际采用:[方法]
□ 问卷设计(如适用):
→ 题型:[单选题/多选题/量表题/开放式]
→ 题数:[X] 题
→ 预计时长:[X] 分钟
→ 核心问题:
· [问题1]
· [问题2]
· [问题3]
样本设计:
□ 目标样本量:[X] 人/份
□ 抽样方法:[随机抽样/分层抽样/配额抽样/便利抽样]
□ 配额设计(如分层/配额):
→ 客户规模:大型 [X]%/中型 [X]%/小型 [X]%
→ 地区:[区域1 X%]/[区域2 X%]
□ 预计完成率:[X]%(根据历史经验)
第二步:数据收集
问卷收集状态:
□ 已发放问卷:[X] 份
□ 已回收:[X] 份
□ 回收率:[X]%
□ 有效问卷:[X] 份
□ 有效率:[X]%(有效 / 已回收)
□ 收集进度:
→ 是否达到目标样本量:[✅ 是 / ⚠️ 否(差 [X] 份)]
→ 截止日期:[YYYY-MM-DD]
数据清洗:
□ 作答时间异常(< [X] 秒):[X] 份 — [保留/删除]
□ 连续相同答案:[X] 份 — [保留/删除]
□ 缺失值:[X] 项 — 处理方式 [删除/插补]
□ 数据清洗后有效样本:[X] 份
第三步:描述性分析
总体满意度/得分:
□ 总体得分:[X]/10(量表 1-10)
□ 分布:
→ 9-10 分(推荐者):[X]%([X] 人)
→ 7-8 分(被动者):[X]%([X] 人)
→ 0-6 分(贬损者):[X]%([X] 人)
□ NPS 计算(如适用):
→ NPS = 推荐者% - 贬损者%
→ NPS = [X](行业平均 [X])
□ 各维度得分(如有):
| 维度 | 得分 | vs 上期 | vs 行业平均 |
|------|------|---------|------------|
| [维度1] | [X]/10 | [±X] | [±X] |
| [维度2] | [X]/10 | [±X] | [±X] |
交叉分析:
□ 按客户规模:
| 规模 | 满意度均值 | NPS | 样本量 |
|------|-----------|-----|--------|
| 大型 | [X] | [X] | [X] |
| 中型 | [X] | [X] | [X] |
| 小型 | [X] | [X] | [X] |
□ 按地区:[类似结构]
□ 显著差异项:
→ 大型客户满意度显著高于中型客户([X] vs [X],p < 0.05)
→ [地区] 地区 NPS 显著低于平均水平([X] vs [X])
第四步:深度分析
关键驱动因素分析:
□ 相关性分析:
→ 总体满意度与 [维度A] 相关性最强(r = [X])
→ 总体满意度与 [维度B] 相关性次之(r = [X])
→ [维度C] 与满意度相关性弱(r = [X])
□ 回归分析(如样本量足够):
→ 影响满意度的关键因素(按重要性排序):
1. [因素1](标准化系数 [X])
2. [因素2](标准化系数 [X])
3. [因素3](标准化系数 [X])
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.
- 11d ago First seen · 256 lines · 94 tokens per session scan A 32214bb27c98
survey-analysis is a skill published in the GitHub repository vivy-yi/finance-skills (28 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 2,276 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.