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 kpi-root-cause-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/kpi-root-cause-analysis)<a href="https://agentmods.dev/skills/vivy-yi/finance-skills/kpi-root-cause-analysis"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/kpi-root-cause-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/kpi-root-cause-analysis"><img src="https://agentmods.dev/badge/skills/vivy-yi/finance-skills/kpi-root-cause-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 | $0.00103 | $0.02239 |
| Opus 5 | $0.00051 | $0.01120 |
| Sonnet 5 | $0.00021 | $0.00448 |
| Haiku 4.5 | $0.00010 | $0.00224 |
Grade A, and why
kpi-root-cause-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 8d 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 — 253 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(KPI 定义/历史基准/改进资源)。
/kpi-root-cause-analysis — KPI 根因分析
Examples
→ 示例:用户说"毛利率连续 3 个月低于预算,业务说是原材料涨价,但财务觉得不止这个原因",系统应调用本技能,执行多维度根因拆解。
→ 示例:用户说"存货周转天数这个月突然变大了 15 天,帮我找找原因",系统应调用本技能,按供应链和销售维度做根因分析。
→ 示例:用户说"营业利润率下降了 2 个点,CFO 要求找出具体是谁的责任",系统应调用本技能,执行责任单元归因分析。
第一步:KPI 表现确认
KPI 未达标情况:
□ KPI 名称:[名称]
□ 目标值:[X]
□ 实际值:[X]
□ 缺口值:[X](目标 - 实际)
□ 达成率:[X]%(实际 / 目标 × 100%)
□ 未达标期间:[YYYY-MM]
□ 持续未达标期数:[X] 期(首次:[YYYY-MM])
历史表现:
□ 近期表现:
| 期间 | 目标值 | 实际值 | 达成率 | 趋势 |
|--------|--------|--------|--------|------|
| [上期] | [X] | [X] | [X]% | — |
| [本期] | [X] | [X] | [X]% | [↓] |
□ 长期均值 vs 目标:[X] vs [X]
□ 未达标频率:[X] 次 / [X] 期
第二步:因素拆解
KPI 拆解树(瀑布分解):
□ 第一层拆解(按业务维度):
KPI 总缺口 = [X]
├── [维度A] 贡献 [X]([占比]%)
│ ├── [子维度A1] 贡献 [X]
│ └── [子维度A2] 贡献 [X]
├── [维度B] 贡献 [X]([占比]%)
│ └── [子维度B1] 贡献 [X]
└── [维度C] 贡献 [X]([占比]%)
□ 主要缺口来源(Top 3):
1. [维度A]:[X],贡献 [X]% 的缺口
2. [维度B]:[X],贡献 [X]% 的缺口
3. [维度C]:[X],贡献 [X]% 的缺口
量化分析:
□ 各因素贡献度:
| 因素 | 贡献值 | 贡献占比 | 可控性 |
|------|--------|---------|--------|
| [因素A] | [X] | [X]% | [高/中/低] |
| [因素B] | [X] | [X]% | [高/中/低] |
第三步:5Why 根因分析
针对主要缺口因素执行 5Why 分析:
□ 针对 [因素A] 的 5Why 分析:
Why 1:KPI 未达标的原因是什么?
→ Because:[因素A] 表现低于预期
Why 2:[因素A] 低的原因是什么?
→ Because:[更深层原因]
Why 3:[更深层原因] 的原因是什么?
→ Because:[更深层原因]
Why 4:[更深层原因] 的原因是什么?
→ Because:[更深层原因]
Why 5(根因):[最深层的根本原因]
□ 根因分类:
→ [人员能力 / 流程缺陷 / 系统限制 / 资源不足 / 外部因素 / 目标设定问题]
第二主要因素的 5Why(简要):
□ 针对 [因素B] 的根因:
→ Why 1 → Why 3:[简述链条]
→ 根因:[最深原因]
→ 根因分类:[分类]
第四步:一次性 vs 系统性归因
归因分类评估:
□ 各因素归因:
| 因素 | 根因 | 归因类型 | 比重 |
|------|------|---------|------|
| [因素A] | [根因] | [一次性/系统性] | [X]% |
| [因素B] | [根因] | [一次性/系统性] | [X]% |
□ 一次性因素:
→ 名称:[因素]
→ 一次性贡献:[X](占总缺口 [X]%)
→ 说明:[为什么会发生]
→ 是否会重复:[可能/不太可能]
□ 系统性因素:
→ 名称:[因素]
→ 系统性贡献:[X](占总缺口 [X]%)
→ 说明:[根源于结构性/流程性/能力性问题]
→ 短期是否可解决:[是/否 — 预计 [X] 月]
归因结论:
□ 一次性因素合计贡献:[X]%(剔除后缺口 [X])
□ 系统性因素合计贡献:[X]%(须长期解决)
□ 目标设定问题(如有):[X]%(目标本身是否合理)
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.
- 8d ago First seen · 253 lines · 103 tokens per session scan A 9c535c65b5f5
kpi-root-cause-analysis is a skill published in the GitHub repository vivy-yi/finance-skills (28 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 2,239 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 2026-09-03.
Other skills, from other repositories
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
hive.error-recovery
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
G2 Legend Expert
Expert skill for G2 legend development - provides comprehensive knowledge about legend rendering implementation, component architecture, layout algorithms, and interaction handling. Use when implementing, customizing, or debugging legend functionality in G2 visualizations.
node-zombie-guardian
Use when diagnosing stale or orphaned Node.js processes launched by VCO, auditing ownership/liveness, or safely simulating cleanup without touching external Node workloads.
sentry
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require SENTRYAUTHTOKEN.