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 peterfei/forge-skill --skill pareto-principle-skillgit clone --depth 1 https://github.com/peterfei/forge-skillWrote 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/peterfei/forge-skill/pareto-principle-skill)<a href="https://agentmods.dev/skills/peterfei/forge-skill/pareto-principle-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/pareto-principle-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/peterfei/forge-skill/pareto-principle-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/pareto-principle-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 | $0.00093 | $0.06938 |
| Opus 5 | $0.00046 | $0.03469 |
| Sonnet 5 | $0.00019 | $0.01388 |
| Haiku 4.5 | $0.00009 | $0.00694 |
Grade A, and why
pareto-principle-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 9d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
帕累托法则 · 思维工具
少数关键输入决定了多数输出——识别并集中作用于那 20% 的杠杆点。
激活条件与触发词
直接调用:「用帕累托法则分析…」「用 80/20 分析…」「帮我找出关键少数」
语义触发:
- 用户讨论资源分配、优先级排序、聚焦策略时
- 用户描述「大部分问题来自少数原因」「大部分收入来自少数客户」等模式
- 用户需要对一组因素进行重要性排序或筛选
组合调用:「先用帕累托法则识别关键因素,再用第一性原理深入分析」
方法框架概览
帕累托法则的核心是识别系统中产生非线性回报的关键少数输入,它通过5个原理来指导决策者在资源有限时实现杠杆最大化。它不是精确的数学公式,而是对幂律分布现象的经验性概括。
核心原理(5个,每个须附 ≥2 个跨域证据)
原理 1: 幂律分布——80/20 是非线性世界的近似表达
一句话定义:许多自然和社会现象中,少数原因贡献了多数结果,其数学本质是幂律分布。
跨域证据:
- 经济学(财富分配):Vilfredo Pareto 在 1896-1897 年的《政治经济学教程》中通过对意大利各省税收数据的实证分析发现,约 20% 的人口拥有约 80% 的土地。这一发现发表在其两卷本著作中,成为帕累托分布的起源。(来源:Vilfredo Pareto, Cours d'économie politique, Lausanne: F. Rouge, 1896-1897)
- 软件工程(缺陷集中):微软通过内部数据分析发现,Windows 和 Office 中约 20% 的漏洞导致了约 80% 的错误和崩溃。更极端的案例中,约 1% 的缺陷导致了 50% 的错误,甚至 1% 的代码引发了 99% 的崩溃。(来源:CRN, "Microsoft's CEO: 80-20 Rule Applies To Bugs, Not Just Features", 2002)
应用方式:面对资源分配或问题诊断时,先量化各因素的贡献度,排序后识别是否呈现幂律特征(少数因素贡献远超比例),再决定是否采用帕累托式聚焦策略。
局限:在均匀分布或正态分布的场景中(如某工厂流水线上每个工位耗时相近),强行套用 80/20 会导致错误的优先级判断。
原理 2: 关键少数与次要多数——分层优先的决策框架
一句话定义:在任何复杂的因果系统中,极少数因素(关键少数)对结果的影响远超其余因素(次要多数)的总和。
跨域证据:
- 质量管理(制造业):Joseph M. Juran 在 1951 年的《质量管理手册》中正式将帕累托的发现提炼为"vital few and trivial many"原则,应用于产品质量缺陷分析。他观察到在多数制造场景中,约 20% 的缺陷类型导致了约 80%的质量问题。(来源:Joseph M. Juran, Quality Control Handbook, McGraw-Hill, 1951; Juran Institute 官方指南)
- 风险投资(金融回报):多家 VC 研究表明,基金中不到 20% 的投资项目贡献了超过 90% 的回报。约 5% 的公司产生 10 倍以上回报,而这些极少数赢家覆盖了整个基金的回报。SSRN 上发表的学术论文证实 VC 回报服从幂律分布。(来源:SSRN, "Power-Law Distribution in Venture Capital Returns", 2019; Altos VC, "Paradox of the Power Law in Venture Capital")
应用方式:面对多因素决策时,对所有因素按影响力排序,将资源集中投向排名前 20% 的因素,而非均匀分配。
局限:当"次要多数"存在协同效应或累积效应时(如长尾经济中大量低销量商品的总收入超过头部商品),忽视次要多数会导致重大遗漏。
原理 3: 非线性杠杆——识别高杠杆点的指数回报
一句话定义:找到正确的关键变量并集中投入,可以产生远超线性比例的回报。
跨域证据:
- 商业战略(客户管理):Salesforce 和多家咨询公司的研究表明,在 B2B 业务中,约 20% 的客户贡献了约 80% 的收入。针对这些关键客户的深度服务和留存投入,其 ROI 远超对中小客户的同等投入。(来源:Salesforce Blog, "Make Your Life and Your Business More Efficient with the 80-20 Rule")
- 技术研发(操作系统优化):IBM 在 OS/2 系统开发中通过帕累托分析识别出被用户使用频率最高的 20% 代码路径,集中重写并优化这些关键路径,以相对较小的工程投入实现了系统性能的大幅提升。(来源:StickyMinds, "Smarter Testing with the 80:20 Rule")
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.
- 9d ago First seen · 264 lines · 93 tokens per session scan A 08a0be4d03e9
pareto-principle-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 6,938 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
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
gpt-vis
A chart-generation tool that recommends visual formats for data and produces either chart settings or runnable code. It uses GPT-Vis, a library for rendering data visualisations.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.