Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Competing Hypothesis Matrix

ASecurity

Tactic: 多假设管理——生成竞争假设,设计区分性预测,构建结构化比较矩阵

417 stars
0 votes
0 copies
0 views
Added 6/1/2026
researchgo

Security Analysis

A100/100

Scanned 6/1/2026

Install to Claude Code

$npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill competing-hypothesis-matrix --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Competing Hypothesis Matrix?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Competing Hypothesis Matrix
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yogsoth-ai-competing-hypothesis-matrix/badge)](https://www.skillsdirectory.com/skills/yogsoth-ai-competing-hypothesis-matrix)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: competing-hypothesis-matrix
description: "Tactic: 多假设管理——生成竞争假设,设计区分性预测,构建结构化比较矩阵"
version: 1.0.0
category: hypothesis-formation
type: tactic
campaign: hypothesis-formulation
sops:
  - competing-hypothesis-generation
  - discriminating-prediction-design
  - hypothesis-comparison-matrix
dependencies:
  skills:
    - subagent-spawning
---

# Competing Hypothesis Matrix

多假设管理——系统生成与主假设竞争的替代解释,设计能区分它们的关键预测,并构建结构化比较矩阵,避免 confirmation bias。

## 编排意图

科学推理中最危险的偏差是只持有一个假设。本 tactic 强制 CC 在确定"最优"假设之前,先系统构建竞争假设,再设计能将它们区分开来的预测。

三步不可颠倒:先生成竞争假设(不允许跳过),再设计区分性预测(不允许只比较,不测试),最后构建比较矩阵(不允许只列举,不量化)。最终产出不是"哪个假设是对的",而是"用什么实验能区分它们"。

## 可用 SOPs

| SOP | 职责 | 何时调用 |
|-----|------|---------|
| competing-hypothesis-generation | 基于主假设,生成 ≥3 个与之竞争的替代假设(不同机制,相同或相似的现象预测范围) | 所有模式必选,首先执行 |
| discriminating-prediction-design | 为每对竞争假设设计区分性预测——找到一个观察结果,使两个假设预测不同 | 所有模式必选,在 competing-hypothesis-generation 之后 |
| hypothesis-comparison-matrix | 将所有假设和区分性预测组装为结构化比较矩阵,标注各假设对每个预测的预期结果 | 所有模式必选,最后执行 |

## 编排模式

**Simplified(S tier,1 个主假设)**
- 顺序执行全部 3 个 SOP;生成 ≥3 个竞争假设;设计 ≥2 个区分性预测;构建比较矩阵
- 适用:单一主假设,需要竞争性思维检验

**Standard(M tier,2-3 个主假设)**
- competing-hypothesis-generation 为每个主假设独立生成竞争假设;discriminating-prediction-design 跨主假设和竞争假设设计区分性预测;hypothesis-comparison-matrix 包含所有假设(主 + 竞争)
- 适用:已有多个候选假设,需要统一管理和比较

**Deep(L tier,复杂假设集)**
- 全部 3 个 SOP 执行;competing-hypothesis-generation 额外要求:至少 1 个竞争假设来自完全不同的理论框架;discriminating-prediction-design 额外要求:每个区分性预测标注所需实验规模和难度;hypothesis-comparison-matrix 额外输出:推荐的实验优先级(最有区分力的预测排前)
- 适用:假设空间复杂,需要为实验设计提供直接输入

## Minimum Yield

- ≥3 个竞争假设(与主假设解释相同现象但机制不同)
- ≥2 个区分性预测(每个预测对至少 2 个假设产生不同的预期结果)
- 结构化比较矩阵:假设 × 预测,每格标注预期结果方向(支持/反对/无关)

## Yield Report

执行结束后向调用方 strategy 报告:
- 竞争假设数 / 区分性预测数
- 最有区分力的预测(能同时区分最多假设对)
- 最难区分的假设对(预测几乎相同,需要极精细的实验设计)
- 推荐优先测试的假设(最易被证伪 + 区分性最强)

Attribution

yogsoth-aiyogsoth-ai
View sourceMore from yogsoth-ai →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review...

452202 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

805541 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publi...

452201 votes

Exa Search

Semantic search, similar content discovery, and structured research using Exa API

304951 votes
View all in research →