TA

taixu-pipeline

Sequences five cognitive reasoning frameworks (Osborn to DeBono) for automated, comprehensive problem solving.

Install

mkdir -p .claude/skills/taixu-pipeline && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16407" && unzip -o skill.zip -d .claude/skills/taixu-pipeline && rm skill.zip

Installs to .claude/skills/taixu-pipeline

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

太虚五转连招:osborn→hegel→bayes→feynman→debono 自动串联编排器。触发词: 一键五转, 跑五转, taixu-pipeline.
80 charsno explicit “when” trigger
Advanced

Key capabilities

  • Automate the osborn (divergence) stage to generate idea pools
  • Automate the hegel (convergence) stage to consolidate ideas
  • Automate the bayes (validation) stage to verify solutions
  • Automate the feynman (simplification) stage to refine understanding
  • Automate the debono (evaluation) stage to assess value

How it works

The skill orchestrates a five-stage reasoning pipeline, automatically chaining osborn, hegel, bayes, feynman, and debono skills to brainstorm, converge, validate, simplify, and evaluate a given topic.

Inputs & outputs

You give it
Topic for analysis and optional problem type
You get back
complete report summarizing the five-stage reasoning process, including idea pools, converged solutions, validated findings, simplified explanations, and e

When to use taixu-pipeline

  • Executing automated ideation pipeline
  • Running complex reasoning flows
  • Applying five-stage cognitive processing
  • Automating problem analysis

About this skill

太虚五转自动串联编排器

一键串联 osborn→hegel→bayes→feynman→debono,保证完整五转流程不被嵌套降级污染。

使用方式

触发词:太虚五转一键五转taixu-pipeline

需要提供 input.topic(分析主题,如"太虚五转自动串联 + 防 Hegel 嵌套降级")。

可选参数:

  • input.type — 显式指定问题类型(deterministic / non_deterministic / mixed),透传给 osborn 作为最高优先级信号
  • --steps osborn,hegel,bayes — 仅执行指定步骤子集
  • 每个步骤后设 CHECKPOINT,用户可选择继续、跳过或终止

前置路由(brainstorm/ce-brainstorm 已废弃,能力归入 pipeline)

ce-brainstorm 和 brainstorm 已完全废弃,其能力分散到太虚五转各层。当用户使用以下触发词时,pipeline 执行前置路由:

用户说路由逻辑
"brainstorm" / "头脑风暴" / "先设计"Step 0 scope assessment → 主题清晰且需求明确 → quick exit(hegel --spec-only 或 liam-plan);主题清晰但方向待探索 → osborn P0;主题模糊 → osborn P0-clarify
"出方案" / "规格化" / "写spec"hegel --spec-only(快速规格化,跳过完整收敛循环)
"从太虚产出写需求"hegel --lens specification-bridge(从五转产出转化为 requirements doc)

Step 0 — Scope Assessment(吸收自 ce-brainstorm Phase 0.2-0.3)

pipeline 入口执行 scope assessment,判定工作量和路由:

  • Lightweight(小、边界清晰,低模糊度)→ 快速路由:osborn P0 简化发散 → hegel --spec-only → 结束
  • Standard(正常功能、有些决策要做)→ 完整五转
  • Deep(跨领域、战略性,高模糊度)→ 完整五转 + bayes 异构验证

路由判定由 osborn P0-clarify 的清晰度测试自动完成:能用一句话说清主题 + 识别 ≥3 个维度轴则直接发散,否则先做 Q&A 澄清。

Quick Exit(吸收自 ce-brainstorm Phase 0.2)

当用户需求已明确(有验收标准、有可参考模式,行为已描述清楚、scope 有约束),不需要发散:

  • 需要规格化 → hegel --spec-only
  • 需要执行计划 → 建议直接用 liam-plan
  • 仅需确认理解 → 简要回复,不启动 pipeline

组合概览

  1. osborn (skill: osborn) — 发散阶段,产出 idea-pool.md
  2. hegel (skill: hegel --standalone) — 收敛阶段,⚠️ 硬编码传入 --standalone 跳过内嵌验证
  3. bayes (skill: bayes) — 验证阶段,使用独立 lens 完整能力
  4. feynman (skill: feynman) — 审查阶段,使用独立 lens 完整能力
  5. debono (skill — debono) — 归真阶段,on_failure: skip,可选。debono 完成后自动触发五转综合总结,V2.2 强制,写入 docs/reports/{topic-slug}-taixu-summary-{date}.md
  6. 执行契约补齐 + plan 桥接(收尾步骤)— 检查 hegel spec,若走了 specification-bridge是否含"执行契约附录",Constraints/Boundaries/Pause if,见 hegel references/lens-specification-bridge.md;缺则从五转产出中派生补齐,标注来源 finding 或 [假设,可推翻]。然后明示用户:可进入 liam-plan,spec 已就绪,走 0.3 carry forward 直接规划路径,零追问。

方法论映射

两大策略(确定性/非确定性)→ 六要素 → 五转的多对多映射。详见 references/methodology-mapping.md

防嵌套机制

  • hegel step 的 args.standalone: true 在 composition block 中硬编码,配置级强制
  • hegel SKILL.md §6.1/§7.1 检测到 --standalone 时跳过 bayes/feynman 内嵌调用
  • 独立调用 /hegel 时不带此参数,行为完全不变(向后兼容)

审查与验证阶段强制条款(D11/D12 修复,2026-07-19)

受控 A/B 实验(runtime/taixu-ab-test/2026-07-18/)发现 2.0 在 D12,审查检出力相对 1.0 退坡 -2.5、D11,验证退坡 -1.0。根因在编排层而非 skill 本体,修复如下:

  1. feynman 盲审不可降级:时间预算紧不构成降级理由。仅当 subagent 工具调用本身失败时才允许降级为主 Agent 自审,且降级必须在 feynman 报告头部显式标注 review_mode: self (fallback)
  2. 宽松度自查:盲审结果 0 veto 且合规项 ≥5/6 时,主 Agent 必须列出 3 条「最可能被否决的断言」逐条自证,写入 feynman 报告附录;自证不通过的断言按 veto 处理。
  3. 深挖优先:bayes 报告中所有 ⚠️[待验证] 项在进入 debono 前必须完成 Bayes 联动深挖(references/depth-engine-principles.md),禁止带未深挖的待验证项进入归真阶段。
  4. bayes 精确数据源约束refuted 判定必须附 file:line / 脚本输出 / 台账定位;估算值只能支撑 unverifiedpartial,不得用于推翻断言。

CHECKPOINT 协议

每个 step 完成后暂停,展示信号、时间预算,相变检测、problem_type 路由。详见 references/checkpoint-protocol.md

UltraPlan 并行模式

可选增强,支持 osborn 维度并行 fan-out + bayes 异构验证 fan-out。详见 references/ultraplan-parallel.md

--steps 子集执行

支持 --steps hegel,bayes 语法:

  • 仅执行指定步骤及其依赖
  • 未指定步骤的产出物需已存在(从上次运行恢复)
  • 若依赖缺失且无法恢复,报错并提示补全

注意

  • 所有原子 skill 仍可独立使用,本 composed skill 是可选上层编排

  • debono 为 soft_depends_on + on_failure: skip,即使 feynman 失败也不阻断管线

  • debono 完成后自动触发五转综合总结(debono V2.2 内置),生成 docs/reports/{topic}-taixu-summary-{date}.md,包含全程叙事、关键转折,核心洞察、元认知收获。此为强制步骤,不可跳过

  • 全程产出物写入 docs/hegel-reports/docs/osborn-pools/,综合总结写入 docs/reports/,按日期命名

  • pipeline 全部 step 完成后(或用户终止后),将各 step 的执行时间汇总追加到 debono 综合总结末尾,格式:

    ## 时间日志
    | Step | 耗时 | Budget | Typical | 偏离 | 累计% |
    |------|------|--------|---------|------|-------|
    | osborn | 8min | 8min | 8min | 1.0x | 18% |
    | hegel | 12min | 8min | 8min | 1.5x | 45% |
    | bayes | 10min | 10min | 10min | 1.0x | 68% |
    | feynman | 15min | 10min | 10min | 1.5x | 102% 🔴 |
    | debono | 6min | 8min | 8min | 0.75x | 116% 🔴 |
    | **合计** | **51min** | **44min** | **44min** | **1.16x** | — |
    
    ## 相变信号汇总
    | Step | 信号 | 值 | 动作 |
    |------|------|-----|------|
    | hegel | terminal_status | converged | — |
    | bayes | refuted_count | 3 | 🔴 highlight |
    | feynman | veto_count | 2 | 🔴 highlight |
    | **相变簇** | **2 个 highlight** | — | **系统性偏差提示** |
    

    时间日志用于 liam-retro 分析和 typical 值校准(≥10 次后用实际中位数替换初始估计值)。预算列用于评估 problem_type → budget 映射的准确性,≥3 次同类型后校准预算值。相变信号汇总用于识别系统性认知偏差。

When not to use it

  • When not needing to chain osborn, hegel, bayes, feynman, and debono skills
  • When individual skills are preferred over an automated pipeline
  • When the problem type is not deterministic, non_deterministic, or mixed

Limitations

  • Requires `input.topic` to be provided.
  • Relies on the successful execution of individual osborn, hegel, bayes, feynman, and debono skills.
  • Default execution is linear, parallel mode is optional.

How it compares

This skill provides an automated, integrated pipeline for complex reasoning, ensuring a complete five-stage process without manual intervention, unlike using individual skills separately.

Compared to similar skills

taixu-pipeline side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
taixu-pipeline (this skill)01moReviewAdvanced
ultrathink282moNo flagsAdvanced
idea-darwin02moNo flagsIntermediate
fortune-router01moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

ultrathink

dashed

Invoke deep sequential thinking for complex problem-solving. Use when the user says 'use ultrathink', 'ultrathink', or when tackling problems that require careful step-by-step reasoning, planning, hypothesis generation, or multi-step analysis.

28115

idea-darwin

diegosouzapw

Idea Darwin Engine workflow skill. Use this skill when the user needs Darwinian idea evolution engine \u2014 toss rough ideas onto an evolution island, let them compete, crossbreed, and mutate through structured rounds to surface your strongest concepts and the operator should preserve the upstream

00

fortune-router

helloworld575

>-

00

nlm-skill

jacob-bd

Expert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of "nlm", "notebooklm", "notebook lm", "podcast generation", "audio overview", or any NotebookLM-related automation task.

895

session-logs

openclaw

Search and analyze your own session logs (older/parent conversations) using jq.

867

red-team-tools-and-methodology

davila7

This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters.

759

Search skills

Search the agent skills registry