What is qiong-ze-bian?

A decision framework for recognizing when a business model has reached a fundamental dead end and needs a major change. It separates confirming the problem, choosing the right time, and building a new operating foundation.

Use it to assess repeated failures, decide whether to pivot or replace the current model, gain team support, and establish new processes or foundations after the change.

It helps teams distinguish a temporary setback from a failed direction and avoid making changes without trust, timing, or a workable replacement.

qiong-ze-bian — Skill for Claude Code and Codex by ace3000chao

Install

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.

Any agent

npx skills add ace3000chao/book2startup --skill qiong-ze-bian

Clone the repo

git clone --depth 1 https://github.com/ace3000chao/book2startup

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ace3000chao/book2startup/qiong-ze-bian/github.svg)](https://agentmods.dev/skills/ace3000chao/book2startup/qiong-ze-bian)

Your own site

<a href="https://agentmods.dev/skills/ace3000chao/book2startup/qiong-ze-bian"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/qiong-ze-bian/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ace3000chao/book2startup/qiong-ze-bian"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/qiong-ze-bian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,189 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00175	$0.02189
Opus 5	$0.00088	$0.01094
Sonnet 5	$0.00035	$0.00438
Haiku 4.5	$0.00017	$0.00219

Measured 11d ago against content hash 16baf8ad2a44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

qiong-ze-bian 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.

易经skills/qiong-ze-bian/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

穷则变，变则通，通则久

R — 原文 (Reading)

"穷则变，变则通，通则久。" "己日乃孚，革命顺利。" — 《易经》系辞下·第二章 + 革卦

I — 方法论骨架 (Interpretation)

"穷则变"揭示了一个根本性规律：当一条路走到尽头（穷），不是绝望，而是变革的起点。变之后才能通达，通达才能持久。

但"穷则变"不是无条件的——需要两个关键支撑：

"己日乃孚"：在合适的时机（己日）才能建立信任、赢得支持，变革不是随时可以发动的
"鼎新"：变革不仅是破旧，更需要建立新秩序（鼎为食器，象征新的基础），没有"鼎"的变是乱变，不是真正的通

应用到创业实践中：

穷的识别：当现有模式、资源、方向已经无法支撑目标达成时，即是穷——这是变革的前提，不是情绪性判断
变的条件：穷是变革的理由，但变需要时机成熟、团队信任、足够资源；盲目变比不变更危险
鼎的建立：变之后必须建立新的秩序、新的模式、新的基础，没有"鼎"的变只是折腾
通的结果：真正的变革会带来新的发展空间（通）和持久性（久）

本质是"穷-变-鼎-通"四步闭环，缺任何一步都会失败。

A1 — 书中的应用 (Past Application)

案例1: 武王伐纣

问题: 商朝政治腐化、经济崩溃、民生凋敝，已处于"穷"的状态；周文王积蓄力量、武王继位后面临是否发动变革的抉择
方法论的使用: 武王在"穷"已显现（商朝内部崩塌迹象明显）且周族实力"鼎"已成熟（德治基础稳固、军力充沛）的条件下，选择时机发动革命
结论: 不是为变而变，而是在穷已确认、鼎已就位的情况下，完成天命更替
结果: 牧野之战一夜倾商，建立周朝，八百年基业从此奠基

案例2: 张瑞敏砸冰箱

问题: 1985年海尔冰箱质量合格率低劣，产品积压，企业处于质量管理的"穷"境
方法论的使用: 张瑞敏在员工大会上亲手砸毁76台不合格冰箱——这是"变"的决心；同时建立全面质量管理体系——这是"鼎"的建设
结论: 不是简单惩罚，而是通过一次极端行为开启全面质量管理变革，建立新的质量文化
结果: 海尔从濒临倒闭的小厂成长为全球家电巨头，质量文化成为核心竞争力

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

用户明确表示当前业务模式已不可持续（亏损扩大、用户流失、市场萎缩），且所有已知方法均无效
创业项目连续失败，团队士气低落，用户开始考虑彻底放弃或转型
用户在经历多次迭代失败后，表达"真的没办法了"、"这不是修修补补能解决的"等根本性质疑

语言信号

"我们已经试过了所有方法，真的不行了"
"这模式从根上就有问题"
"没有别的路了"
"继续下去只有死路一条"
"要么彻底变，要么关门"

与相邻 skill 的区分

与 ce07（穷之灾）的区别: ce07强调"穷"本身带来的灾难性后果，本skill强调"穷"之后的"变+鼎"出路；两者是前后关系
与 p06（或跃在渊）的区别: p06是在"渊"中蓄势等待，本skill是在"穷"后被迫变革；p06是主动等待，本skill是被动但理性的应度

E — 可执行步骤 (Execution)

确认"穷"的状态——真的走到尽头了吗
- 完成标准: 列出当前业务/项目的三个核心问题，逐一确认：每个问题是否有已知解法？是否已尝试过？失败原因是什么？——若三个核心问题均无解，进入下一步
- 判停条件: 若存在任何未尝试的解法（哪怕成功率低），先尝试这些方法，不启动本skill的完整变革
判断"变"的时机——现在能变吗
- 完成标准: 评估变革时机成熟度：团队核心成员是否信任（≥60%支持）、资源是否足够支撑过渡期（≥3个月现金流）、外部环境是否允许（无重大外部威胁）——至少两项满足
- 判停条件: 若时机完全不成熟（三项均不满足），告知用户"穷但不能变，需要先创造变的条件"
设计"鼎"——新的基础是什么
- 完成标准: 明确变革后的新模式、新机制或新方向，用一段话（≥50字）描述"新的基础架构"；没有"鼎"的变只是一次折腾
- 判停条件: 若无法描述新基础是什么，说明变革设计不完整，暂停执行
执行"变"——分步骤实施
- 完成标准: 制定变革实施步骤（≤5步），每步有明确里程碑和时间节点；先破后立还是先立后破，根据实际情况选择
- 判停条件: 若步骤设计超过5步或无法确定里程碑，简化方案，确保可执行性

Read the full file on GitHub · 134 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

test-prompts.json 1.1 KB

Changes

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 · 134 lines · 175 tokens per session scan A 16baf8ad2a44

Subscribe to this mod's changes

qiong-ze-bian is a skill published in the GitHub repository ace3000chao/book2startup (80 stars, last pushed 4mo ago), licensed MIT. It adds 175 tokens to every session and 2,189 once invoked, about $0.0009 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.

Planning crisis-management transformation yijing

story-structure-and-arc

Teaches the five-second moment principle, the relationship between surface spectacle and underlying transformation, and the But and Therefore technique for creating narrative momentum. Use when a pitch or presentation feels flat despite containing good material, when a founder's narrative lacks forward movement, when…

fatihguner/foreman · 81 tokens

kaizen-bpr

Applies two complementary process improvement philosophies: Kaizen (continuous incremental improvement) and Business Process Reengineering (radical process redesign from scratch). Helps determine when to refine existing processes versus when to tear them up and rebuild. Use when operational efficiency is declining…

fatihguner/foreman · 88 tokens

kotter-change-model

Guides organizational change initiatives using Kotter's eight-step model: creating urgency, forming a guiding coalition, developing a vision, communicating the vision, empowering action, generating short-term wins, consolidating gains, and anchoring changes in culture. Use when leading a strategic pivot, implementing…

fatihguner/foreman · 90 tokens

qiong-ze-bian