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 linshidream/skill-hub --skill diverge-convergegit clone --depth 1 https://github.com/linshidream/skill-hubWrote 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/linshidream/skill-hub/diverge-converge)<a href="https://agentmods.dev/skills/linshidream/skill-hub/diverge-converge"><img src="https://agentmods.dev/badge/skills/linshidream/skill-hub/diverge-converge/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/linshidream/skill-hub/diverge-converge"><img src="https://agentmods.dev/badge/skills/linshidream/skill-hub/diverge-converge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.05378 |
| Opus 5 | $0.00088 | $0.02689 |
| Sonnet 5 | $0.00035 | $0.01076 |
| Haiku 4.5 | $0.00017 | $0.00538 |
Grade A, and why
diverge-converge 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
扩散收敛法 (Diverge–Converge)
一种与 Agent 共建的思维方法。不是帮用户执行某个方案，而是陪用户生长出方案——从一个看不清全貌的想法，到一份任何智能体都能接手的手稿。
这个 skill 是什么
它定义的是协议，不是脚本：当用户带着一个不成熟的想法来，这个 skill 规定 agent 如何扮演思维合伙人，通过受控的扩散与收敛，把模糊想法逼近成完整可实施方案，最后结晶为手稿。
核心交付不是任何单轮回答，而是累积锁定的决策 + 其依据 + 被否决的备选——最终沉淀为一份手稿，成为后续与其他 agent 协作的工作基础。
为什么是"先扩散，后收敛"
一个不成熟的想法有隐藏的完整形状。想法的主人看不见它，因为缺少地图。
- 若不先扩散就收敛：你在看不见地形时就承诺了一条路，只能做局部优化，等撞上承重约束时已经太晚、改动成本已经很高。(典型：软件里的时区暗礁、研究里被忽略的混杂变量、创业里没算到的现金流回款周期——这些都是"以为是一行字"、实则改写整个方案的点，只有扩散才能在便宜的时候暴露它们。)
- 扩散的职责：把用户不知道的点、可能相关的点铺开，扩张地图，暴露未知的未知 (unknown-unknowns)。
- 收敛的职责：每次锁定一个决策，直到所有问题都解决完，一条可走通的完整路径浮现——MVP 方案就有了。
扩散与收敛不是两个阶段，是一台双相引擎。每一轮对话都可能既扩张某个子领域、又锁死一个决策。随着轮次推进，重心从"以扩散为主"平滑滑向"以收敛为主"。
使用场景(触发信号)
- 用户带着半成熟想法，说"先扩散后收敛"、"扩散收敛一下"、"diverge-converge"、"帮我把这个想法展开"
- 用户想在动手前"看清这件事的全貌"、"有哪些我没考虑到的点"
- 用户想把一段多轮探讨/头脑风暴结晶成一份可实施文档/会议纪要/手稿
- 任何复杂、开放、没有现成答案的课题：软件架构、研究选题、商业决策、产品设计、政策制定、写作框架、职业规划……
总览:四相循环
┌─────────────────────────────────────────────────┐
│ [0] 理解想法 Intake │
│ 复述想法 → 找到"真正的问题" │
└───────────────────────┬─────────────────────────┘
▼
╔════════════════════ 双相引擎(循环 N 轮) ════════════════════╗
║ ║
║ [1] 扩散 Diverge ──────────► [2] 选择+深入 Select&Deepen ║
║ 铺开地图、暴露未知 用户选一条线，越钻越具体 ║
║ ▲ │ ║
║ │ [3] 收敛 Converge │ ║
║ └──── 每轮锁一个决策 ◄────────┘ ║
║ 重心从扩散滑向收敛 ║
╚═══════════════════════════╤══════════════════════════════════╝
▼ (检测到"无悬而未决项")
┌─────────────────────────────────────────────────┐
│ [4] 结晶 Crystallize │
│ 把整段探讨写成手稿(可实施文档/会议纪要) │
└─────────────────────────────────────────────────┘
What ships with it
2 files 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.
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 · 235 lines · 175 tokens per session scan A e42705de25a9
diverge-converge is a skill published in the GitHub repository linshidream/skill-hub (20 stars, last pushed 29d ago), licensed MIT. It adds 175 tokens to every session and 5,378 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…