What is conversation-flow?

Design guidance for how an AI should classify requests, choose a workflow, ask clarifying questions, and decide how independently to act.

Use it to design intent classification, domain routing, clarification policies, autonomy levels, and workflows from exploration through verification.

Without routing rules, an agent may treat questions like tasks, ask unnecessary questions, or act on unclear requirements.

conversation-flow — Skill for Claude Code and Codex by kangarooking

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 kangarooking/system-prompt-skills --skill conversation-flow

Clone the repo

git clone --depth 1 https://github.com/kangarooking/system-prompt-skills

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/kangarooking/system-prompt-skills/conversation-flow/github.svg)](https://agentmods.dev/skills/kangarooking/system-prompt-skills/conversation-flow)

Your own site

<a href="https://agentmods.dev/skills/kangarooking/system-prompt-skills/conversation-flow"><img src="https://agentmods.dev/badge/skills/kangarooking/system-prompt-skills/conversation-flow/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/kangarooking/system-prompt-skills/conversation-flow"><img src="https://agentmods.dev/badge/skills/kangarooking/system-prompt-skills/conversation-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,929 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	$0.00133	$0.01929
Opus 5	$0.00067	$0.00964
Sonnet 5	$0.00027	$0.00386
Haiku 4.5	$0.00013	$0.00193

Measured 10d ago against content hash 67ae1b497b86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

conversation-flow 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 10d 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.

conversation-flow/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

对话流程与路由设计

R — 原文 (Reading)

跨供应商系统提示词中浮现的对话管理核心模式：先将用户输入二分为"问题"与"任务"（Warp），再按领域路由到专用处理流程（Claude Chrome 的"芯片"机制）。Claude Design 要求新设计至少提问 10 个问题才开工；ChatGPT Agent 则主张"尽可能推进，只在被阻塞时才请求澄清"。Codex 对简单任务跳过规划，Jules 有正式的计划评审步骤。核心张力在于"先问清楚"与"先做了再说"之间的平衡。

I — 方法论骨架 (Interpretation)

意图二分法 — 首先将用户输入分类为"信息查询"（问题）或"任务执行"（动作），触发不同处理管线
领域路由表 — 为每个已识别领域（邮件/文档/代码/搜索等）建立专用处理流程，含输入验证和输出格式
澄清策略谱系 — 从"先问再做"（高澄清）到"假设并继续"（低澄清），按任务复杂度和风险级别选择
自主度分级 — 定义 AI 在多大程度上可以自主推进：低（每步确认）→ 中（关键节点确认）→ 高（完成后汇报）
结构化工作流生命周期 — 提问 → 探索 → 规划 → 执行 → 验证 → 总结，每个阶段有明确的进入/退出条件
简化任务快速通道 — 对预估复杂度低于阈值的任务（如 Codex 的 25% 简单任务），跳过规划直接执行
工具优先原则 — 如果一个请求可以通过工具调用直接解决，立即调用工具，不请求许可（Notion AI）

A1 — 案例分析 (Past Application)

案例: Claude Design 的十问启动流程

问题: 设计任务的高度开放性导致 AI 经常基于模糊需求产出偏离用户期望的结果
设计模式的使用: Claude Design 系统提示词要求在开始任何新设计前至少提出 10 个澄清问题，涵盖目标用户、设计风格、功能范围、技术约束等维度。工作流为：提问 → 探索 → 规划 → 构建 → 验证 → 总结
结论: 强制澄清阶段虽然增加了前置轮次，但显著减少了后期返工率

案例: ChatGPT Agent 的"尽可能推进"策略

问题: 频繁请求用户确认导致任务完成效率低下，用户体验碎片化
设计模式的使用: ChatGPT Agent 系统提示词要求"尽可能推进，不做不必要的检查"。仅在真正被阻塞时才请求用户澄清，否则使用"假设...并继续"模式自主推进
结论: 该策略适合高自主度场景，但对模糊需求的容错率较低，需要在"推进速度"和"方向准确"之间权衡

案例: Warp 的二分路由

问题: 混合处理查询和任务导致输出格式混乱——回答问题时给出执行步骤，执行任务时给出理论解释
设计模式的使用: Warp 系统提示词将用户输入严格二分为"问题"（→ 简洁指令式回答）和"任务"（→ 直接执行），消除格式歧义
结论: 简单的二分路由显著提升了输出一致性，尤其适合终端/CLI 等高效场景

A2 — 触发场景 (Future Trigger) ★

用户在什么情境下需要?

设计多任务型 AI 助手，需要根据用户意图路由到不同处理流程（如客服机器人的工单/FAQ/人工转接）
构建编程/设计工具类 AI，需要在"先问清楚"和"先做再说"之间找到平衡点
优化现有 AI 产品的对话体验——用户反馈"问太多问题"或"不问就做，方向经常跑偏"
为 AI Agent 设计工作流生命周期，需要定义规划→执行→验证的标准流程
实现"快速通道"机制——简单任务跳过规划直接执行，复杂任务走完整流程

语言信号

"AI 问的问题太多/太少了"
"不同类型的请求需要不同的处理方式"
"简单任务不要走复杂流程"
"需要先规划再执行"
"用户说了一句话就期望 AI 开始做事"

与相邻 skill 的区分

与 output-formatting 的区别: output-formatting 控制输出的"形式"，本 Skill 控制决定"输出什么"的流程逻辑
与 agent-delegation 的区别: agent-delegation 管理多代理间的任务分配，本 Skill 管理单代理内的对话路由
与 context-management 的区别: context-management 管理信息存储和加载，本 Skill 管理对话决策逻辑

Read the full file on GitHub · 96 lines

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.

10d ago First seen · 96 lines · 133 tokens per session scan A 67ae1b497b86

Subscribe to this mod's changes

conversation-flow is a skill published in the GitHub repository kangarooking/system-prompt-skills (183 stars, last pushed 4mo ago), licensed MIT. It adds 133 tokens to every session and 1,929 once invoked, about $0.0007 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.

Building agents Prompt Injection agent-design ai-agents cangjie-skill context-management prompt-engineering 公众号

gpt-image-2-prompt-engine

A structured prompt-writing tool for GPT-Image-2, using reusable JSON templates and a four-step workflow. It is designed for controlled commercial images such as product photos, posters, infographics, brand visuals, UI screenshots, and character designs.

anbeime/skill · 146 tokens

conversation-flow