7步需求拆解框架

v1.1.0

7-Part Demand Analysis Framework. Use before executing any user task or request. Forces structured requirement analysis before action to prevent blind execut...

1· 44·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for zcz-user/demand-analyzer.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "7步需求拆解框架" (zcz-user/demand-analyzer) from ClawHub.
Skill page: https://clawhub.ai/zcz-user/demand-analyzer
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install demand-analyzer

ClawHub CLI

Package manager switcher

npx clawhub@latest install demand-analyzer
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (7-part requirement analysis) match the SKILL.md and references. The skill doesn't request unrelated binaries, env vars, or installs — everything requested is appropriate for a conversational analysis helper.
Instruction Scope
Runtime instructions are limited to pausing 3 seconds, producing the 7-part breakdown, asking for user confirmation, and reading the bundled references/framework.md. The references mention using 'semantic search' to find related memories — that implies the skill may access agent memory when handling vague queries. This is coherent with its purpose but is a privacy-related behavior you should be aware of.
Install Mechanism
No install spec and no code files beyond the documentation — lowest-risk model for skills. Nothing will be downloaded or written to disk by an installer.
Credentials
The skill requires no environment variables, credentials, or external config paths. No disproportionate credential requests are present.
Persistence & Privilege
always:false and no special privileges requested. The skill can be invoked autonomously (platform default), which is normal; there is no evidence it modifies other skills or system-wide settings.
Assessment
This skill appears coherent and low-risk: it's instruction-only, asks for no credentials, and its behavior (pause, ask clarifying questions, produce a 7-part analysis) matches its description. Two things to consider before installing: (1) the references mention using semantic search of memories — if you store sensitive data in agent memory, clarify whether the skill should access it; (2) the source/homepage is missing, so if you need stronger trust guarantees inspect the included files (SKILL.md and references/framework.md) yourself — they are small and readable. If you want automatic pre-execution analysis in all contexts, confirm how often the skill will be invoked and whether that interaction model suits your workflow.

Like a lobster shell, security has layers — review code before you run it.

latestvk970f8dtwx6trps297jtb9bmv185m5bw
44downloads
1stars
2versions
Updated 1d ago
v1.1.0
MIT-0

Demand Analyzer

7 部分需求拆解框架——在行动之前先理解,避免接到任务就瞎干。

工作流程

  1. 收到用户消息 → 停顿 3 秒,不要立刻回复
  2. 输出 7 部分拆解 → 按框架逐项分析
  3. 等用户确认 → 不要自己猜,让用户选
  4. 执行计划 → 用户确认后按方案行动

7 部分框架

读取 references/framework.md 获取完整框架和模板。

核心结构:

1. 核心意图 — 用户真正想要什么
2. 关键约束 — 时间、资源、限制条件
3. 隐含需求 — 用户没明说但重要的
4. 歧义澄清 — 哪些地方需要确认
5. 信息缺口 — 还缺什么信息
6. 可选方案 — 2-5 个方案(不要只给 3 个!)
7. 执行计划 — 确认后怎么干

关键规则

⚡ 停顿 3 秒

收到用户消息后,不要立刻回复"马上去做"。先拆解,再行动。

⚡ 不要只给 3 个方案

打破"3 的魔咒"——方案数量根据实际需要,2-5 个或更多。

⚡ 模糊问题先追问

用户说模糊的话(如"那个"、"怎么样了"),先列出 2-5 个可能的理解,让用户确认。

⚡ 信息不够先问

不要猜,不要脑补。缺信息就问用户。

适用场景

场景怎么用
用户提出任务完整 7 部分拆解
用户问问题核心意图 + 歧义澄清 + 可选方案
用户分享链接核心意图 + 隐含需求 + 可选方案
用户说模糊的话列出 2-5 个理解 + 追问
复杂任务完整 7 部分 + 详细执行计划

Comments

Loading comments...