需求发现 → 方向定界
SkillAI & modelsNeeds Discovery → Direction Scoping combo Skill. Starting from user pain points, systematically runs micro-need detection, real-need validation, and four-layer decomposition, outputting a Direction ready to enter direction scoping.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the 需求发现 → 方向定界 skill
What this skill tells your AI
The instructions your AI receives, as published by gmaxxxie/ai-native-product-agent-skills in skills/combo-needs-to-direction/SKILL.md and read by ahel’s review.
一句话定位
从一个模糊的痛点线索出发,跑完需求发现全流程,直接输出 Direction Brief。
何时触发
- 你有一个产品想法,需要快速验证并进入方向定界
- 不想分别调用多个工具卡,需要一站式输出
- 需要从"我有一个想法"到"方向定界简报"的最短路径
输入
一个模糊的产品想法或痛点描述。
示例输入:
"我想做一个帮律师自动审查合同的 AI 产品"
编排流程
输入: 模糊想法
↓
【Step 1】微需求检测 (p0a)
→ 是否存在被忽视的微需求?
→ 是否需要重新定义问题?
↓
【Step 2】需求四层拆解 (p0c)
→ 表达层:用户说了什么
→ 场景层:问题发生在哪里
→ 处境层:谁被困住了
→ 代价层:不解决会怎样
↓
【Step 3】真需求验证 (p0b)
→ 5问验证:长期性、代价、补偿行为、结构性、自然存续
→ 真/伪判定
↓
【Step 4】方向定界准备
→ 将需求发现结果转化为 Direction Brief 输入
→ 明确问题定义、场景切入、资料条件
↓
输出: Direction Brief(可直接进入 p1)
综合输出格式
direction_brief_input:
source: "原始想法"
problem_definition:
surface_problem: "表面问题"
deep_problem: "深层问题"
why_different: "为什么不同"
scenario_entry:
user: "目标用户"
scenario: "使用场景"
pain_point: "核心痛点"
evidence:
micro_needs: ["微需求发现"]
real_need_validation: "真需求验证结果"
cost_evidence: "代价证据"
compensation_behaviors: ["补偿行为"]
data_readiness:
available_data: "可获取的数据"
data_sensitivity: "数据敏感度"
access_difficulty: "获取难度"
preliminary_judgment:
worth_pursuing: true/false
confidence: "high/medium/low"
key_risks: ["风险列表"]
next_step: "进入方向定界 (p1)"
一句判断
好的方向定界,始于好的需求发现。不要带着假设进入方向定界,要带着证据。
Signals
- GitHub stars
- 46
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
combo-needs-to-direction- Source
- github.com/gmaxxxie/ai-native-product-agent-skills