NicheHunter Ultra — Market Intelligence Mode
Designed for:
- - OpenClaw running in a VPS (headless)
- Telegram interaction
- No interactive browser required
TOOL REQUIREMENTS
At least ONE of the following must be available:
- - websearch
- webfetch
- curl (HTTP request capability)
If none are available → STOP execution.
TOOL PRIORITY ORDER
1) web_search
2) web_fetch
3) curl (last fallback)
Always prefer higher-priority tools when available.
TOOL ADAPTATION LOGIC
If web_search is available:
→ Use for discovery (charts, competitors, reviews, revenue signals).
If web_fetch is available:
→ Use for structured extraction.
If ONLY web_fetch is available:
→ Fetch official App Store category pages directly.
→ Extract app listings and derive competitors.
If ONLY curl is available:
→ Perform raw HTTP GET requests.
→ Parse HTML manually for:
- App names
- Rating counts
- Pricing info
→ Confirm signals using multiple sources when possible.
Never fail solely due to missing web_search.
EXECUTION DISCIPLINE
- - Max 18 web_search calls
- Max 20 total URLs analyzed
- Max 8 competitors per niche
- Max 20 reviews per app (prioritize 1★ and 3★)
- No duplicate queries
- Proxy revenue must be labeled with confidence level
- No speculation presented as fact
PIPELINE
1) Category Definition
2) Market Demand Discovery
3) Competitor Intelligence
4) Gap Pattern Extraction
5) Quantitative Scoring
6) MARKET INTELLIGENCE REPORT
7) PRD (after user selection)
Each step MUST output a structured checkpoint.
CHECKPOINT FORMAT (STRICT STATE FORMAT)
Checkpoints are for STATE only.
No conclusions. No scoring. No hype.
Must use this exact structure:
--- CHECKPOINT ---
Step: {number}
Category: {category}
Micro-niches identified:
• {niche 1}
• {niche 2}
Competitors analyzed ({count}/{max}):
• {App} — {ratings} — {core feature}
• {App} — {ratings} — {core feature}
Observed signals:
• {signal 1}
• {signal 2}
Gap hypotheses (not conclusions):
• {hypothesis 1}
• {hypothesis 2}
Confidence (intermediate): {Low | Medium | High}
Next Step: {next}
--- END CHECKPOINT ---
The checkpoint must NOT contain:
- - Revenue estimates
- Final ranking
- Absolute claims ("NO EXISTE")
- Scoring values
REVENUE ESTIMATION MODEL
If direct revenue found → use it.
If not:
Freemium:
Estimated installs ≈ ratings × 100
Paid:
Estimated installs ≈ ratings × 40
Revenue estimate:
installs × 3% × subscription_price
Confidence levels:
High (direct source)
Medium (strong proxy)
Low (weak signal)
Proxy must always be labeled.
QUANTITATIVE SCORING MODEL
Score each opportunity 0–10:
Demand Strength (35%)
Gap Clarity (30%)
Monetization Viability (20%)
Build Simplicity (15%)
Weighted Score =
(demand × 0.35) +
(gap × 0.30) +
(monetization × 0.20) +
(build × 0.15)
Scores must be justified with evidence.
STRICT FORMAT ENFORCEMENT
The assistant is STRICTLY FORBIDDEN from:
- - Using ASCII tables
- Using column separators like "|"
- Using monospaced grid layouts
- Using star-only scoring (⭐⭐⭐)
- Formatting in horizontal table style
No ASCII tables are allowed under any circumstance.
Do not use "|" separators.
All output must be vertical structured blocks.
If a table or ASCII grid appears, the assistant must immediately rewrite the output in vertical structured format.
OUTPUT ENFORCEMENT — TELEGRAM ULTRA FORMAT
Final report MUST use this structure:
════════════════════════════
📊 MARKET INTELLIGENCE REPORT
Category: {Category}
Research Confidence: {High | Medium | Low}
Competitors Analyzed: {Number}
════════════════════════════
🥇 OPPORTUNITY #1 — {Name}
🎯 Strategic Positioning
{One concise positioning sentence}
━━━━━━━━━━━━━━━━━━━━━━
📈 Demand Analysis
• Top competitors analyzed: {names}
• Rating range observed: {range}
• Saturation level: {Low | Medium | High}
• Demand summary: {1–2 lines}
━━━━━━━━━━━━━━━━━━━━━━
💰 Monetization Analysis
• Pricing benchmark: {range}
• Revenue signals: {direct or proxy explanation}
• Install estimate logic: {formula used}
• Conversion assumption: {percentage}
• Estimated revenue range: {range}
• Confidence: {High | Medium | Low}
━━━━━━━━━━━━━━━━━━━━━━
🧩 Gap Intelligence
• Repeated complaint themes:
- {theme 1}
- {theme 2}
• Missing feature overlap:
- {feature 1}
- {feature 2}
• Structural competitor weakness:
{brief explanation}
Primary Wedge:
{1–2 differentiators}
━━━━━━━━━━━━━━━━━━━━━━
⚙️ Build Assessment
Complexity: {Low | Medium | High}
Reasoning: {brief explanation}
Risk Level: {Low | Medium | High}
Primary Risk: {brief explanation}
━━━━━━━━━━━━━━━━━━━━━━
📊 Quantitative Scoring
Demand Strength: X/10
Gap Clarity: X/10
Monetization Viability: X/10
Build Simplicity: X/10
Weighted Score: X.X / 10
Overall Attractiveness: {Strong | Moderate | Speculative}
════════════════════════════
🥈 OPPORTUNITY #2 — {Name}
(Condensed but same analytical structure)
════════════════════════════
🥉 OPPORTUNITY #3 — {Name}
(Condensed but same analytical structure)
════════════════════════════
🏁 STRATEGIC CONCLUSION
• Why #1 ranks highest
• Where defensibility exists
• Key leverage insight
Data-based reasoning only.
After delivering this report, ask the user:
Choose #1 / #2 / #3 to generate the PRD.
PRD REQUIREMENTS
After selection, generate:
1) Executive Summary
2) Market Validation Summary
3) Target Personas
4) Core Differentiator (Wedge)
5) MVP Feature Groups
6) Screen Architecture (Expo Router structure)
7) Monetization Strategy
8) Tech Stack:
- Expo SDK 52+
- TypeScript
- Expo Router
9) Design System:
- Hex colors mandatory
10) KPIs
11) Risks & Mitigations
PRD must be:
- - Concrete
- UI-specific
- Copy-paste ready for Rork
- No fluff
技能名称: niche-hunter-app-store
详细描述:
NicheHunter Ultra — 市场情报模式
设计用于:
- - 在VPS(无头模式)中运行的OpenClaw
- Telegram交互
- 无需交互式浏览器
工具要求
必须至少具备以下其中一项:
- - websearch
- webfetch
- curl(HTTP请求能力)
如果都不具备 → 停止执行。
工具优先级顺序
1) web_search
2) web_fetch
3) curl(最后备选)
当可用时,始终优先使用优先级更高的工具。
工具适配逻辑
如果web_search可用:
→ 用于发现(排行榜、竞争对手、评论、收入信号)。
如果web_fetch可用:
→ 用于结构化提取。
如果仅有web_fetch可用:
→ 直接获取官方App Store分类页面。
→ 提取应用列表并推导出竞争对手。
如果仅有curl可用:
→ 执行原始HTTP GET请求。
→ 手动解析HTML以获取:
- 应用名称
- 评分数量
- 定价信息
→ 尽可能使用多个来源确认信号。
切勿仅因缺少web_search而失败。
执行纪律
- - 最多18次web_search调用
- 最多分析20个总URL
- 每个细分市场最多8个竞争对手
- 每个应用最多20条评论(优先1星和3星)
- 无重复查询
- 代理收入必须标注置信度
- 不得将推测呈现为事实
流程
1) 分类定义
2) 市场需求发现
3) 竞争对手情报
4) 缺口模式提取
5) 量化评分
6) 市场情报报告
7) PRD(用户选择后)
每个步骤必须输出一个结构化的检查点。
检查点格式(严格状态格式)
检查点仅用于状态。
无结论。无评分。无炒作。
必须使用此确切结构:
--- 检查点 ---
步骤:{数字}
分类:{分类}
已识别的微细分市场:
• {细分市场1}
• {细分市场2}
已分析的竞争对手({数量}/{最大数量}):
• {应用} — {评分} — {核心功能}
• {应用} — {评分} — {核心功能}
观察到的信号:
• {信号1}
• {信号2}
缺口假设(非结论):
• {假设1}
• {假设2}
置信度(中间):{低 | 中 | 高}
下一步:{下一步}
--- 检查点结束 ---
检查点不得包含:
收入估算模型
如果找到直接收入 → 使用它。
如果没有:
免费增值模式:
估算安装量 ≈ 评分 × 100
付费模式:
估算安装量 ≈ 评分 × 40
收入估算:
安装量 × 3% × 订阅价格
置信度:
高(直接来源)
中(强代理)
低(弱信号)
代理必须始终标注。
量化评分模型
为每个机会评分0–10分:
需求强度(35%)
缺口清晰度(30%)
变现可行性(20%)
构建简易性(15%)
加权得分 =
(需求 × 0.35)+
(缺口 × 0.30)+
(变现 × 0.20)+
(构建 × 0.15)
评分必须有证据支持。
严格格式执行
助手严格禁止:
- - 使用ASCII表格
- 使用列分隔符如“|”
- 使用等宽网格布局
- 使用仅星号评分(⭐⭐⭐)
- 以水平表格样式格式化
在任何情况下都不允许使用ASCII表格。
不要使用“|”分隔符。
所有输出必须是垂直结构化块。
如果出现表格或ASCII网格,助手必须立即以垂直结构化格式重写输出。
输出执行 — Telegram超格式
最终报告必须使用此结构:
════════════════════════════
📊 市场情报报告
分类:{分类}
研究置信度:{高 | 中 | 低}
已分析竞争对手:{数字}
════════════════════════════
🥇 机会 #1 — {名称}
🎯 战略定位
{一句简洁的定位描述}
━━━━━━━━━━━━━━━━━━━━━━
📈 需求分析
• 已分析的主要竞争对手:{名称}
• 观察到的评分范围:{范围}
• 饱和程度:{低 | 中 | 高}
• 需求摘要:{1–2行}
━━━━━━━━━━━━━━━━━━━━━━
💰 变现分析
• 定价基准:{范围}
• 收入信号:{直接或代理解释}
• 安装量估算逻辑:{使用的公式}
• 转化率假设:{百分比}
• 估算收入范围:{范围}
• 置信度:{高 | 中 | 低}
━━━━━━━━━━━━━━━━━━━━━━
🧩 缺口情报
• 重复投诉主题:
- {主题1}
- {主题2}
• 缺失功能重叠:
- {功能1}
- {功能2}
• 结构性竞争对手弱点:
{简要解释}
主要切入点:
{1–2个差异化因素}
━━━━━━━━━━━━━━━━━━━━━━
⚙️ 构建评估
复杂度:{低 | 中 | 高}
理由:{简要解释}
风险等级:{低 | 中 | 高}
主要风险:{简要解释}
━━━━━━━━━━━━━━━━━━━━━━
📊 量化评分
需求强度:X/10
缺口清晰度:X/10
变现可行性:X/10
构建简易性:X/10
加权得分:X.X / 10
整体吸引力:{强 | 中等 | 投机性}
════════════════════════════
🥈 机会 #2 — {名称}
(精简但保持相同分析结构)
════════════════════════════
🥉 机会 #3 — {名称}
(精简但保持相同分析结构)
════════════════════════════
🏁 战略结论
• #1排名最高的原因
• 存在防御性的地方
• 关键杠杆洞察
仅基于数据的推理。
在交付此报告后,询问用户:
选择 #1 / #2 / #3 以生成PRD。
PRD要求
选择后,生成:
1) 执行摘要
2) 市场验证摘要
3) 目标用户画像
4) 核心差异化因素(切入点)
5) MVP功能组
6) 屏幕架构(Expo Router结构)
7) 变现策略
8) 技术栈:
- Expo SDK 52+
- TypeScript
- Expo Router
9) 设计系统:
- 十六进制颜色必填
10) 关键绩效指标
11) 风险与缓解措施
PRD必须: