[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7715MJ2KGEN3SCP2REP9X01":3,"skill-same:01M7715MJ2KGEN3SCP2REP9X01":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M7715MJ2KGEN3SCP2REP9X01","ai-market-research",null,"整合 crawl4ai、trendradar、product-research 的全链路市场研究自动化技能","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fc\u002Fchace-ai-market-research\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ai-market-research\nversion: 0.1.0\nauthor: Chace\nlicense: MIT\ndescription: 整合 crawl4ai、trendradar、product-research 的全链路市场研究自动化技能\ndependencies:\n  mcp: [\"crawl4ai\", \"trendradar\"]\n  skills: [\"product-research\"]\n  plugins: [\"agentmemory\", \"vector-memory\"]\ncategories: [research, automation, market-intelligence]\nhomepage: \"https:\u002F\u002Fgithub.com\u002Fyourusername\u002Fai-market-research-skill\"\n---\n\n# AI Market Research 组合技能\n\n> 整合 crawl4ai、trendradar、product-research 的全链路市场研究自动化\n\n## 定义\n\n**ai-market-research** 是 OpenClaw 的组合技能，提供端到端的市场研究能力：\n\n1. **crawl4ai** - 深度网页抓取与结构化提取\n2. **trendradar** - 多平台热点监控与舆情分析\n3. **product-research** - 结构化市场分析框架（竞品\u002F用户\u002F趋势）\n4. **agentmemory** - 历史数据持久化与跨期对比\n\n## 适用场景\n\n- 竞品进入新市场前的深度调研\n- 行业趋势追踪（每周\u002F每月自动报告）\n- 新品发布前的市场环境扫描\n- 投资决策前的赛道分析\n\n## 核心能力\n\n### 输入参数\n\n| 参数 | 类型 | 必填 | 说明 |\n|------|------|------|------|\n| `topic` | string | ✅ | 研究主题（产品名\u002F行业\u002F赛道） |\n| `depth` | enum | ⭕ | 研究深度：`quick`（1小时）\u002F`standard`（4小时）\u002F`deep`（8小时+）|\n| `sources` | array | ⭕ | 指定 crawl4ai 抓取的URL列表（不指定则自动发现）|\n| `output_format` | enum | ⭕ | 输出格式：`markdown`\u002F`html`\u002F`json`（默认 markdown）|\n| `compare_previous` | bool | ⭕ | 是否与历史研究对比（默认 true）|\n\n### 输出产物\n\n- **主报告** (`research-report.md`) - 结构化分析\n- **数据附件** (`artifacts\u002F`) - 原始抓取内容、热度摘要、竞品表格\n- **记忆写入** - 自动保存到 agentmemory，支持长期追踪\n\n## 工作流\n\n```mermaid\ngraph LR\n    A[任务: 研究 X] --> B[crawl4ai 深度抓取]\n    A --> C[trendradar 热点聚合]\n    B --> D[product-research 分析引擎]\n    C --> D\n    D --> E[生成结构化报告]\n    E --> F[保存到 agentmemory]\n    F --> G[推送结果]\n```\n\n### 阶段说明\n\n1. **数据采集** (Data Collection)\n   - crawl4ai: 抓取产品官网、竞品页、评测文章、用户评论\n   - trendradar: 获取微博\u002F知乎\u002F百度等平台的关联热点\n\n2. **数据分析** (Analysis)\n   - product-research: 应用标准框架（SWOT\u002FPEST\u002F竞品矩阵）\n   - AI 摘要: 提炼核心洞察、风险评估、机会点\n\n3. **知识存储** (Memory)\n   - 将本次研究的关键结论存入向量数据库\n   - 建立 `topic → timestamp → findings` 索引链\n\n4. **报告交付** (Delivery)\n   - 生成 Markdown 报告（支持微信阅读）\n   - 可选 HTML 可视化版本\n   - 通过 OpenClaw 消息通道推送\n\n## 使用示例\n\n### 基本调用\n```bash\n# 快速研究（1小时）\nai-market-research --topic \"宇树科技机器人\" --depth quick\n\n# 深度研究（8小时+）\nai-market-research --topic \"人形机器人赛道\" --depth deep --compare_previous true\n```\n\n### 指定数据源\n```bash\nai-market-research \\\n  --topic \"特斯拉FSD\" \\\n  --sources \"https:\u002F\u002Ftesla.com\u002Ffsd\" \"https:\u002F\u002F electrek.co\u002Ftesla-fsd-review\" \\\n  --output_format markdown\n```\n\n## 配置依赖\n\n### MCP 服务\n必须已启动：\n- `crawl4ai` (localhost:11235)\n- `trendradar` (localhost:3333)\n\n### 技能启用\n以下技能必须在 `openclaw.json` 中启用：\n- `product-research`\n- `agentmemory` (插件)\n- `vector-memory`（可选，用于历史对比）\n\n### 环境变量\n- `AI_API_KEY` - 用于 trendradar AI 分析（如果启用）\n- `OPENCLAW_WECHAT_TO` - 微信推送目标（optional）\n\n## 性能与成本\n\n| 深度 | 预计耗时 | crawl4ai 调用 | trendradar 调用 | LLM token 消耗 |\n|------|----------|--------------|----------------|----------------|\n| quick | ~1h | 5-10 URL | 1次（当日数据） | ~50k |\n| standard | ~4h | 20-30 URL | 3天历史 + 每日增量 | ~200k |\n| deep | ~8h+ | 50+ URL | 7天历史 + 全平台 | ~500k+ |\n\n## 故障排除\n\n### 常见问题\n\n1. **crawl4ai JWT 错误** → 检查 `CRAWL4AI_JWT` 环境变量\n2. **trendradar MCP 连接失败** → 确认 `uv run python -m mcp_server.server` 正在运行\n3. **memory 写入失败** → 确认 `agentmemory` 插件已启用\n4. **token 超限** → 降低 `depth` 或减少 `sources` 数量\n\n## 安装\n\n### 手动安装\n\n```bash\n# 克隆到技能目录\ngit clone https:\u002F\u002Fgithub.com\u002Fyourusername\u002Fai-market-research-skill.git \\\n  ~\u002F.openclaw\u002Fworkspace\u002F.agents\u002Fskills\u002Fai-market-research\n\n# 启用技能（添加到 openclaw.json）\n# 重启网关\nopenclaw gateway restart\n```\n\n### 通过 ClawHub（即将推出）\n\n搜索 `ai-market-research` 并一键安装。\n\n## Roadmap\n\n- [ ] 真实 MCP 调用（替换模拟数据）\n- [ ] product-research 深度集成\n- [ ] 自动来源发现（Google 搜索 + 筛选）\n- [ ] 向量历史对比（vector-memory）\n- [ ] Webhook 推送自动化\n- [ ] Docker 容器化\n- [ ] 多语言报告支持\n\n## License\n\nMIT © Chace\n","# AI Market Research 组合技能\n\n> 整合 crawl4ai、trendradar、product-research 的全链路市场研究自动化\n\n## 定义\n\n**ai-market-research** 是 OpenClaw 的组合技能，提供端到端的市场研究能力：\n\n1. **crawl4ai** - 深度网页抓取与结构化提取\n2. **trendradar** - 多平台热点监控与舆情分析\n3. **product-research** - 结构化市场分析框架（竞品\u002F用户\u002F趋势）\n4. **agentmemory** - 历史数据持久化与跨期对比\n\n## 适用场景\n\n- 竞品进入新市场前的深度调研\n- 行业趋势追踪（每周\u002F每月自动报告）\n- 新品发布前的市场环境扫描\n- 投资决策前的赛道分析\n\n## 核心能力\n\n### 输入参数\n\n| 参数 | 类型 | 必填 | 说明 |\n|------|------|------|------|\n| `topic` | string | ✅ | 研究主题（产品名\u002F行业\u002F赛道） |\n| `depth` | enum | ⭕ | 研究深度：`quick`（1小时）\u002F`standard`（4小时）\u002F`deep`（8小时+）|\n| `sources` | array | ⭕ | 指定 crawl4ai 抓取的URL列表（不指定则自动发现）|\n| `output_format` | enum | ⭕ | 输出格式：`markdown`\u002F`html`\u002F`json`（默认 markdown）|\n| `compare_previous` | bool | ⭕ | 是否与历史研究对比（默认 true）|\n\n### 输出产物\n\n- **主报告** (`research-report.md`) - 结构化分析\n- **数据附件** (`artifacts\u002F`) - 原始抓取内容、热度摘要、竞品表格\n- **记忆写入** - 自动保存到 agentmemory，支持长期追踪\n\n## 工作流\n\n```mermaid\ngraph LR\n    A[任务: 研究 X] --> B[crawl4ai 深度抓取]\n    A --> C[trendradar 热点聚合]\n    B --> D[product-research 分析引擎]\n    C --> D\n    D --> E[生成结构化报告]\n    E --> F[保存到 agentmemory]\n    F --> G[推送结果]\n```\n\n### 阶段说明\n\n1. **数据采集** (Data Collection)\n   - crawl4ai: 抓取产品官网、竞品页、评测文章、用户评论\n   - trendradar: 获取微博\u002F知乎\u002F百度等平台的关联热点\n\n2. **数据分析** (Analysis)\n   - product-research: 应用标准框架（SWOT\u002FPEST\u002F竞品矩阵）\n   - AI 摘要: 提炼核心洞察、风险评估、机会点\n\n3. **知识存储** (Memory)\n   - 将本次研究的关键结论存入向量数据库\n   - 建立 `topic → timestamp → findings` 索引链\n\n4. **报告交付** (Delivery)\n   - 生成 Markdown 报告（支持微信阅读）\n   - 可选 HTML 可视化版本\n   - 通过 OpenClaw 消息通道推送\n\n## 使用示例\n\n### 基本调用\n```bash\n# 快速研究（1小时）\nai-market-research --topic \"宇树科技机器人\" --depth quick\n\n# 深度研究（8小时+）\nai-market-research --topic \"人形机器人赛道\" --depth deep --compare_previous true\n```\n\n### 指定数据源\n```bash\nai-market-research \\\n  --topic \"特斯拉FSD\" \\\n  --sources \"https:\u002F\u002Ftesla.com\u002Ffsd\" \"https:\u002F\u002F electrek.co\u002Ftesla-fsd-review\" \\\n  --output_format markdown\n```\n\n## 配置依赖\n\n### MCP 服务\n必须已启动：\n- `crawl4ai` (localhost:11235)\n- `trendradar` (localhost:3333)\n\n### 技能启用\n以下技能必须在 `openclaw.json` 中启用：\n- `product-research`\n- `agentmemory` (插件)\n- `vector-memory`（可选，用于历史对比）\n\n### 环境变量\n- `AI_API_KEY` - 用于 trendradar AI 分析（如果启用）\n- `OPENCLAW_WECHAT_TO` - 微信推送目标（optional）\n\n## 性能与成本\n\n| 深度 | 预计耗时 | crawl4ai 调用 | trendradar 调用 | LLM token 消耗 |\n|------|----------|--------------|----------------|----------------|\n| quick | ~1h | 5-10 URL | 1次（当日数据） | ~50k |\n| standard | ~4h | 20-30 URL | 3天历史 + 每日增量 | ~200k |\n| deep | ~8h+ | 50+ URL | 7天历史 + 全平台 | ~500k+ |\n\n## 故障排除\n\n### 常见问题\n\n1. **crawl4ai JWT 错误** → 检查 `CRAWL4AI_JWT` 环境变量\n2. **trendradar MCP 连接失败** → 确认 `uv run python -m mcp_server.server` 正在运行\n3. **memory 写入失败** → 确认 `agentmemory` 插件已启用\n4. **token 超限** → 降低 `depth` 或减少 `sources` 数量\n\n## 安装\n\n### 手动安装\n\n```bash\n# 克隆到技能目录\ngit clone https:\u002F\u002Fgithub.com\u002Fyourusername\u002Fai-market-research-skill.git \\\n  ~\u002F.openclaw\u002Fworkspace\u002F.agents\u002Fskills\u002Fai-market-research\n\n# 启用技能（添加到 openclaw.json）\n# 重启网关\nopenclaw gateway restart\n```\n\n### 通过 ClawHub（即将推出）\n\n搜索 `ai-market-research` 并一键安装。\n\n## Roadmap\n\n- [ ] 真实 MCP 调用（替换模拟数据）\n- [ ] product-research 深度集成\n- [ ] 自动来源发现（Google 搜索 + 筛选）\n- [ ] 向量历史对比（vector-memory）\n- [ ] Webhook 推送自动化\n- [ ] Docker 容器化\n- [ ] 多语言报告支持\n\n## License\n\nMIT © Chace\n",{"name":5,"author":24,"license":15,"version":25,"homepage":26,"categories":27,"description":7,"dependencies":31},"Chace","0.1.0","https:\u002F\u002Fgithub.com\u002Fyourusername\u002Fai-market-research-skill",[28,29,30],"research","automation","market-intelligence",{"mcp":32,"skills":35,"plugins":37},[33,34],"crawl4ai","trendradar",[36],"product-research",[38,39],"agentmemory","vector-memory","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fc\u002Fchace-ai-market-research",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill ai-market-research",{"tool":55,"command":56},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill ai-market-research",{"tool":58,"command":59},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill ai-market-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fc\u002Fchace-ai-market-research\u002FSKILL.md",true,[],[64,72,79,86,93,100],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":71},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":71},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":71},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":71},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":71},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":71},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]