{"id":"4e4d49dc-d0c0-4ed8-9d08-c646b2114d5b","entityType":"agent","slug":"clawhub-ming0429-ad-analyzer-yima","name":"广告数据分析","canonicalUrl":"https://www.xpersona.co/agent/clawhub-ming0429-ad-analyzer-yima","canonicalPath":"/agent/clawhub-ming0429-ad-analyzer-yima","generatedAt":"2026-10-11T15:15:52.545Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T12:27:09.636Z","emptyReason":null},"description":"广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导... Skill: 广告数据分析 Owner: ming0429 Summary: 广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导... Tags: advertising:1.0.1, data-analyzer:1.0.2, latest:1.0.2 Version history: v1.0.2 | 2026-04-16T06:11:09.989Z | user **New version adds automated data visualization and script-based analysis.** - Added scripts/analyze.py","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s174ep1mzq3b0mz7q623kj2wfd84tj1c:ad-analyzer-yima","sourceUrl":"https://clawhub.ai/ming0429/ad-analyzer-yima","homepage":"https://clawhub.ai/ming0429/skills/ad-analyzer-yima","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/ming0429/ad-analyzer-yima","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/ming0429/skills/ad-analyzer-yima","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T12:27:09.636Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T12:27:09.636Z","emptyReason":null},"stars":null,"forks":null,"downloads":1065,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"1.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T12:27:09.579Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T12:27:09.636Z","lastCrawledAt":"2026-10-11T12:27:09.579Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T12:27:09.579Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-04-16T06:11:09.989Z","changelog":"**New version adds automated data visualization and script-based analysis.** - Added scripts/analyze.py for one-click automated广告报表分析 and图表生成功能. - 现支持自动输出 5 张 PNG 图表（数据总量柱状图、维度对比、趋势线、指标相关性热力图、主维度饼图）. - 增强依赖声明，集成 pandas、openpyxl、xlrd、matplotlib、seaborn. - 强调仅支持保存为 .py 文件运行，内联 (python3 -c) 不再适用. - 更新说明文档，细化分析流程与图表输出位置.","fileCount":4,"zipByteSize":7645},{"version":"1.0.1","createdAt":"2026-04-15T02:31:27.268Z","changelog":"- Added pip install requirements for pandas, openpyxl, and xlrd to improve compatibility with Excel/CSV file formats. - No changes to core functionality, API, or usage. - All analytics features and workflows remain the same.","fileCount":2,"zipByteSize":2863},{"version":"1.0.0","createdAt":"2026-04-15T02:21:00.496Z","changelog":"- Initial release of ad-analyzer-yima for ad campaign data analysis. - Automatically detects all columns and aggregates all metrics in uploaded Excel/CSV ad reports. - Identifies dimension, date, and numeric columns without preset field names; supports multiple ad platforms’ export formats. - Performs anomaly detection, trend analysis, and groups data by dimensions for detailed reporting. - Outputs a complete analysis report with findings and optimization suggestions, fully compatible with UTF-8/GBK encoding. - No setup required; supports large files and does not transmit data externally.","fileCount":2,"zipByteSize":2845}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s174ep1mzq3b0mz7q623kj2wfd84tj1c:ad-analyzer-yima","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ming0429-ad-analyzer-yima/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ming0429-ad-analyzer-yima/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ming0429-ad-analyzer-yima/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ming0429-ad-analyzer-yima/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ming0429-ad-analyzer-yima/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ming0429-ad-analyzer-yima/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T15:15:52.545Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ming0429-ad-analyzer-yima/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ming0429-ad-analyzer-yima/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ming0429-ad-analyzer-yima/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ming0429-ad-analyzer-yima/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T12:27:09.636Z","emptyReason":null},"readme":"Skill: 广告数据分析\n\nOwner: ming0429\n\nSummary: 广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导...\n\nTags: advertising:1.0.1, data-analyzer:1.0.2, latest:1.0.2\n\nVersion history:\n\nv1.0.2 | 2026-04-16T06:11:09.989Z | user\n\n**New version adds automated data visualization and script-based analysis.**\n\n- Added scripts/analyze.py for one-click automated广告报表分析 and图表生成功能.\n- 现支持自动输出 5 张 PNG 图表（数据总量柱状图、维度对比、趋势线、指标相关性热力图、主维度饼图）.\n- 增强依赖声明，集成 pandas、openpyxl、xlrd、matplotlib、seaborn.\n- 强调仅支持保存为 .py 文件运行，内联 (python3 -c) 不再适用.\n- 更新说明文档，细化分析流程与图表输出位置.\n\nv1.0.1 | 2026-04-15T02:31:27.268Z | user\n\n- Added pip install requirements for pandas, openpyxl, and xlrd to improve compatibility with Excel/CSV file formats.\n- No changes to core functionality, API, or usage.\n- All analytics features and workflows remain the same.\n\nv1.0.0 | 2026-04-15T02:21:00.496Z | auto\n\n- Initial release of ad-analyzer-yima for ad campaign data analysis.\n- Automatically detects all columns and aggregates all metrics in uploaded Excel/CSV ad reports.\n- Identifies dimension, date, and numeric columns without preset field names; supports multiple ad platforms’ export formats.\n- Performs anomaly detection, trend analysis, and groups data by dimensions for detailed reporting.\n- Outputs a complete analysis report with findings and optimization suggestions, fully compatible with UTF-8/GBK encoding.\n- No setup required; supports large files and does not transmit data externally.\n\nArchive index:\n\nArchive v1.0.2: 4 files, 7645 bytes\n\nFiles: scripts/analyze.py (11962b), skill-card.md (2452b), SKILL.md (2869b), _meta.json (135b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: ad-analyzer-yima\ndescription: 广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导出格式。\nhomepage: https://clawhub.ai/ming0429/ad-analyzer-yima\nversion: 1.1.0\nauthor: guojiaming\ntags: [advertising, analytics, excel, csv, 广告分析, 投放优化, 数据可视化, chart]\nmetadata:\n  clawdbot:\n    emoji: 📊\n    requires:\n      bins: [python3]\n      pip: [pandas, openpyxl, xlrd, matplotlib, seaborn]\n      env: []\n---\n\n# 广告数据分析 Skill\n\n分析用户上传的广告报表，自动识别所有列，汇总指标，检测异常，生成图表，输出优化建议。\n\n## Setup\n\n无需任何配置，开箱即用。支持 `.xlsx` / `.xls` / `.csv`，兼容 UTF-8 / GBK 编码。\n\n## Usage\n\n用户上传文件后，将完整分析脚本保存为文件再执行。**不要用 `-c` 内联方式运行**，内联模式不支持多行缩进代码。\n\n正确执行方式：\n```bash\n# 第一步：把 scripts/analyze.py 脚本保存到本地\n# 第二步：执行\npython3 analyze.py --file /path/to/report.xlsx --out ./charts\n```\n\n## 分析脚本说明\n\n脚本位于 `scripts/analyze.py`，执行后自动完成以下步骤：\n\n1. **读取文件** — 自动识别 xlsx/xls/csv，自动尝试 utf-8/gbk 编码\n2. **识别列类型** — 自动区分日期列、维度列（文字）、指标列（数值），不预设列名\n3. **汇总指标** — 所有数值列的合计、均值、最大值、最小值\n4. **分组分析** — 按每个维度列分组汇总，自动排序\n5. **异常检测** — 均值 ±2 倍标准差自动标记异常行\n6. **生成图表** — 输出 5 张 PNG 图表\n7. **输出建议** — 基于数据给出具体优化方向\n\n## 图表输出\n\n| 文件名 | 内容 |\n|--------|------|\n| chart_1_totals.png | 各指标总量柱状图 |\n| chart_2_dim_compare.png | 主维度横向对比图 |\n| chart_3_trend.png | 指标趋势折线图（有日期列时） |\n| chart_4_correlation.png | 指标相关性热力图（指标≥3时） |\n| chart_5_pie.png | 主维度占比饼图 |\n\n## Notes\n\n- 必须保存为 `.py` 文件执行，不支持 `python3 -c` 内联模式\n- 完全动态识别列名，表头是什么分析什么，一列不漏\n- 数据不外传，完全本地处理\n- 编码自动识别，兼容国内广告平台导出文件\n\n## Examples\n\n分析巨量引擎报表：\n```bash\npython3 analyze.py --file ~/Downloads/report.xlsx --out ~/Desktop/charts\n```\n\n分析腾讯广告 CSV：\n```bash\npython3 analyze.py --file ~/Downloads/tencent.csv --out ~/Desktop/charts\n```\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn75qh8ba8e3ekf513rveqqstx84tt20\",\n  \"slug\": \"ad-analyzer-yima\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1776319869989\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\n广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导出格式。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[ming0429](https://clawhub.ai/user/ming0429)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nMarketing operators, analysts, and agent users can use this skill to analyze user-provided advertising Excel or CSV reports, identify metrics and anomalies, generate local charts, and draft optimization guidance across common ad-platform export formats.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Advertising reports can contain sensitive business data.\n\nMitigation: Run the analyzer only on reports intentionally provided by the user and keep generated chart files in an appropriate local output folder.\n\nRisk: Automated optimization suggestions may be incomplete or misleading for business decisions.\n\nMitigation: Review the generated recommendations against campaign context before changing budgets, pausing ads, or reallocating spend.\n\nRisk: The skill installs standard Python data-analysis packages and writes PNG outputs.\n\nMitigation: Use a trusted Python environment and choose an output directory where generated chart files are expected.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/ming0429/skills/ad-analyzer-yima)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Shell commands, Code, Files, Guidance]\n\n**Output Format:** [Markdown guidance with bash command examples, console analysis text, and local PNG chart files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires python3 plus pandas, openpyxl, xlrd, matplotlib, and seaborn; reads user-provided Excel/CSV files locally and writes charts to the selected output directory.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.1: 2 files, 2863 bytes\n\nFiles: SKILL.md (5006b), _meta.json (135b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: ad-analyzer-yima\ndescription: 广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/数据有没有问题/哪个计划效果差\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导出格式。\nhomepage: https://clawhub.ai/ming0429/ad-analyzer-yima\nversion: 1.0.0\nauthor: guojiaming\ntags: [advertising, analytics, excel, csv, 广告分析, 投放优化, 数据可视化]\nmetadata:\n  clawdbot:\n    emoji: 📊\n    requires:\n      bins: [python3]\n      pip: [pandas, openpyxl, xlrd]\n      env: []\n---\n\n# 广告数据分析 Skill\n\n分析用户上传的广告报表文件，自动识别所有列，汇总指标，发现异常，输出优化建议。\n\n## Setup\n\n无需任何配置，开箱即用。支持 `.xlsx` / `.xls` / `.csv` 格式，兼容 UTF-8 和 GBK 编码。\n\n## Usage\n\n### 第一步：读取文件，识别所有列\n\n```python\nimport pandas as pd\n\n# 自动识别编码和格式\ntry:\n    df = pd.read_excel(\"report.xlsx\")\nexcept:\n    try:\n        df = pd.read_csv(\"report.csv\", encoding=\"utf-8\")\n    except:\n        df = pd.read_csv(\"report.csv\", encoding=\"gbk\")\n\n# 输出所有列名和前3行，让 AI 理解表头含义\nprint(\"列名：\", df.columns.tolist())\nprint(\"行数：\", len(df))\nprint(df.head(3).to_string())\n```\n\n读取后，根据列名语义判断：\n- **日期列**：值格式为日期（2024-01-01、20240101 等）\n- **维度列**：文字类，如广告计划、广告组、地区、性别、创意名称\n- **指标列**：数值类，全部列出，一列不漏\n\n### 第二步：汇总所有数值指标\n\n```python\n# 识别所有数值列（不预设列名，完全由表头决定）\nnumeric_cols = df.select_dtypes(include='number').columns.tolist()\ntext_cols = df.select_dtypes(include='object').columns.tolist()\n\nprint(\"=== 全量指标汇总 ===\")\nprint(df[numeric_cols].sum().to_string())\n\nprint(\"\\n=== 均值 ===\")\nprint(df[numeric_cols].mean().round(2).to_string())\n```\n\n### 第三步：按维度分组分析\n\n```python\n# 按每个维度列分组，汇总所有数值指标\nfor col in text_cols:\n    if df[col].nunique() <= 50:  # 维度值不超过50个时分析\n        grouped = df.groupby(col)[numeric_cols].sum()\n        grouped = grouped.sort_values(numeric_cols[0], ascending=False)\n        print(f\"\\n=== 按【{col}】分组 ===\")\n        print(grouped.to_string())\n```\n\n### 第四步：趋势分析（有日期列时）\n\n```python\n# 检测日期列\ndate_col = None\nfor col in df.columns:\n    try:\n        pd.to_datetime(df[col])\n        date_col = col\n        break\n    except:\n        continue\n\nif date_col:\n    df[date_col] = pd.to_datetime(df[date_col])\n    daily = df.groupby(date_col)[numeric_cols].sum().sort_index()\n    print(\"\\n=== 日期趋势 ===\")\n    print(daily.to_string())\n```\n\n### 第五步：异常检测\n\n```python\n# 对每个数值列检测异常波动\nfor col in numeric_cols:\n    mean_val = df[col].mean()\n    std_val = df[col].std()\n    outliers = df[df[col] > mean_val + 2 * std_val]\n    if len(outliers):\n        print(f\"【{col}】异常高值：{len(outliers)} 行，均值 {mean_val:.2f}，阈值 {mean_val + 2*std_val:.2f}\")\n```\n\n### 第六步：输出分析报告\n\n按以下结构输出（Markdown 格式）：\n\n```\n## 投放概览\n[2-3句总结整体表现]\n\n## 数据详情\n[全量指标汇总表格]\n[主维度分组表格，按第一个数值指标降序]\n\n## 关键发现\n1. [最重要的发现，附具体数字]\n2. [第二重要发现]\n3. [异常情况说明]\n\n## 优化建议\n- [具体可执行的动作，如\"暂停XX计划\"、\"增加XX维度预算\"]\n\n## 需关注\n[数据缺口或需人工核查的问题]\n```\n\n## Notes\n\n- **完全动态识别**：不预设任何列名，表头是什么就分析什么\n- **全列覆盖**：所有数值列都会参与汇总和分析，不遗漏\n- **不对接 API**：只处理本地上传的文件，数据不外传\n- **编码兼容**：自动识别 UTF-8 / GBK，兼容国内平台导出的 CSV\n- **大文件处理**：超过 10 万行建议按时间段拆分上传\n\n## Examples\n\n**场景 1：巨量引擎周报分析**\n> \"这是上周巨量引擎的投放报表，帮我看看哪些计划效果差\"\n\n执行流程：\n1. 读取文件，识别列名（日期、广告计划、消费、展示数、点击数、转化数）\n2. 汇总全量：总消费、总点击、总转化\n3. 按\"广告计划\"分组，找出消费最高和转化最差的计划\n4. 检测异常：某计划 CPA 超均值 150% 则标红\n5. 输出建议：暂停高 CPA 计划，预算转移至效果最优计划\n\n**场景 2：多维度交叉分析**\n> \"帮我看看不同地区、不同时段的投放效果\"\n\n执行流程：\n1. 识别维度列：地区、时段\n2. 分别按地区、时段分组汇总所有数值指标\n3. 找出高效地区和黄金时段\n4. 输出交叉分析建议\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn75qh8ba8e3ekf513rveqqstx84tt20\",\n  \"slug\": \"ad-analyzer-yima\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1776220287268\n}\n\nArchive v1.0.0: 2 files, 2845 bytes\n\nFiles: SKILL.md (4970b), _meta.json (135b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: ad-analyzer-yima\ndescription: 广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/数据有没有问题/哪个计划效果差\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导出格式。\nhomepage: https://clawhub.ai/ming0429/ad-analyzer-yima\nversion: 1.0.0\nauthor: guojiaming\ntags: [advertising, analytics, excel, csv, 广告分析, 投放优化, 数据可视化]\nmetadata:\n  clawdbot:\n    emoji: 📊\n    requires:\n      bins: [python3]\n      env: []\n---\n\n# 广告数据分析 Skill\n\n分析用户上传的广告报表文件，自动识别所有列，汇总指标，发现异常，输出优化建议。\n\n## Setup\n\n无需任何配置，开箱即用。支持 `.xlsx` / `.xls` / `.csv` 格式，兼容 UTF-8 和 GBK 编码。\n\n## Usage\n\n### 第一步：读取文件，识别所有列\n\n```python\nimport pandas as pd\n\n# 自动识别编码和格式\ntry:\n    df = pd.read_excel(\"report.xlsx\")\nexcept:\n    try:\n        df = pd.read_csv(\"report.csv\", encoding=\"utf-8\")\n    except:\n        df = pd.read_csv(\"report.csv\", encoding=\"gbk\")\n\n# 输出所有列名和前3行，让 AI 理解表头含义\nprint(\"列名：\", df.columns.tolist())\nprint(\"行数：\", len(df))\nprint(df.head(3).to_string())\n```\n\n读取后，根据列名语义判断：\n- **日期列**：值格式为日期（2024-01-01、20240101 等）\n- **维度列**：文字类，如广告计划、广告组、地区、性别、创意名称\n- **指标列**：数值类，全部列出，一列不漏\n\n### 第二步：汇总所有数值指标\n\n```python\n# 识别所有数值列（不预设列名，完全由表头决定）\nnumeric_cols = df.select_dtypes(include='number').columns.tolist()\ntext_cols = df.select_dtypes(include='object').columns.tolist()\n\nprint(\"=== 全量指标汇总 ===\")\nprint(df[numeric_cols].sum().to_string())\n\nprint(\"\\n=== 均值 ===\")\nprint(df[numeric_cols].mean().round(2).to_string())\n```\n\n### 第三步：按维度分组分析\n\n```python\n# 按每个维度列分组，汇总所有数值指标\nfor col in text_cols:\n    if df[col].nunique() <= 50:  # 维度值不超过50个时分析\n        grouped = df.groupby(col)[numeric_cols].sum()\n        grouped = grouped.sort_values(numeric_cols[0], ascending=False)\n        print(f\"\\n=== 按【{col}】分组 ===\")\n        print(grouped.to_string())\n```\n\n### 第四步：趋势分析（有日期列时）\n\n```python\n# 检测日期列\ndate_col = None\nfor col in df.columns:\n    try:\n        pd.to_datetime(df[col])\n        date_col = col\n        break\n    except:\n        continue\n\nif date_col:\n    df[date_col] = pd.to_datetime(df[date_col])\n    daily = df.groupby(date_col)[numeric_cols].sum().sort_index()\n    print(\"\\n=== 日期趋势 ===\")\n    print(daily.to_string())\n```\n\n### 第五步：异常检测\n\n```python\n# 对每个数值列检测异常波动\nfor col in numeric_cols:\n    mean_val = df[col].mean()\n    std_val = df[col].std()\n    outliers = df[df[col] > mean_val + 2 * std_val]\n    if len(outliers):\n        print(f\"【{col}】异常高值：{len(outliers)} 行，均值 {mean_val:.2f}，阈值 {mean_val + 2*std_val:.2f}\")\n```\n\n### 第六步：输出分析报告\n\n按以下结构输出（Markdown 格式）：\n\n```\n## 投放概览\n[2-3句总结整体表现]\n\n## 数据详情\n[全量指标汇总表格]\n[主维度分组表格，按第一个数值指标降序]\n\n## 关键发现\n1. [最重要的发现，附具体数字]\n2. [第二重要发现]\n3. [异常情况说明]\n\n## 优化建议\n- [具体可执行的动作，如\"暂停XX计划\"、\"增加XX维度预算\"]\n\n## 需关注\n[数据缺口或需人工核查的问题]\n```\n\n## Notes\n\n- **完全动态识别**：不预设任何列名，表头是什么就分析什么\n- **全列覆盖**：所有数值列都会参与汇总和分析，不遗漏\n- **不对接 API**：只处理本地上传的文件，数据不外传\n- **编码兼容**：自动识别 UTF-8 / GBK，兼容国内平台导出的 CSV\n- **大文件处理**：超过 10 万行建议按时间段拆分上传\n\n## Examples\n\n**场景 1：巨量引擎周报分析**\n> \"这是上周巨量引擎的投放报表，帮我看看哪些计划效果差\"\n\n执行流程：\n1. 读取文件，识别列名（日期、广告计划、消费、展示数、点击数、转化数）\n2. 汇总全量：总消费、总点击、总转化\n3. 按\"广告计划\"分组，找出消费最高和转化最差的计划\n4. 检测异常：某计划 CPA 超均值 150% 则标红\n5. 输出建议：暂停高 CPA 计划，预算转移至效果最优计划\n\n**场景 2：多维度交叉分析**\n> \"帮我看看不同地区、不同时段的投放效果\"\n\n执行流程：\n1. 识别维度列：地区、时段\n2. 分别按地区、时段分组汇总所有数值指标\n3. 找出高效地区和黄金时段\n4. 输出交叉分析建议\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn75qh8ba8e3ekf513rveqqstx84tt20\",\n  \"slug\": \"ad-analyzer-yima\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1776219660496\n}","readmeExcerpt":"Skill: 广告数据分析 Owner: ming0429 Summary: 广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导... Tags: advertising:1.0.1, data-analyzer:1.0.2, latest:1.0.2 Version history: v1.0.2 | 2026-04-16T06:11:09.989Z | user **New version adds automated data visualization and script-based analysis.** - Added scripts/analyze.py","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# 第一步：把 scripts/analyze.py 脚本保存到本地\n# 第二步：执行\npython3 analyze.py --file /path/to/report.xlsx --out ./charts"},{"language":"bash","snippet":"python3 analyze.py --file ~/Downloads/report.xlsx --out ~/Desktop/charts"},{"language":"bash","snippet":"python3 analyze.py --file ~/Downloads/tencent.csv --out ~/Desktop/charts"},{"language":"python","snippet":"import pandas as pd\n\n# 自动识别编码和格式\ntry:\n    df = pd.read_excel(\"report.xlsx\")\nexcept:\n    try:\n        df = pd.read_csv(\"report.csv\", encoding=\"utf-8\")\n    except:\n        df = pd.read_csv(\"report.csv\", encoding=\"gbk\")\n\n# 输出所有列名和前3行，让 AI 理解表头含义\nprint(\"列名：\", df.columns.tolist())\nprint(\"行数：\", len(df))\nprint(df.head(3).to_string())"},{"language":"python","snippet":"# 识别所有数值列（不预设列名，完全由表头决定）\nnumeric_cols = df.select_dtypes(include='number').columns.tolist()\ntext_cols = df.select_dtypes(include='object').columns.tolist()\n\nprint(\"=== 全量指标汇总 ===\")\nprint(df[numeric_cols].sum().to_string())\n\nprint(\"\\n=== 均值 ===\")\nprint(df[numeric_cols].mean().round(2).to_string())"},{"language":"python","snippet":"# 按每个维度列分组，汇总所有数值指标\nfor col in text_cols:\n    if df[col].nunique() <= 50:  # 维度值不超过50个时分析\n        grouped = df.groupby(col)[numeric_cols].sum()\n        grouped = grouped.sort_values(numeric_cols[0], ascending=False)\n        print(f\"\\n=== 按【{col}】分组 ===\")\n        print(grouped.to_string())"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: ad-analyzer-yima\ndescription: 广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导出格式。\nhomepage: https://clawhub.ai/ming0429/ad-analyzer-yima\nversion: 1.1.0\nauthor: guojiaming\ntags: [advertising, analytics, excel, csv, 广告分析, 投放优化, 数据可视化, chart]\nmetadata:\n  clawdbot:\n    emoji: 📊\n    requires:\n      bins: [python3]\n      pip: [pandas, openpyxl, xlrd, matplotlib, seaborn]\n      env: []\n---\n\n# 广告数据分析 Skill\n\n分析用户上传的广告报表，自动识别所有列，汇总指标，检测异常，生成图表，输出优化建议。\n\n## Setup\n\n无需任何配置，开箱即用。支持 `.xlsx` / `.xls` / `.csv`，兼容 UTF-8 / GBK 编码。\n\n## Usage\n\n用户上传文件后，将完整分析脚本保存为文件再执行。**不要用 `-c` 内联方式运行**，内联模式不支持多行缩进代码。\n\n正确执行方式：\n```bash\n# 第一步：把 scripts/analyze.py 脚本保存到本地\n# 第二步：执行\npython3 analyze.py --file /path/to/report.xlsx --out ./charts\n```\n\n## 分析脚本说明\n\n脚本位于 `scripts/analyze.py`，执行后自动完成以下步骤：\n\n1. **读取文件** — 自动识别 xlsx/xls/csv，自动尝试 utf-8/gbk 编码\n2. **识别列类型** — 自动区分日期列、维度列（文字）、指标列（数值），不预设列名\n3. **汇总指标** — 所有数值列的合计、均值、最大值、最小值\n4. **分组分析** — 按每个维度列分组汇总，自动排序\n5. **异常检测** — 均值 ±2 倍标准差自动标记异常行\n6. **生成图表** — 输出 5 张 PNG 图表\n7. **输出建议** — 基于数据给出具体优化方向\n\n## 图表输出\n\n| 文件名 | 内容 |\n|--------|------|\n| chart_1_totals.png | 各指标总量柱状图 |\n| chart_2_dim_compare.png | 主维度横向对比图 |\n| chart_3_trend.png | 指标趋势折线图（有日期列时） |\n| chart_4_correlation.png | 指标相关性热力图（指标≥3时） |\n| chart_5_pie.png | 主维度占比饼图 |\n\n## Notes\n\n- 必须保存为 `.py` 文件执行，不支持 `python3 -c` 内联模式\n- 完全动态识别列名，表头是什么分析什么，一列不漏\n- 数据不外传，完全本地处理\n- 编码自动识别，兼容国内广告平台导出文件\n\n## Examples\n\n分析巨量引擎报表：\n```bash\npython3 analyze.py --file ~/Downloads/report.xlsx --out ~/Desktop/charts\n```\n\n分析腾讯广告 CSV：\n```bash\npython3 analyze.py --file ~/Downloads/tencent.csv --out ~/Desktop/charts\n```"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn75qh8ba8e3ekf513rveqqstx84tt20\",\n  \"slug\": \"ad-analyzer-yima\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1776319869989\n}"},{"path":"skill-card.md","content":"## Description:\n\n广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导出格式。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[ming0429](https://clawhub.ai/user/ming0429)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nMarketing operators, analysts, and agent users can use this skill to analyze user-provided advertising Excel or CSV reports, identify metrics and anomalies, generate local charts, and draft optimization guidance across common ad-platform export formats.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Advertising reports can contain sensitive business data.\n\nMitigation: Run the analyzer only on reports intentionally provided by the user and keep generated chart files in an appropriate local output folder.\n\nRisk: Automated optimization suggestions may be incomplete or misleading for business decisions.\n\nMitigation: Review the generated recommendations against campaign context before changing budgets, pausing ads, or reallocating spend.\n\nRisk: The skill installs standard Python data-analysis packages and writes PNG outputs.\n\nMitigation: Use a trusted Python environment and choose an output directory where generated chart files are expected.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/ming0429/skills/ad-analyzer-yima)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Shell commands, Code, Files, Guidance]\n\n**Output Format:** [Markdown guidance with bash command examples, console analysis text, and local PNG chart files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires python3 plus pandas, openpyxl, xlrd, matplotlib, and seaborn; reads user-provided Excel/CSV files locally and writes charts to the selected output directory.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导... Skill: 广告数据分析 Owner: ming0429 Summary: 广告投放数据分析。当用户上传 Excel/CSV 广告报表，或说\"帮我分析投放数据/看看这个报表/哪个计划效果差/数据有没有问题\"时触发。自动识别所有表头列，无需预设字段名，汇总全部指标，检测异常，生成可视化图表，输出分析报告和优化建议。支持巨量引擎、腾讯广告、Meta Ads、Google Ads、快手等平台导... Tags: advertising:1.0.1, data-analyzer:1.0.2, latest:1.0.2 Version history: v1.0.2 | 2026-04-16T06:11:09.989Z | user **New version adds automated data visualization and script-based analysis.** - Added scripts/analyze.py","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":816,"uniquenessScore":58,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T12:27:09.636Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T12:27:09.636Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:15:52.545Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}