analyze
installsforks
How to install analyze?
anthropics/knowledge-work-plugins/analyze
$npx -y skills add anthropics/knowledge-work-plugins --skill analyzeanalyze is an agent skill published from anthropics/knowledge-work-plugins, installable through the skills CLI.
SKILL.md
| 1 | # /analyze - Answer Data Questions |
| 2 | |
| 3 | > If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md). |
| 4 | |
| 5 | Answer a data question, from a quick lookup to a full analysis to a formal report. |
| 6 | |
| 7 | ## Usage |
| 8 | |
| 9 | ``` |
| 10 | /analyze <natural language question> |
| 11 | ``` |
| 12 | |
| 13 | ## Workflow |
| 14 | |
| 15 | ### 1. Understand the Question |
| 16 | |
| 17 | Parse the user's question and determine: |
| 18 | |
| 19 | - **Complexity level**: |
| 20 | - **Quick answer**: Single metric, simple filter, factual lookup (e.g., "How many users signed up last week?") |
| 21 | - **Full analysis**: Multi-dimensional exploration, trend analysis, comparison (e.g., "What's driving the drop in conversion rate?") |
| 22 | - **Formal report**: Comprehensive investigation with methodology, caveats, and recommendations (e.g., "Prepare a quarterly business review of our subscription metrics") |
| 23 | - **Data requirements**: Which tables, metrics, dimensions, and time ranges are needed |
| 24 | - **Output format**: Number, table, chart, narrative, or combination |
| 25 | |
| 26 | ### 2. Gather Data |
| 27 | |
| 28 | **If a data warehouse MCP server is connected:** |
| 29 | |
| 30 | 1. Explore the schema to find relevant tables and columns |
| 31 | 2. Write SQL query(ies) to extract the needed data |
| 32 | 3. Execute the query and retrieve results |
| 33 | 4. If the query fails, debug and retry (check column names, table references, syntax for the specific dialect) |
| 34 | 5. If results look unexpected, run sanity checks before proceeding |
| 35 | |
| 36 | **If no data warehouse is connected:** |
| 37 | |
| 38 | 1. Ask the user to provide data in one of these ways: |
| 39 | - Paste query results directly |
| 40 | - Upload a CSV or Excel file |
| 41 | - Describe the schema so you can write queries for them to run |
| 42 | 2. If writing queries for manual execution, use the `sql-queries` skill for dialect-specific best practices |
| 43 | 3. Once data is provided, proceed with analysis |
| 44 | |
| 45 | ### 3. Analyze |
| 46 | |
| 47 | - Calculate relevant metrics, aggregations, and comparisons |
| 48 | - Identify patterns, trends, outliers, and anomalies |
| 49 | - Compare across dimensions (time periods, segments, categories) |
| 50 | - For complex analyses, break the problem into sub-questions and address each |
| 51 | |
| 52 | ### 4. Validate Before Presenting |
| 53 | |
| 54 | Before sharing results, run through validation checks: |
| 55 | |
| 56 | - **Row count sanity**: Does the number of records make sense? |
| 57 | - **Null check**: Are there unexpected nulls that could skew results? |
| 58 | - **Magnitude check**: Are the numbers in a reasonable range? |
| 59 | - **Trend continuity**: Do time series have unexpected gaps? |
| 60 | - **Aggregation logic**: Do subtotals sum to totals correctly? |
| 61 | |
| 62 | If any check raises concerns, investigate and note caveats. |
| 63 | |
| 64 | ### 5. Present Findings |
| 65 | |
| 66 | **For quick answers:** |
| 67 | - State the answer directly with relevant context |
| 68 | - Include the query used (collapsed or in a code block) for reproducibility |
| 69 | |
| 70 | **For full analyses:** |
| 71 | - Lead with the key finding or insight |
| 72 | - Support with data tables and/or visualizations |
| 73 | - Note methodology and any caveats |
| 74 | - Suggest follow-up questions |
| 75 | |
| 76 | **For formal reports:** |
| 77 | - Executive summary with key takeaways |
| 78 | - Methodology section explaining approach and data sources |
| 79 | - Detailed findings with supporting evidence |
| 80 | - Caveats, limitations, and data quality notes |
| 81 | - Recommendations and suggested next steps |
| 82 | |
| 83 | ### 6. Visualize Where Helpful |
| 84 | |
| 85 | When a chart would communicate results more effectively than a table: |
| 86 | |
| 87 | - Use the `data-visualization` skill to select the right chart type |
| 88 | - Generate a Python visualization or build it into an HTML dashboard |
| 89 | - Follow visualization best practices for clarity and accuracy |
| 90 | |
| 91 | ## Examples |
| 92 | |
| 93 | **Quick answer:** |
| 94 | ``` |
| 95 | /analyze How many new users signed up in December? |
| 96 | ``` |
| 97 | |
| 98 | **Full analysis:** |
| 99 | ``` |
| 100 | /analyze What's causing the increase in support ticket volume over the past 3 months? Break down by category and priority. |
| 101 | ``` |
| 102 | |
| 103 | **Formal report:** |
| 104 | ``` |
| 105 | /analyze Prepare a data quality assessment of our customer table -- completeness, consistency, and any issues we should address. |
| 106 | ``` |
| 107 | |
| 108 | ## Tips |
| 109 | |
| 110 | - Be specific about time ranges, segments, or metrics when possible |
| 111 | - If you know the table names, mention them to speed up the process |
| 112 | - For complex questions, Claude may break them into multiple queries |
| 113 | - Results are always validated before presentation -- if something looks off, Claude will flag it |
People who liked this also viewed
6 picksType
- lark-drive飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sSkillsJul 2026
- lark-sharedUse for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handlingSkillsJul 2026
- lark-whiteboard飞书画板：查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用多种格式更新画板内容。 当用户需要查看画板内容、导出画板图片、编辑画板时使用此 skill。不负责：飞书云文档内容编辑（lark-doc）、文档内嵌电子表格/Base（lark-sheets / lark-base）。SkillsJul 2026
- lark-task飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更新智能体主页数据、写入任务记录时使用。SkillsJul 2026
- lark-attendance飞书考勤打卡：查询自己的考勤打卡记录SkillsJul 2026
- lark-apps妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要SkillsJul 2026
