# Send Excel weekly dashboards at scale to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "excel-weekly-dashboard", "name": "Excel weekly dashboards at scale", "source": "tencent", "type": "skill", "category": "数据分析", "sourceUrl": "https://clawhub.ai/KOwl64/excel-weekly-dashboard", "canonicalUrl": "https://clawhub.ai/KOwl64/excel-weekly-dashboard", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/excel-weekly-dashboard", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=excel-weekly-dashboard", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "assets/power-query-folder-ingest-template.pq.md", "assets/refresh-checklist.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "excel-weekly-dashboard", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T10:24:28.128Z", "expiresAt": "2026-05-06T10:24:28.128Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=excel-weekly-dashboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=excel-weekly-dashboard", "contentDisposition": "attachment; filename=\"excel-weekly-dashboard-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "excel-weekly-dashboard" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/excel-weekly-dashboard" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/excel-weekly-dashboard", "downloadUrl": "https://openagent3.xyz/downloads/excel-weekly-dashboard", "agentUrl": "https://openagent3.xyz/skills/excel-weekly-dashboard/agent", "manifestUrl": "https://openagent3.xyz/skills/excel-weekly-dashboard/agent.json", "briefUrl": "https://openagent3.xyz/skills/excel-weekly-dashboard/agent.md" } } ``` ## Documentation ### PURPOSE Designs refreshable Excel dashboards (Power Query + structured tables + validation + pivot reporting). ### WHEN TO USE TRIGGERS: Build me a Power Query pipeline for this file so it refreshes weekly with no manual steps. Turn this into a structured table with validation lists and clean data entry rules. Create a pivot-driven weekly dashboard with slicers for year and ISO week. Fix this Excel model so refresh does not break when new columns appear. Design a reusable KPI pack that updates from a folder of CSVs. DO NOT USE WHEN… You need advanced forecasting/valuation modeling (this skill is for repeatable reporting pipelines). You need a BI tool build (Power BI/Tableau) rather than Excel. You need web scraping as the primary ingestion method. ### INPUTS REQUIRED: Source data file(s): CSV, XLSX, DOCX-exported tables, or PDF-exported tables (provided by user). Definition of ‘week’ (ISO week preferred) and the KPI fields required. OPTIONAL: Data dictionary / column definitions. Known “bad data” patterns to validate (e.g., blank PayNumber, invalid dates). Existing workbook to refactor. EXAMPLES: Folder of weekly CSV exports: exports/2026-W02/*.csv Single XLSX dump with changing columns month to month ### OUTPUTS If asked for plan only (default): a step-by-step build plan + Power Query steps + sheet layout + validation rules. If explicitly asked to generate artifacts: workbook_spec.md (workbook structure and named tables) power_query_steps.pq (M code template) refresh-checklist.md (from assets/) Success = refresh works after adding a new week’s files without manual edits, and validation catches bad rows. ### WORKFLOW Identify source type(s) (CSV/XLSX/DOCX/PDF-export) and the stable business keys (e.g., PayNumber). Define the canonical table schema: required columns, types, allowed values, and “unknown” handling. Design ingestion with Power Query: Prefer Folder ingest + combine, with defensive “missing column” handling. Normalize column names (trim, case, collapse spaces). Design cleansing & validation: Create a Data_Staging query (raw-normalized) and Data_Clean query (validated). Add validation columns (e.g., IsValidPayNumber, IsValidDate, IssueReason). Build reporting layer: Pivot table(s) off Data_Clean Slicers: Year, ISOWeek; plus operational dimensions Add a “Refresh Status” sheet: last refresh timestamp, row counts, query error flags, latest week present STOP AND ASK THE USER if: required KPIs/columns are unspecified, the source files don’t include any stable key, week definition/timezone rules are unclear, PDF/DOCX tables are not reliably extractable without a provided export. ### OUTPUT FORMAT When producing a plan, use this template: WORKBOOK PLAN - Sheets: - Data_Staging (query output) - Data_Clean (query output + validation flags) - Dashboard (pivots/charts) - Refresh_Status (counts + health checks) - Canonical Schema: - : | Required? | Validation - Power Query: - Query 1: Ingest_ (Folder/File) - Query 2: Clean_ - Key transforms: - Validation rules: - -> - Pivot design: - Rows/Columns/Values - Slicers If asked for artifacts, also output: assets/power-query-folder-ingest-template.pq (adapted) assets/refresh-checklist.md ### SAFETY & EDGE CASES Read-only by default: provide a plan + snippets unless the user explicitly requests file generation. Never delete or overwrite user files; propose new filenames for outputs. Prefer “no silent failure”: include row-count checks and visible error flags. For PDF/DOCX sources, require user-provided exported tables (CSV/XLSX) or clearly mark extraction risk. ### EXAMPLES Input: “Folder of weekly CSVs with PayNumber/Name/Date.” Output: Folder-ingest PQ template + schema + Refresh Status checks + pivot dashboard plan. Input: “Refresh breaks when new columns appear.” Output: Defensive missing-column logic + column normalization + typed schema plan. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: KOwl64 - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-29T10:24:28.128Z - Expires at: 2026-05-06T10:24:28.128Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/excel-weekly-dashboard) - [Send to Agent page](https://openagent3.xyz/skills/excel-weekly-dashboard/agent) - [JSON manifest](https://openagent3.xyz/skills/excel-weekly-dashboard/agent.json) - [Markdown brief](https://openagent3.xyz/skills/excel-weekly-dashboard/agent.md) - [Download page](https://openagent3.xyz/downloads/excel-weekly-dashboard)