weekly-crm-report

Featured

Cleans a weekly CRM export and produces a regional sales summary. Activates when the user asks to clean a CRM export, deduplicate sales rows, calculate regional totals, or generate a weekly sales report from a CSV.

Data & Documents 2,382 stars 262 forks Updated 1 weeks ago MIT

Install

View on GitHub

Quality Score: 94/100

Stars 20%
100
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Weekly CRM Report Turn a raw weekly CRM export (CSV) into a clean regional sales summary: drop duplicate rows, total revenue per region, and emit a structured JSON summary an agent can narrate or hand to a PDF/dashboard step. This is a bundled **example** skill — small but real, and used to demonstrate the creator's validation, pipeline, and eval-rollout machinery end to end. ## Activation Activates on requests like "clean this CRM export", "weekly sales report", "regional totals from this CSV". Do **not** activate on general spreadsheet or analytics questions that don't involve a CRM export. ## Input A CSV with at least `region` and `amount` columns (extra columns are ignored). Duplicate rows (identical across all columns) are removed before totalling. ## Run One command produces the summary: ```bash python3 scripts/run_pipeline.py --input <export.csv> --output summary.json ``` Output JSON shape: ```json { "rows_in": 120, "rows_after_dedup": 118, "regions": {"West": 40210.5, "East": 38110.0}, "grand_total": 78320.5 } ``` ## Gotchas - **`rows_after_dedup` does not reconcile with `grand_total`.** Rows with a blank or missing `region` are skipped when totalling but still counted in `rows_after_dedup`, so a CSV with unassigned rows reports more rows than it actually summed. Do not present the two numbers as if one explains the other — if they must reconcile, filter blank regions before running. - **An unparseable `amount` silently becomes `0.0`,** ...

Details

Author
FrancyJGLisboa
Repository
FrancyJGLisboa/agent-skills-platform
Created
10 months ago
Last Updated
1 weeks ago
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

Data & Documents Listed

weekly-report

Produces one weekly operating readout for a store or product from exported performance, traffic, lifecycle, inventory, and support summaries, instead of scattered dashboards. Use when the user wants a single weekly view of what changed, what likely caused it, and what to do next. Boundary: this skill summarizes across whatever data the user brings this week. For a deep read on one specific area (margin, cohorts, checkout, search), use the matching skill directly and feed its output in here as one of the week's inputs.

1 Updated today
sidchaudhary
Data & Documents Listed

pipeline-reporter-free

Generate pipeline reports from CRM CSV exports. Use when the user says "analyze pipeline", "generate pipeline report", "forecast from CSV", "sales report", or asks for a sales pipeline summary, weighted forecast, stage forecast, rep performance, opportunity analysis, or CRM export review from deal/opportunity CSV data. This is the single-report, no-CRM-connection version; for 12-month forecasting, CRM API connections, PDF export, and scheduled reports, use pipeline-reporter-pro.

1 Updated 1 weeks ago
justhandledlabs
AI & Automation Listed

crm-export-auditor

Audit a CRM CSV export for the data faults that make every report built on it wrong: exact and near-duplicate accounts and contacts, close dates already in the past on open deals, deals with no activity in the last N days, blank required fields by stage, single-threaded deals carrying one contact, records with no owner or a departed one, stage and amount combinations that contradict each other, and currency, date and country formats that drift between rows. Returns a fix list ordered by how much each fault distorts a reported number, with the record IDs to correct and which fixes are safe to apply in bulk. Use when a pipeline number is disputed, when a migration or a dedupe is being planned, or when nobody has checked the export the forecast is built on.

1 Updated today
imtiazrayhan