Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Weekly Crm Report

ASecurity

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.

2,399 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythonrustgobashapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add FrancyJGLisboa/agent-skills-platform --skill weekly-crm-report --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Weekly Crm Report?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Weekly Crm Report
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/francyjglisboa-weekly-crm-report-agent-skills-platform/badge)](https://www.skillsdirectory.com/skills/francyjglisboa-weekly-crm-report-agent-skills-platform)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: weekly-crm-report
description: 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.
license: MIT
metadata:
  author: agent-skills-platform
  version: 1.0.0
  created: 2026-06-27
  last_reviewed: 2026-07-20
  review_interval_days: 180
---

# 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`,** it does not raise. A column
  of `N/A` or `—` produces a region total of `0.0` that looks like a real zero.
  Check the input for non-numeric amounts before trusting a suspiciously low total.
- **Dedup compares every column, not just `region` and `amount`.** Two rows with
  identical sales data but a differing timestamp or record-ID column are both kept.
  The "extra columns are ignored" note above applies to totalling, not to dedup.

## Anti-goals

- Not a general BI tool; it totals one numeric column per region.
- Does not fetch from a live CRM API; it operates on an exported CSV.

Attribution

FrancyJGLisboaFrancyJGLisboa
View sourceMore from FrancyJGLisboa →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →