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
  • Authors
  • 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.

ProTermsPrivacyRefunds
Back to skills

Build Personal Crm System

ASecurity

Guide users building a personal CRM from simple files to structured database.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgosqldebugginggitdatabase

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill build-personal-crm-system --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Build Personal Crm System?

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

Security grade badge for Build Personal Crm System
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-build-personal-crm-system/badge)](https://www.skillsdirectory.com/skills/rondoflow-build-personal-crm-system)

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

Download with Pro
Files
SKILL.md
---
name: build-personal-crm-system
description: "Guide users building a personal CRM from simple files to structured database."
category: "Data & Analytics"
author: community
version: "1.0.0"
icon: chart-bar
---

## First Interaction
- Ask what they're tracking: clients, leads, investors, job contacts, networking — context shapes schema
- Ask their technical comfort: spreadsheets, JSON, databases — determines starting format
- Create `~/crm/` folder as the single source of truth

## Start With Files, Not Apps
- JSON or CSV for first version — validate data model before adding complexity
- Single file `contacts.json` initially — resist creating multiple files until needed
- Don't suggest web app until they've used files for at least a week
- Don't suggest database until files feel slow or limiting

## Minimal Contact Schema
- id, name, email, company, phone, notes, tags, created, updated — nothing more initially
- tags array over rigid categories — flexible, no schema changes needed
- notes field is often the most valuable — encourage freeform context
- Generate UUID for id, not auto-increment — survives merges and imports

## When To Add Interactions File
- User asks "when did I last talk to X" — signal they need history
- Separate file linked by contact_id — not nested in contact object
- type field (note/email/call/meeting) enables filtering later
- Always include date — timeline view is essential

## When To Add Companies File
- Multiple contacts at same company — signal to separate
- Many-to-many: one person can work at multiple companies over time
- company_id in contacts, not company name duplication

## When To Add Deals/Opportunities
- User mentions "pipeline", "stage", "close date", "deal value"
- Link to contact_id and optionally company_id
- Stages as simple string field initially — don't over-engineer state machine

## SQLite Migration Triggers
- File operations feel slow (>100 contacts typically)
- User wants to query/filter in complex ways
- Multiple users need access (SQLite handles concurrent reads)
- Offer to write migration script — don't force manual re-entry

## Progressive Timeline
- Week 1: contacts file only, prove they'll use it
- Week 2: add interactions when they want history
- Week 3: add tags, search helper script
- Month 2: companies file if needed
- Month 3: deals file if tracking opportunities
- Only then: consider web UI or more complex tooling

## What NOT To Suggest Early
- Web application — massive scope increase, validate data model first
- Email sync/integration — suggest BCC/forward workflow, much simpler
- Calendar integration — manual logging is fine initially
- Authentication — single-user local CRM doesn't need it
- Mobile app — sync complexity not worth it early

## Helper Scripts Worth Offering
- Quick add from command line — reduces friction
- Search across all files — grep/jq one-liner
- Backup to timestamped zip — essential before migrations
- Export to CSV — for users who want spreadsheet view

## Data Integrity Habits
- Backup before any bulk edit or migration
- Check for duplicate emails before adding contact
- Validate email format on entry
- Keep created/updated timestamps — debugging lifesaver

## Sync When Asked
- Cloud folder (Dropbox/iCloud/Drive) for multi-device — simplest
- Git repo for version history — good for technical users
- Don't suggest complex sync solutions until files prove insufficient

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
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 that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

693621 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 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 →