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

Update Lead

ASecurity

Update status, contacts, notes in CRM

92 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentspythongo

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add aAAaqwq/AGI-Super-Team --skill update-lead --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Update Lead?

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

Security grade badge for Update Lead
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aaaaqwq-update-lead-agi-super-team/badge)](https://www.skillsdirectory.com/skills/aaaaqwq-update-lead-agi-super-team)

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

Download Zip
Files
SKILL.md
---
name: update-lead
description: Update status, contacts, notes in CRM
---
# CRM Update Lead

> Updating status, priority, and other fields of an existing lead

## When to use

- "update status to responded"
- "change priority to high"
- "add a note"
- "change source to google"
- After receiving a response

## Paths

| What | Path |
|------|------|
| Leads | `$CRM_PATH/relationships/leads.csv` |
| People | `$CRM_PATH/contacts/people.csv` |

## How to update

```python
import pandas as pd
from datetime import date

# Load
df = pd.read_csv('$CRM_PATH/contacts/people.csv')

# Find by linkedin_url or email
mask = df['email'] == 'example@email.com'
# or
mask = df['linkedin_url'] == 'https://linkedin.com/in/example'

# Update fields
df.loc[mask, 'status'] = 'responded'
df.loc[mask, 'priority'] = 'high'
df.loc[mask, 'notes'] = 'Responded positively 2025-02-03'
df.loc[mask, 'last_updated'] = str(date.today())  # REQUIRED!

# Save
df.to_csv('$CRM_PATH/contacts/people.csv', index=False)
```

## How to update leads.csv

```python
import pandas as pd
from datetime import date

leads = pd.read_csv('$CRM_PATH/relationships/leads.csv')

mask = leads['lead_id'] == 'lead-example-001'

leads.loc[mask, 'stage'] = 'qualified'
leads.loc[mask, 'next_action'] = 'Schedule discovery call'
leads.loc[mask, 'next_action_date'] = '2026-03-10'
leads.loc[mask, 'last_updated'] = str(date.today())

leads.to_csv('$CRM_PATH/relationships/leads.csv', index=False)
```

## Batch update

```python
# Update all who responded "yes"
responded_emails = ['email1@test.com', 'email2@test.com']

for email in responded_emails:
    mask = df['email'] == email
    df.loc[mask, 'status'] = 'responded'
    df.loc[mask, 'priority'] = 'high'
    df.loc[mask, 'last_updated'] = str(date.today())

df.to_csv(path, index=False)
```

## Stages (leads.csv)

```
new -> qualified -> proposal -> negotiation -> won/lost
```

## Statuses (people.csv)

```
new -> researched -> contacted -> responded -> meeting -> won/lost
```

Do not skip stages without a reason.

## Source of Truth (since 2026-03-02)

**leads.csv `next_action` is the canonical source for sales follow-ups.**

- Do NOT create pm_tasks for sales follow-ups (invoices, payment checks, deal closing).
- Instead, update the lead's `next_action` and `next_action_date` in leads.csv.
- pm_tasks_master.csv is for dev/project tasks only.

## Source fields

Leads have three source fields:
- **source** — enum: google, website, facebook, linkedin, email, telegram, referral, direct, event, calendly, research
- **source_direction** — inbound or outbound
- **source_detail** — _(optional)_ campaign name, referrer, post URL, etc.

## Rules

1. **ALWAYS** update `last_updated`
2. If you change `status` -- add an explanation in `notes`
3. If there is a response -- record the text in `response` or `notes`
4. Verify the record exists before updating
5. For sales actions, update `next_action` + `next_action_date` in leads.csv (not pm_tasks)

## Related skills

- `query-leads` -- find a lead before updating
- `log-activity` -- log activity
- `telegram-check` -- check for responses

Attribution

aAAaqwqaAAaqwq
View sourceMore from aAAaqwq →
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".

1066601 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.

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.

651 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 →