Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Gnet Intro Request

ASecurity

Gives you Introduction Request Points for asking one contact to introduce you to one named person, covering why that person, the small ask and an easy way to say no, with a double opt-in step so the other side agrees first. Use for "run gnet-intro-request", "how do I ask for an introduction", "my contact mentioned someone I want to meet", "ask a lecturer to introduce me", "can you introduce me message", "warm introduction request", "ask a friend to connect me with someone", part of the Claude...

2 stars
0 votes
0 copies
0 views
Added 10/5/2026
ai-agentsgo

Works with

cli

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add polar-bear-org/claude-skills --skill gnet-intro-request --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Gnet Intro Request?

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

Security grade badge for Gnet Intro Request
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-gnet-intro-request/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-gnet-intro-request)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: gnet-intro-request
description: Gives you Introduction Request Points for asking one contact to introduce you to one named person, covering why that person, the small ask and an easy way to say no, with a double opt-in step so the other side agrees first. Use for "run gnet-intro-request", "how do I ask for an introduction", "my contact mentioned someone I want to meet", "ask a lecturer to introduce me", "can you introduce me message", "warm introduction request", "ask a friend to connect me with someone", part of the Claude Graduate Networking Guide Pack by Polar Bear.
---

# Introduction Request

## When To Use
A contact mentioned someone you would love to talk to: "you should speak to my old colleague", or a name that came up in a coffee chat. This gives you points for asking that contact for one introduction, in a way that is easy for them to say yes or no to, and fair to the person being introduced.

## When Not To Use
If someone offered to help but you have no name in mind, use Helper Brief instead. If the contact has already agreed and asked for "something to forward", go straight to Forwardable Blurb. If you have never spoken to the contact yourself, start with Message Points.

## Inputs
- Who the contact is and how you know them
- The named person, their role and employer, and how their name came up
- Person Research Notes on that person, if you have them, and your Networking Brief
If you have none of this, I start from the contact, the name and why you want to talk to them, and mark the output as a first draft.

## Approach
The method is the double opt-in introduction, from Fred Wilson's 2009 post on his AVC blog: before introducing two people who do not know each other, the introducer asks each of them first. It protects the contact's relationship and the other person's time. The failure it prevents: a contact copying you and a busy stranger into an email out of the blue, the stranger feeling cornered, and your contact quietly deciding not to do it again. A close friend may prefer an informal introduction; the contact decides.

## Workflow
1. Ask up to three questions: how you know the contact, how the named person came up, and what one thing you would ask them.
2. Check the request: one contact, one named person. If you have several names, pick one now and keep the rest for later.
3. Draft the point on why this person, using only what the contact said or a sourced fact from your research. No guessing about the person's interests.
4. Draft the point on the small ask: advice or a 15-minute conversation, never a job or a referral.
5. Draft the point on the double opt-in and the easy no: ask the contact to check with the person first, offer a forwardable blurb, and make "not right now" a comfortable answer.
6. Check the points: 2 or 3 points, each 3 or 4 sentences. Nothing asks the contact for the person's email or phone number. You write the message and send it.

## Output Format
```markdown
# Introduction Request Points
**To:** [contact's first name] · **About:** [named person, role, employer] · **How the name came up:** [source]
## Points to make
1. **Why this person:** [3 or 4 sentences from the contact's words or sourced research]
2. **The small ask:** [3 or 4 sentences: advice or 15 minutes, on what topic]
3. **Their call, and an easy no:** [3 or 4 sentences: please check with them first; happy to send a short blurb; no worries if not]
## Facts used
| Fact | Source |
|---|---|
| [fact about the named person] | [contact said / public source and date] |
## Decision
You decide whether to send this, and when, by [date]; the contact decides whether to ask the named person.
```

## Done When
- One contact and one named person, nothing more
- Every fact about the named person has a source
- The ask is small and the easy no is explicit
- The double opt-in step is in the points

## Quality Bar
- Points, not a finished message; if asked to write the message, offer Grammar Check on your draft instead
- Never ask the contact for the other person's contact details directly
- No job or referral in an introduction request
- Nothing about the named person is guessed or taken from private sources
- You ask one person for one introduction, and the other side agrees first.

## Next
Run gnet-forwardable-blurb (Forwardable Blurb) to give the introducer something to forward.

## About the makers

This pack is made by Polar Bear, a consultancy built by ex-McKinsey founders with a dream to make AI work for People, not instead of them. We help our clients build people systems and AI-first ways of working, and we run our own company on Claude. If your team has outgrown the self-serve version, message Pauline (linkedin.com/in/paulinebertry).

Attribution

polar-bear-orgpolar-bear-org
View sourceSee grades on GitHubMore from polar-bear-org →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →