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 Forwardable Blurb

ASecurity

Gives you Forwardable Blurb Points for three or four sentences about you that an introducer can forward unchanged, covering who you are, why this person, the small ask and an easy decline, then checks your draft. Use for "run gnet-forwardable-blurb", "send me something I can forward", "write a blurb for an introduction", "forwardable email", "what to send someone introducing me", "short intro paragraph about me", "blurb for a warm intro", part of the Claude Graduate Networking Guide Pack by P...

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

Works with

cli

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add polar-bear-org/claude-skills --skill gnet-forwardable-blurb --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Gnet Forwardable Blurb?

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

Security grade badge for Gnet Forwardable Blurb
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-gnet-forwardable-blurb/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-gnet-forwardable-blurb)

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-forwardable-blurb
description: Gives you Forwardable Blurb Points for three or four sentences about you that an introducer can forward unchanged, covering who you are, why this person, the small ask and an easy decline, then checks your draft. Use for "run gnet-forwardable-blurb", "send me something I can forward", "write a blurb for an introduction", "forwardable email", "what to send someone introducing me", "short intro paragraph about me", "blurb for a warm intro", part of the Claude Graduate Networking Guide Pack by Polar Bear.
---

# Forwardable Blurb

## When To Use
Someone agreed to introduce you and said "send me something I can forward". You want it back to them within a day or two, before the moment passes. This gives you points for three or four sentences the introducer can forward unchanged, then checks what you wrote.

## When Not To Use
If nobody has agreed to introduce you yet, run Introduction Request first. If the person already knows you well and will happily write their own introduction, skip the blurb and just thank them.

## Inputs
- Who the introducer is and who they will forward it to (name, role, employer)
- Your Elevator Pitch or Networking Brief
- Person Research Notes on the recipient, or what the introducer said about them
If you have none of this, I start from your course, what you want to ask and the recipient's role, and mark the output as a first draft.

## Approach
The forwardable email is a practitioner convention, described generically: a short, self-contained note the introducer can pass on without rewriting. It supports the double opt-in introduction from Fred Wilson's 2009 AVC post: the recipient reads the blurb and decides whether to say yes. The judgment is that it gets read cold, by a stranger, forwarded under someone else's name. The failure it prevents: a three-paragraph cover letter with a CV attached, which the introducer has to edit and the recipient never opens.

## Workflow
1. Ask up to three questions: who the recipient is and why them, the one thing you want to ask, and how you know the introducer.
2. Point one, who you are: one sentence from your pitch, written so it reads well forwarded (your name, course, what you are drawn to).
3. Point two, why this person: one sentence from the introducer's words or a sourced fact. No flattery, no guesses.
4. Point three, the small ask: advice or a 15-minute conversation on one topic. Never a job, a referral or a CV review.
5. Point four, the easy decline: one sentence making no a comfortable answer.
6. You write the blurb. Then I check it: three or four sentences, one ask, no job ask, every claim about you true and every claim about them sourced, no attachments by default. I show each issue; you fix it.

## Output Format
```markdown
# Forwardable Blurb Points
**Introducer:** [name] · **Recipient:** [name, role, employer]
## Points for four sentences
1. **Who I am:** [from your pitch]
2. **Why you:** [introducer's words or sourced fact]
3. **The small ask:** [advice or 15 minutes on one topic]
4. **Easy decline:** [no pressure line, in your words]
## Check on your draft
| Check | Result | Fix |
|---|---|---|
| Three or four sentences | [yes / no] | [what to cut] |
| One ask, no job ask | [yes / no] | [fix] |
| Claims about you true, claims about them sourced | [yes / no] | [fix] |
| Reads well forwarded, no attachment | [yes / no] | [fix] |
## Decision
You decide the final wording and send it to the introducer by [date]; the recipient decides whether to say yes.
```

## Done When
- Four points, each one sentence's worth
- Your draft passes all four checks, or you chose to keep a change
- The ask is advice or 15 minutes, never a job
- No CV or attachment unless the introducer asked for one

## Quality Bar
- Points, not a finished blurb; you write every word and I check it
- The check fixes length, ask and accuracy; it never rewrites your voice
- Every fact about the recipient has a source
- Third person friendly: it still makes sense when forwarded under another name
- You write the blurb from points; nothing about you is invented.

## Next
Run gnet-referral-ask (Referral Ask) for when a conversation leads to an open role.

## 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', ...

698461 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 →