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 Helper Brief

ASecurity

Builds a one-page Helper Brief a friend, lecturer or mentor can read to open their own network, covering what you want, the help you need and who would fit, with the helper choosing who to ask. Use for "run gnet-helper-brief", "my lecturer said let me know how I can help", "what do I send a family friend who offered to help", "write a one-pager for my mentor", "brief for someone helping me network", "how do I ask people to help me find contacts", "make it easy for someone to help me", part of...

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-helper-brief --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Gnet Helper Brief?

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

Security grade badge for Gnet Helper Brief
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-gnet-helper-brief/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-gnet-helper-brief)

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-helper-brief
description: Builds a one-page Helper Brief a friend, lecturer or mentor can read to open their own network, covering what you want, the help you need and who would fit, with the helper choosing who to ask. Use for "run gnet-helper-brief", "my lecturer said let me know how I can help", "what do I send a family friend who offered to help", "write a one-pager for my mentor", "brief for someone helping me network", "how do I ask people to help me find contacts", "make it easy for someone to help me", part of the Claude Graduate Networking Guide Pack by Polar Bear.
---

# Helper Brief

## When To Use
A lecturer, placement manager or family friend says "let me know how I can help", and you reply "thanks, I will", then never do. This gives them one short page, so they can think of the right people in their own network and choose who to ask.

## When Not To Use
If you already know the exact person you want to meet, use Introduction Request: it asks for one named introduction. If you have no brief yet, run Networking Brief first, or the page will say "anything in business, really".

## Inputs
- Your Networking Brief (target roles, the help you need, what you can offer back)
- Who the helper is and how you know them, in a line
- Your Elevator Pitch, if you have one
If you have none of this, I start from the roles you are curious about and the kind of help you want, and mark the output as a first draft.

## Approach
The method is a principle, described generically: open your brief to a few people who want to help, and let whoever knows a person write to them. The helper owns their network, so they choose who to ask, ask that person first and pass on contact details only with consent. The failure it prevents: a helper offering their whole contact list, you collecting names you were never introduced to, and a stranger receiving an unexpected message that mentions them. Data protection questions about other people's details (UK Information Commissioner's Office guidance on personal and household activity) are flagged as questions only.

## Workflow
1. Ask up to three questions: who the helper is to you, what help you most want from them (advice, a 15-minute conversation, an introduction), and anything you want left out.
2. Write who you are in two lines from the brief or pitch: course or degree, what you are drawn to and why, in plain words.
3. Write what you want and the help you need. Keep the ask small: advice or a 15-minute conversation, never a job.
4. Describe who would fit as types of roles and employers only. Never name people from your list, map or log; the helper's page is about their network, not yours.
5. Set out what the helper does (chooses who to ask, writes to them, checks the other person is happy first) and what you will do (reply fast, report back with a Close the Loop Note).
6. Read the page as a busy helper would: anything they would skim past gets cut. If you want a shareable page, build it in Claude Docs (beta); a plain document works too. Flag any data question for a qualified adviser.

## Output Format
```markdown
# Helper Brief
**For:** [helper's first name] · **From:** [your name] · **Date:** [date]
## Who I am
[Two lines: degree or course, what you are drawn to and why]
## What I am looking for
[Target roles, in plain words] · [Timing, if any]
## The help that would mean most
- [Advice on X / a 15-minute conversation with someone in Y / an introduction]
## Who might fit
| Type of role | Type of employer or team | What I would ask them |
|---|---|---|
| [role] | [employer type, never a named person] | [one small question] |
## How this works
You choose who, if anyone, to ask. You write to them and check they are happy first. I only get contact details if they agree.
## What I will do
Reply within [timeframe you set], keep it short, and tell you what happened.
## Decision
You decide whether to send this, and to whom, by [date]; the helper decides who, if anyone, to ask.
```

## Done When
- It fits on one page and a busy helper can read it in one go
- No names, emails or phone numbers from your own list appear anywhere
- The ask is advice or a 15-minute conversation, never a job
- The helper's choices and the consent step are written out

## Quality Bar
- Every line comes from your brief, pitch or answers; nothing about you is invented
- "Who might fit" names role and employer types, never people
- One page, no attachments, no CV unless the helper asks
- Data questions end with "check with a qualified adviser"; keep contact details out of Claude memory
- The helper chooses who to ask and writes to them; no contact details pass to you without consent.

## Next
Run gnet-forwardable-blurb (Forwardable Blurb) so the helper has something short 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 →