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

Glink Featured Section

ASecurity

Plans your LinkedIn Featured section with three to five items to pin (case, project file, certificate, post), a one-line description for each, a permission and confidentiality check per item and the order a reader sees them in. Use for "run glink-featured-section", "what should I put in Featured", "my Featured section is empty", "can I pin my group assignment", "is it ok to share my placement work", "order my Featured items", "plan my Featured section", part of the Claude for LinkedIn Network...

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 glink-featured-section --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Glink Featured Section?

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

Security grade badge for Glink Featured Section
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-glink-featured-section/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-glink-featured-section)

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: glink-featured-section
description: Plans your LinkedIn Featured section with three to five items to pin (case, project file, certificate, post), a one-line description for each, a permission and confidentiality check per item and the order a reader sees them in. Use for "run glink-featured-section", "what should I put in Featured", "my Featured section is empty", "can I pin my group assignment", "is it ok to share my placement work", "order my Featured items", "plan my Featured section", part of the Claude for LinkedIn Networking for Recent Graduates Pack by Polar Bear.
---

# Featured Section Plan

## When To Use
Your Featured section is empty, or it holds a group assignment you are not sure you may share. This skill picks three to five items that show real work, checks each one is yours to share, and answers: what should a recruiter see first?

## When Not To Use
If you have nothing yet worth pinning, run Project Case Study first; an empty Featured is better than a pinned certificate with nothing behind it. If the question is only whether one item breaks your employer's contract, that is for the employer or a qualified adviser, not a plan.

## Inputs
- Your candidate items: the Project Case Study, project files, certificates, your own posts or articles
- Your Target Role Brief, so the order follows the roles you want
- For each item: who made it, whether it was assessed, whether it holds employer material or anyone else's data
If you have none of this, I start from a list of what you have and mark the plan as a first draft.

## Approach
LinkedIn Help describes Featured as the place to showcase samples of your work (posts, articles, links and media), and LinkedIn's student page frames it as something tangible a recruiter can see. UK careers-service advice adds the brake: don't upload confidential documents without permission. So permission comes before order. The failure it prevents: a pinned group report with a teammate's analysis and a placement client's figures in it, live on your profile under your name.

## Workflow
1. Ask at most three questions: which items you have, which target roles the plan serves, and whether you are on a placement or in a job with a social media policy.
2. List every candidate item with what it is and where it came from (case, project, certificate, own post).
3. Run the permission check per item, four questions: own work or group work (group work needs your teammates' yes); assessed (within your university's module rules); employer material (confidentiality and social media policy); other people's personal data (remove it or drop the item). Any unknown means "not pinned yet", with the question to ask written down.
4. Write one line per cleared item: what it is and what it shows, using only words your evidence backs. "Dissertation summary: how I tested [question] with [method]", not "my passion for research".
5. Choose three to five and set the order: the strongest proof for your target roles first, because a reader may stop at the first item. LinkedIn needs at least two items before you can reorder them.
6. Remind yourself before any change: an item removed from Featured cannot be restored, so keep the source file. You add, order and remove items yourself on LinkedIn.

## Output Format
```markdown
# Featured Section Plan
For: [target roles] · Checked on: [date]
## Permission check
| Item | Own or group | Assessed | Employer material | Others' data | Status |
|---|---|---|---|---|---|
| [item] | [own / group: teammates' yes?] | [module rules?] | [policy?] | [removed / none] | [cleared / not pinned yet] |
## Items to pin, in reading order
| Order | Item | One-line description | Evidence behind it |
|---|---|---|---|
| 1 | [strongest proof] | [what it is and what it shows] | [interview note / inventory row] |
| 2 | [item] | [line] | [source] |
## Questions still open
- [Question for tutor, teammate or manager, and by when]
## Decision
You decide by [date] which cleared items to pin; unknowns wait until answered. Legal or contractual points: check with a qualified adviser.
```

## Done When
- Every candidate item has a status; nothing unknown is in the reading order.
- Three to five items are pinned, or the plan says why fewer.
- Each pinned item has a one-line description traced to evidence.
- The source file for each item is kept outside LinkedIn.

## Quality Bar
- Permission before order; a strong item with an open question waits.
- Group work only with teammates' yes, and described as the group's.
- No document with anyone else's personal data, and no employer material without clearance.
- No description claims more than the item shows.
- Nothing pinned that is not yours to share.

## Next
Run glink-recommendation-request (LinkedIn Recommendation Request) to ask someone who saw the work to say so in their own words.

## 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', ...

698621 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 →