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 Activity Log

ASecurity

Sets up a LinkedIn Activity Log with one row per action (post, comment, connection, reply), what each led to and notes for the monthly refresh, plus weekly counts of your own actions. Use for "run glink-activity-log", "LinkedIn activity log", "track my LinkedIn activity", "who did I message on LinkedIn", "LinkedIn tracker spreadsheet", "keep track of LinkedIn connections", "which posts worked", "log my comments", part of the Claude for LinkedIn Networking for Recent Graduates Pack by Polar Bear.

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

Works with

cliapi

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add polar-bear-org/claude-skills --skill glink-activity-log --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Glink Activity Log?

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

Security grade badge for Glink Activity Log
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-glink-activity-log/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-glink-activity-log)

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-activity-log
description: Sets up a LinkedIn Activity Log with one row per action (post, comment, connection, reply), what each led to and notes for the monthly refresh, plus weekly counts of your own actions. Use for "run glink-activity-log", "LinkedIn activity log", "track my LinkedIn activity", "who did I message on LinkedIn", "LinkedIn tracker spreadsheet", "keep track of LinkedIn connections", "which posts worked", "log my comments", part of the Claude for LinkedIn Networking for Recent Graduates Pack by Polar Bear.
---

# LinkedIn Activity Log

## When To Use
You cannot remember who you spoke to or which posts started conversations. Use this alongside your weekly 20 minutes so follow-ups do not slip and the monthly refresh has something real to look back on.

## When Not To Use
If you have only done a handful of things on LinkedIn so far, a note on your phone is fine until the Weekly LinkedIn Routine is running. If you want to decide what to change, that is Monthly Profile Refresh; the log only records.

## Inputs
- Your rough notes from this week's sessions (who, what, when), pasted as they are
- Any replies or messages you want to note, summarised in your words
- An existing log, if you already keep one
If you have none of this, I start from a blank log with this week's date and mark the output as a first draft.

## Approach
A simple contact and activity log, a practitioner convention, entered by you by hand (no scraping, no exports, no automation, in line with LinkedIn's User Agreement §8.2; R1). The judgment is in what to leave out: no column that rates a person's value, warmth or usefulness, and as little personal data as the job needs. The failure it prevents: a promising reply from three weeks ago that you never answered because it sat in your inbox under twenty notifications.

## Workflow
1. Ask three questions: where you will keep the log (a chat table, or a Google Sheet created from the desktop app's output picker with Google Drive connected), how long you want to keep rows, and whether you already track anything.
2. Set the columns: date, action type (post, comment, connection, reply), where (the post, or a person by name and public role), what you said in a few words, what it led to (reply, conversation, nothing yet), follow-up date, notes for the refresh.
3. Tidy your pasted notes into rows, one action per row, keeping your words; where something is unclear, mark it `[check]` rather than guess.
4. Add a follow-up date only where a reply or conversation needs one; "nothing yet" rows get no chasing date.
5. Count the week by action type and by outcome. Counts describe your actions only, never the people.
6. Pull out up to three notes for the Monthly Profile Refresh (a kind of post or comment that led to conversations, a new piece of evidence, a profile line someone asked about).
7. Remind you to delete rows you no longer need; for data protection questions about keeping contact details, check with a qualified adviser.

## Output Format
```markdown
# LinkedIn Activity Log
## Week of [date]
| Date | Action | Where | What I said | Led to | Follow-up | Notes for refresh |
|---|---|---|---|---|---|---|
| [date] | [post / comment / connection / reply] | [post title or name, public role] | [a few words] | [reply / conversation / nothing yet] | [date or none] | [note] |
## This week in numbers
| Action type | Count | Led to a reply | Led to a conversation |
|---|---|---|---|
| [type] | [n] | [n] | [n] |
## Follow-ups due
1. [name, public role]: [what you will say], by [date]
## For the monthly refresh
- [up to three notes]
## Decision
You decide which follow-ups to send by hand this week and which rows to delete, by [date].
```

## Done When
- Every row is one action with a date, a type and an outcome
- No column or note rates, ranks or scores a person
- Each person appears by name and public role only, with nothing else about them
- Counts cover your actions, by type and outcome, and nothing more

## Quality Bar
- Your words stay your words; unclear notes are marked, never filled in
- "Nothing yet" is a normal outcome, not a failure to chase
- No message is drafted to several people at once from the log
- Minimal personal data; old rows are deleted, not archived forever
- It counts your own actions, entered by you; it never scores the people you contacted.

## Next
Run glink-monthly-refresh (Monthly Profile Refresh) to turn a month of rows into profile updates and one change to try.

## 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 →