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 Milestone Post

ASecurity

Drafts a short Milestone Post for a placement, an offer, graduation or a result, with the news first, what you are starting and why, thanks to named people only with their yes, no gratitude roll call and no inflated title. Use for "run glink-milestone-post", "announce my graduate job", "I got the offer", "post about graduating", "starting my placement post", "announce my degree result", "new job post that is not cringe", part of the Claude for LinkedIn Networking for Recent Graduates Pack by ...

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 glink-milestone-post --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Glink Milestone Post?

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

Security grade badge for Glink Milestone Post
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-glink-milestone-post/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-glink-milestone-post)

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-milestone-post
description: Drafts a short Milestone Post for a placement, an offer, graduation or a result, with the news first, what you are starting and why, thanks to named people only with their yes, no gratitude roll call and no inflated title. Use for "run glink-milestone-post", "announce my graduate job", "I got the offer", "post about graduating", "starting my placement post", "announce my degree result", "new job post that is not cringe", part of the Claude for LinkedIn Networking for Recent Graduates Pack by Polar Bear.
---

# Milestone Post

## When To Use
You got the offer, the placement or the degree, and the usual announcement post makes you wince: "Humbled and thrilled to announce", then a list of everyone you have ever met. This skill answers: how do I share the news plainly, say why it matters to me, and thank people without a roll call?

## When Not To Use
If you want to say something about what you learned or built, Learning Post or Project Post carry more; this is the short announcement. Changing your Open to Work settings after an offer belongs to Open to Work Settings, not to a post.

## Inputs
- The news: the exact title and employer as on the offer, the placement, or the degree and result you choose to share
- Why it matters to you, roughly, and the inventory row or moment behind it
- Anyone you want to thank, and whether they said yes to being named
- Optional: your Personal Voice Guide and the employer's social media policy
If you have none of this, I start from the news in one line and mark the post as a first draft.

## Approach
Bottom line up front and active voice, from the US Army writing standard AR 25-50 (paragraph 1-38), kept in your own voice: the first sentence is the news. One true thing per post. The failure it prevents: a post that calls a summer internship a "role as Analyst" and thanks a manager who never agreed to be named, three days before the employer asked new starters not to post yet.

## Workflow
1. Ask at most three questions: the news exactly as written on the offer or result, why it matters to you in one rough sentence, and who you want to thank (with or without their yes).
2. First sentence is the news: what you are starting, finishing or got, title and employer exactly as on the offer. No "humbled", "thrilled to announce" or "journey".
3. Then one or two sentences on why it matters to you, from a real row or moment (the module that pointed you there, the part-time job that taught you the thing you will use).
4. Thanks: a few named people at most, each with a recorded yes; otherwise thank by role ("my dissertation supervisor") or not at all. No list of everyone, and nothing about other candidates.
5. Confidentiality: no start date, pay, team details or office location unless the employer allows it; check the employer's social media policy and any offer conditions first. Anything contractual: check with a qualified adviser.
6. Keep it short: about 50 to 120 words is the default, and you can change it. Apply your voice guide, strip the AI tells and count the words.

## Output Format
```markdown
# Milestone Post Draft
News: [offer / placement / graduation / result] · Title and employer as on the offer: [exact wording]
## Post
[First sentence: the news]
[Why it matters to me, from a real row]
[Thanks: named with a yes, by role, or none]
## Checks
| Check | Status |
|---|---|
| Title matches the offer | [yes / fix] |
| Named people said yes | [names / none named] |
| Employer policy checked | [yes / question for: person] |
| Word count | [count] |
## Decision
You decide by [date] whether and when to post, once the employer policy check is done; you post it yourself.
```

## Done When
- The first sentence is the news, with the title exactly as on the offer.
- Why it matters comes from a real row or moment, not a slogan.
- Every named person has a recorded yes; nobody else is listed.
- Nothing confidential appears, and the employer policy check has a status.

## Quality Bar
- No inflated title, no "incoming" grade you do not hold, no result you have not received.
- No mention of rejections, other candidates or how hard it was to get in compared with others.
- No gratitude roll call; three names is already a lot.
- Short beats complete; the post is the news, not a CV.
- Your real title and news, posted by you, with nobody named without their yes.

## Next
Run glink-voice-check (Voice Check) to make sure the post still sounds like you before it goes up.

## 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 →