Glink Project Post

---
name: glink-project-post
description: Drafts a Project Post about one moment from your Project Case Study (the problem you found, the mistake, the turn), in the first person, 120 to 250 words, with what you would do again and an optional carousel outline in text. Use for "run glink-project-post", "post about my dissertation", "turn my case study into a post", "share my group project on LinkedIn", "post about my placement project", "carousel outline for my project", "people will not open Featured", part of the Claude for LinkedIn Networking for Recent Graduates Pack by Polar Bear.
---

# Project Post

## When To Use
You have a Project Case Study and want people who will never open your Featured section to see how you work. This skill picks one moment from the case and answers: what is the single true story here, and how do I tell it in under 250 words?

## When Not To Use
Without a case or Project Interview Notes, run Project Interview first; a post written from memory turns into "we did a presentation and got a good mark". If the post is about something you learned from a talk or course, Learning Post fits better.

## Inputs
- Your Project Case Study, with its do-not-claim list and permission note
- Optional: the Project Interview Notes, for your exact words
- Optional: your Personal Voice Guide
If you have none of this, I ask the six interview moments in short form and mark the post as a first draft.

## Approach
One moment per post, with the AI tells removed (a Polar Bear practice method). A post that summarises the whole project says nothing; a post that starts in the week it nearly went wrong says one true thing and gets out. The mistake is usually the centre, because it is the part readers believe. The failure it prevents: "Thrilled to share my final year project!" followed by a list of tools, with a teammate's part quietly claimed as yours.

## Workflow
1. Ask at most three questions: which one moment (the problem you found, the mistake, or the turn), whether teammates may be named (or stay by role), and whether the permission note has cleared anything new.
2. First line from inside the moment, in your words from the notes ("Week six, the survey data was empty."). No announcement opener, no "excited to share".
3. Body in "I" sentences: what happened, what you did, who made the call, what you would do again. Group work stays the group's, by role. If the notes hold a mistake, it sits in the middle.
4. Results only as recorded in the case, with their source; marks only if you chose to share them. Anything on the do-not-claim list stays out.
5. Last line: a plain fact or a pointer to the case in Featured. Never "what do you think?", never engagement bait.
6. Fit to 120 to 250 words, apply your voice guide and strip the AI tells. Count the words.
7. Optional carousel outline: six to ten slides, one line each (the problem, one slide per beat, what you would do again, where the full case lives). Text only; you design it.

## Output Format
```markdown
# Project Post Draft
Case: [project] · Moment: [problem / mistake / turn] · Permission: [cleared / pending: item]
## Post
[First line inside the moment]
[What happened, what I did, who made the call]
[What I would do again]
[Plain last line or pointer to the case]
## Carousel outline (optional)
1. [Slide line]
2. [Slide line]
## Source check
| Line | Case or notes source | Do-not-claim clear |
|---|---|---|
| [line] | [moment / section] | [yes / removed] |
## Decision
You decide by [date] whether to post it, after Voice Check and once the permission note is clear; you post it yourself.
```

## Done When
- The post covers exactly one moment from the case.
- Every line traces to the case or the notes; nothing on the do-not-claim list appears.
- The post is 120 to 250 words with a plain last line.
- Teammates are by role or named with a recorded yes.

## Quality Bar
- No tool lists or skill roll calls; the moment does the showing.
- No "humbled", "journey" or lessons numbered one to five.
- No confidential data, client names or slides from a placement or module.
- A figure keeps its source and is never rounded up.
- One true moment from your notes, posted by you.

## Next
Run glink-voice-check (Voice Check) to check the draft against your voice guide and your evidence.

## 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).