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 Project Interview

ASecurity

Interviews you for about 20 minutes on one project, dissertation or placement task in six moments and writes Project Interview Notes in your own words, with a memory or record mark on every fact and a do-not-claim list. Use for "run glink-project-interview", "interview me about my project", "help me write up my dissertation", "turn my group project into something", "what can I say about my placement project", "we just got a good mark, now what", "get the real story out of my project", 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 glink-project-interview --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Glink Project Interview?

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

Security grade badge for Glink Project Interview
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-glink-project-interview/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-glink-project-interview)

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-project-interview
description: Interviews you for about 20 minutes on one project, dissertation or placement task in six moments and writes Project Interview Notes in your own words, with a memory or record mark on every fact and a do-not-claim list. Use for "run glink-project-interview", "interview me about my project", "help me write up my dissertation", "turn my group project into something", "what can I say about my placement project", "we just got a good mark, now what", "get the real story out of my project", part of the Claude for LinkedIn Networking for Recent Graduates Pack by Polar Bear.
---

# Project Interview

## When To Use
You did a real project, a dissertation or a placement task, and every time you try to describe it you get stuck at "we did a presentation and got a good mark". This interview gets underneath that line, one question at a time, and answers one question: what actually happened, and which part of it was yours?

## When Not To Use
If you want a quick list of everything you have done across your degree, jobs and societies, run Experience Inventory first; this skill goes deep on one project only. If the project is still running or not yet marked, wait: moments 5 and 6 need an ending.

## Inputs
- The project in one line, and who else worked on it (by role: teammates, tutor, placement manager)
- Any rules on sharing it: module rules, the employer's confidentiality or social media policy
- Optional: the brief, your feedback sheet, emails, slides, your Experience Inventory row for it
If you have none of this, I start from your one-line description and your memory, and mark every fact "memory only".

## Approach
The six-moment interview is a Polar Bear practice method, adapted here from client projects to a module, a tutor, a group or a placement manager, with the STAR habit of "I, not we" from the National Careers Service guide to the STAR method. The order gets the real story out before the polished one, and I write down what you say without improving it. The failure it prevents: a write-up that says "we delivered a successful report" and could be anyone's, or one where a teammate's analysis quietly becomes yours. Plain chat works; a Project (beta, select plans) keeps the notes beside your Experience Inventory.

## Workflow
1. Two questions before the story: the project in one line, and who else worked on it plus any rules on sharing it (module rules, employer confidentiality). I record exactly what you say about permission, not what you hope.
2. Moment 1, what was actually wrong or hard: not the brief, the thing behind it. Follow-up: how did you find out? Then moment 2, the moment you understood it. Follow-up: what did you notice that you had missed before?
3. Moment 3, the turn: the decision or piece of work that changed direction. Follow-up: who made the call? If it was the group or the tutor, the notes say so.
4. Moment 4, the mistake or dead end. Follow-up: what did you do next? People skip this one, and it is the one a reader believes. I wait for a real answer before moving on.
5. Moment 5, what you delivered and the first time it was used or assessed; moment 6, what changed and how you know. One follow-up each. I ask about concrete moments ("what was on the whiteboard", "what did the first email after say"), never "what was the outcome".
6. Mark every fact "record" (with the source: feedback sheet, email, mark) or "memory only". A number without a record stays words. Your words stay verbatim, including the clumsy ones.
7. Build the do-not-claim list with you: other people's parts, results you hoped for and did not see, anything confidential or not yet marked. Stop at about 20 minutes; past that people start performing for the record.

## Output Format
```markdown
# Project Interview Notes
Project: [one line] · Dates: [from to] · With: [roles]
Sharing rules: [module rules, employer policy, as you stated them]
## The six moments
| Moment | Your words | Record or memory | Source |
|---|---|---|---|
| 1 What was wrong | [verbatim] | [record / memory only] | [feedback sheet, email] |
| 2 When you understood it | [verbatim] | [ ] | [ ] |
| 3 The turn (who decided) | [verbatim] | [ ] | [ ] |
| 4 The mistake and what next | [verbatim] | [ ] | [ ] |
| 5 What you delivered, first use | [verbatim] | [ ] | [ ] |
| 6 What changed, how you know | [verbatim] | [ ] | [ ] |
## Your part
[What was yours, in "I" sentences; what was the group's, by role]
## Do-not-claim list
- [Other people's parts] · [Hoped-for results] · [Confidential or unmarked]
## Decision
You decide by [date] whether these notes are ready for a case study, or which moment needs a record first.
```

## Done When
- All six moments have an answer in your words, with moment 4 not left blank or softened.
- Every fact is marked record or memory only; no number sits without a source.
- The do-not-claim list has at least one entry or says "checked, none".
- Your part and the group's part are separated, with teammates by role.

## Quality Bar
- One question at a time, one follow-up each; never a form to fill.
- Nothing is polished or summarised at this stage; the notes are a record.
- No judgement of anyone's contribution: "we split the work differently", never "they did nothing".
- Quotes from a tutor or manager only if you are sure of the wording and the person knows; otherwise a paraphrase without quotation marks.
- Your words are recorded as said; the do-not-claim list travels with every draft.

## Next
Run glink-project-case (Project Case Study) to turn these notes into one page a recruiter can open.

## 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 →