# Pmjob Story Bank

> Builds your Interview Story Bank, eight to twelve stories from your evidence rows in a two minute and a thirty second version, tagged by competency, with likely follow-up questions and the facts you must not stretch. Use for "run pmjob-story-bank", "build my interview stories", "STAR stories for a product interview", "I always tell the same launch story", "stories for behavioural questions", "story about a failure", "story about a disagreement", "shorten my interview story", part of the Claude Guide for Product Interviews Pack by 90n.

- Skill: `polar-bear-org/pmjob-story-bank` (Agent Skill)
- Install (CLI): `npx get-skill add polar-bear-org/pmjob-story-bank`
- Raw SKILL.md: https://api.skillmd.com/api/skills/polar-bear-org/pmjob-story-bank/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: polar-bear-org (https://skillmd.com/u/polar-bear-org)
- Updated: 2026-11-14
- Page: https://skillmd.com/skills/polar-bear-org/pmjob-story-bank

---


# Interview Story Bank

## When To Use
Every behavioural question gets the same launch story, told a little differently each time. You have years of work and one story on repeat. Run this once per search to answer: which eight to twelve pieces of my work can I tell, in two lengths, and what will I be asked next?

## When Not To Use
If you have no evidence rows yet, run Career Evidence Inventory first. To match stories to the competencies of one booked round, run Behavioural Interview Answers. For a long timed talk on two or three pieces of work, run Portfolio and Project Walkthrough.

## Inputs
- Your Career Evidence Inventory, with the rows and the do-not-claim list
- The roles you are aiming at, or the Interview Loop Map if rounds are booked
- The stories you already tell, as you tell them
If you have none of this, I start from three pieces of work you describe in the chat, and mark the output as a first draft.

## Approach
STAR as set out in The STAR method guide of the National Careers Service: Situation, Task, Action, Result, where the result includes what you gained. That guide also says to expect follow-up questions and to speak naturally, so the bank holds speaking notes, not a script to memorise. The balance rule is a practice rule: Action is the longest part. The failure this prevents is two minutes of situation and ten seconds of action, with "we" all the way through.

## Workflow
1. Ask up to three questions: which roles or rounds the bank is for, which stories you already tell most, and which rows are off limits.
2. Pick eight to twelve rows that differ in kind, not only the wins: a launch, a failure or a mistake, a disagreement, a decision with thin data, something stopped or cut, influence without authority, a hire or a person developed, a hard trade-off, a recovery.
3. Write each story in four parts: Situation (the context or challenge), Task (what you were responsible for), Action (the steps you personally took), Result (the outcome, plus what you learned). If Situation runs longer than Action, cut Situation. "I" for your part, the team by role for theirs.
4. Give two lengths: about two minutes spoken and about thirty seconds. The short one keeps the decision and the result and drops the rest.
5. Tag each story with the competencies public employer interview guides say rounds probe: delivering results, cross-functional collaboration, handling ambiguity, prioritisation, influence and disagreement, leading and developing people, learning from failure, customer impact. A coverage table shows any competency with fewer than two stories.
6. Per story, write three likely follow-ups, such as "what was your part exactly", "what would you do differently" and "how do you know it worked", each with your honest answer in one line.
7. Per story, list the "do not stretch" facts from the row: who decided, which number has a source, what the team did.

## Output Format
```markdown
# Interview Story Bank
Updated: [date] · Built for: [roles or rounds] · Stories: [count]
## S1 · [short title] · rows [E2, E5]
Kind: [launch / failure / disagreement / thin data / stopped or cut / influence / people / trade-off / recovery]
- Situation: [context or challenge, two sentences]
- Task: [what you were responsible for]
- Action: [the steps you took, "I", the longest part]
- Result: [outcome in words, or a figure with its source] · Learned: [what you do differently now]
Thirty second version: [the decision and the result]
| Likely follow-up | Honest answer in one line |
|---|---|
| [question] | [answer] |
Do not stretch: [who decided] · [which number has a source] · [what the team did]
## Coverage
| Competency | Stories | Status |
|---|---|---|
| [competency] | [S1, S4] | [covered / fewer than two] |
## Decision
You decide which stories to say aloud first and which thin competency to fill from another real row, by [date].
```

## Done When
- Eight to twelve stories, and not all of them wins
- Every story cites its evidence rows and has both lengths
- Action is the longest part of every story
- Each story has three follow-ups and its "do not stretch" facts
- The coverage table shows every competency, thin ones included

## Quality Bar
- Speaking notes in your own words; nothing to recite.
- Colleagues appear by role and nobody is judged, least of all in the disagreement and failure stories.
- A competency with fewer than two stories is shown as thin and stays thin until a real row fills it.
- The failure story keeps the failure; it is not turned into a win.
- Stories come from evidence rows; nothing is added to make a story land, and a number with no source stays in words.

## Next
Run pmjob-tell-me-about-yourself (Tell Me About Yourself) to build the opening answer from three of these rows.

## About the makers

This pack is made by 90n ([90n.ai](https://90n.ai)): AI-native ways of working and tools for Product, Marketing and HR teams, built by ex-McKinsey founders. We map where time and money leak, redesign the work around AI and stay until your people run it themselves, and we run our own company on Claude. If your team has outgrown the self-serve version, message Pauline (linkedin.com/in/paulinebertry).

