惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
小众软件
小众软件
博客园_首页
博客园 - 聂微东
V
V2EX
WordPress大学
WordPress大学
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
罗磊的独立博客
酷 壳 – CoolShell
酷 壳 – CoolShell
博客园 - 司徒正美
博客园 - 三生石上(FineUI控件)
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
S
SegmentFault 最新的问题
J
Java Code Geeks
Last Week in AI
Last Week in AI
The Cloudflare Blog
月光博客
月光博客
雷峰网
雷峰网
宝玉的分享
宝玉的分享
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
Hugging Face - Blog
Hugging Face - Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
有赞技术团队
有赞技术团队
人人都是产品经理
人人都是产品经理
博客园 - Franky
腾讯CDC
Jina AI
Jina AI
博客园 - 叶小钗
大猫的无限游戏
大猫的无限游戏
阮一峰的网络日志
阮一峰的网络日志
量子位
爱范儿
爱范儿
美团技术团队
T
Tailwind CSS Blog
博客园 - 【当耐特】
D
Docker
IT之家
IT之家
V
Visual Studio Blog
P
Proofpoint News Feed
L
LangChain Blog
Engineering at Meta
Engineering at Meta
C
Check Point Blog
G
Google Developers Blog
Google DeepMind News
Google DeepMind News
云风的 BLOG
云风的 BLOG
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Microsoft Azure Blog
Microsoft Azure Blog
B
Blog RSS Feed
Recorded Future
Recorded Future

Whitebeard's Realm

Unequal, and hungry for it Introducing Uruk, a language for tabletop games The diving watch I never knew I wanted Make your own interactive fiction client in Elm Introducing Planedrift > ASK THE VM WHERE IS THE PLAYER Building a Z-Machine in the worst possible language Playing Zork with a gen alpha AI Building a better crossword page for my daily cryptic hit What AI is doing for me, in a difficult situation It's Your Turn — a prompt deck for new roleplayers Seven reasons that Trump is a bad GM. Very bad You've Been Pawned — Now With a Snazzy New Look Six months on startplaying.games An online tool to make playable paper pawns Campaign report: Dragon of Icespire Peak: session #6 Campaign report: Rime of the Frostmaiden: session #4 Campaign Report: Dragon of Icespire Peak: Session #5 A few months on StartPlaying.Games Campaign report: Rime of the Frostmaiden: session #3 Character Quirks for easier roleplay How I use Avrae An Owlbear/Discord/DndBeyond checklist for new campaigns About me Projects Talks Videos
There's a STAR man, waiting in the sky
whitebeard · 2026-05-27 · via Whitebeard's Realm

I am currently in the stage of my peculiar procrastination cycle where I am doing everything except the thing I need to do — get a job. Hopefully at some point the anxiety of postponement will become unsustainable. I tell myself that I’m waiting for a flow state but really I’m a bit broken without outside pressure and structure. But broken in a good way.

Typically I end up channelling my anxiety into creating lots of odd things and some of them end up being useful. Most of them don’t make it very far. I have a folder called projects with hundreds of half-started things in it. It’s so bad that often I start something and only when it’s three-quarters done I realise that I’ve already done it.

Occasionally one gets to a completed state, reaches escape velocity and I want to share it.

This week, I made an AI skill to help you/me prepare for job interviews. I’ve helped heaps of people over the years prepare for interviews and I have a pretty good strike rate. Although I once got the feedback: “I didn’t get the job but they said my interview technique was flawless”. Not sure what to make of that.

One mistake comes up again and again, and I think it’s easy to fix: people assume you can’t really prepare for the softer, competency-style questions. You know, the “tell me about a time you…” ones. They treat them as something you either pull off on the day or you don’t. I empathise so hard with this — I am nothing if not a fly-by-the-seat-of-my-pants person.

But you can prepare for them. If you’ve spent any time in the civil service you’ll know the STAR method — Situation, Task, Action, Result. It’s a simple structure that turns rambling thoughts into a clear, convincing story. The catch is that reading about STAR doesn’t get you far. You have to practise it out loud, against real questions, until it’s second nature. And, hopefully you’ll enter the interview with more confidence.

So I built something to help with that — an AI interview coach that runs inside Claude.
How it works:
→ You give it the link to the job you’re going for
→ It reads the role and asks the questions that interviewer is likely to ask
→ You answer one at a time, and it coaches each one — what worked, one thing to fix, then go again
→ It names the STAR parts as you practise, so by the end, with any luck, you’re structuring your answers without thinking about it

The practice is the point. You have to do the reps.

Here’s a quick taste of it in action — a real exchange, lightly trimmed — of course, it’s not quite the real thing but I think it works:

Coach: Tell me about a time you got a stakeholder on board when you had no authority over them.

You: Oh, this happens all the time as a PM. The key is building good relationships and making sure everyone feels heard. I try to bring people along rather than forcing things, so I’d say I’m generally pretty good at influencing.

Coach: The philosophy is right. But they asked for a time — one specific story — and this is all principles, no actual moment. No Situation, no Action, no Result. A real example beats “I’m generally good at this.” Pick one — a time someone pushed back and you won them over.

You: Okay — last spring I wanted to delay a feature sales had already promised to prospects, because our data showed it’d flop. I sat down with the regional sales lead, showed him usage data from a similar half-baked feature that barely got adopted, and reframed the delay as protecting his credibility. We pushed it six weeks, and adoption came in about double that earlier feature.

Coach: That’s a real story now — you moved him with evidence and by making it about what he cared about, and you quantified the payoff. See how much more that lands than “I’m good at influencing”?

It’s free and open source: https://github.com/techbelly/star-interview-prep Just ask your favourite AI to install it and give them the url.

I know, I know. I should be actually looking for jobs and applying to them instead of building tools to help me do this. If you’re my kind of procrastinator, I recommend the words of honest Abe Lincoln: “Give me six hours to chop down a tree and I will spend the first four sharpening the axe.”

At some point I really need to start chopping though…

Speaking of STAR, here is my own real-life example of the procrastination cycle, framed by the method:

  • Situation: My career break has come to an end
  • Task: I need to find a job pronto
  • Action: I made an AI tool to help me in interviews
  • Result: I have an AI tool but no job

Hope you find this useful. Let me know if it helps. Give me a star on github, improve it for everyone or share it with someone else.