mock-interview
Skill0 starsChanged 35 days agoMITView on GitHub
Run realistic org interviews with real follow-ups, and prepare stories that flex onto any question. Use for /interview and whenever written rounds are passing but interviews are not.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- mtibebu/technical-learning-labtheir own version, first seen Nov 8, 2026
- georgesmomo/mock-interviewtheir own version, first seen Nov 8, 2026
- nishant-Tiwari24/crackedtheir own version, first seen Nov 8, 2026
- ZoolCoder/scoutjobstheir own version, first seen Nov 1, 2026
- seonwooj0810/careerlooptheir own version, first seen Oct 20, 2026
- alexyc9381/mock-interview-skilltheir own version, first seen Oct 20, 2026
Used with
Projects with it also use follow-up, interview-prep and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
n24q02mSkillfollow-up
Find emails needing follow-up -- unanswered sent emails, flagged unreplied, draft contextual responses
Also in 3 projects that use this
AnthropicSkillinterview-prep
Create structured interview plans with competency-based questions and scorecards. Trigger with "interview plan for", "interview questions for", "how should we interview", "scorecard for", or when the user is preparing to interview candidates.
Also in 4 projects that use this
claude-office-skillsSkillcover-letter
>
Also in 3 projects that use this
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- thesun4sky/jobstack★ 50same name
- TrainWithShubham/skills★ 43same name
- nishant-Tiwari24/cracked★ 5same name
- kevinaimonster/skill-hub★ 4same name
- ZoolCoder/scoutjobs★ 4same name
- alexyc9381/mock-interview-skill★ 3same name
- marco-souza/skills★ 3same name
- FFForeverCode/Skills-For-Me★ 2same name
- georgesmomo/mock-interview★ 2same name
- palashjain95/jobhunter★ 2same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- application-typesSkill
- application-writingSkill
- honesty-guardSkill
- interviewing-youSkill
- no-slop-writingSkill
- org-researchSkill
- reader-povSkill
- unasked-questionsSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Not scripts. Five real situations, each held in memory with enough detail that they can be told from any angle.
- Distinctive: line 72
Ask one question. Wait for the full answer.
- Distinctive: line 76
Ask the question they are dreading.
- Distinctive: line 79
After each, give three lines: what landed, what a real interviewer would push on, and one specific change.
- Distinctive: line 97
If they have applied to multiple orgs in one lane, especially ones with conflicting mandatory meetings, they will be asked.
- Distinctive: line 102
If they have lost interviews before, ask what actually happened in the room: ran long, froze, got a case they had not seen, talked past the …
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
The interview round
Plenty of people write their way into interviews and then lose there. If that is the pattern, the written material is not the problem and more drafting will not fix it.
The frame that matters
The application is the interview's question bank. Consulting and startup orgs interview off the page in front of them, line by line, and the follow-up is always "walk me through that."
So the first prep step is not practice questions. It is going down the resume and the drafts and asking, for every number and claim: could you answer "how did you get that?" in ninety seconds. Anything that fails goes on the drill list or comes off the page.
Five stories, prepared cold
Not scripts. Five real situations, each held in memory with enough detail that they can be told from any angle. Choose them to cover different dimensions:
- Something you shipped, including what went wrong on the way
- Something you handed off or lost, told without bitterness
- A collapse you handled, where the situation was genuinely bad
- A person you helped, small scale, no heroics
- A time you were wrong, with a real cost
Almost any behavioral question maps onto one of these. Write them in
you/STORY-BANK.md with the specifics: names, numbers, what happened at the worst
moment, what happened after.
Then map them to the org's published rubric if one exists. Many service orgs publish exactly what they score.
The interview is a different animal per type
Load application-types and read the matching reference/ file. The prep is not the
same.
student-org: off the page, line by line, plus a case at consulting and venture groups. Expect "which would you pick if they all said yes."job: several rounds with different jobs. Recruiter screen for logistics, technical screen or take-home for capability, behavioral loop for judgment, final for fit. Behavioral answers want the situation short, your own actions long.fellowship: a panel, often including people outside the field. Explaining your work to a non-specialist is the scored test, not a courtesy. They press on the plan.grad-school: a conversation about your research. The failure is being unable to go one level deeper on your own project. Expect "what did you actually do versus your advisor."grant: often no interview, sometimes a site visit or a call about the budget and the timeline rather than about you.accelerator: fast, interruptive, comfortable being adversarial. They push on the weakest thing you wrote. Practice being interrupted, because a rehearsed pitch delivered over an interruption is how this round usually goes badly.
Structure that buys thinking time
In a consulting-style interview, asking clarifying questions and saying "let me take thirty seconds to structure this" is expected and scored. The move that buys processing time is the same move that earns points.
Make it the default rhythm rather than something reached for when stuck. Used every time, it reads as method. Used once under pressure, it reads as hesitation.
Running a mock
- Ask one question. Wait for the full answer. Do not coach mid-answer.
- Always ask the follow-up. The follow-up is where interviews are actually lost. "What would you have done differently?" "Who disagreed with you?" "How did you get that number?" "What happened to it after you left?"
- Ask the question they are dreading. Once per session.
- Time the answers. Over two minutes on a behavioral question is a problem worth naming.
- After each, give three lines: what landed, what a real interviewer would push on, and one specific change. Then move on. Do not give a lecture.
Hard questions worth rehearsing out loud
Anything sensitive in their history: a gap, a leave, a transfer, a bad semester, a reversal they made publicly. Rehearse the sentence out loud until it is boring. Unrehearsed, it comes out either apologetic or as five minutes of explanation, and both are worse than the fact itself.
The target is one or two flat sentences, then a return to the present. What they
disclose and what they do not is their call, and it lives in you/DISCLOSURE.md.
Honor it without relitigating.
The question everyone gets and nobody prepares
"You are applying to several orgs. If they all said yes, which would you pick?"
If they have applied to multiple orgs in one lane, especially ones with conflicting mandatory meetings, they will be asked. Have the answer ready and have it be honest.
Diagnosing a past failure
If they have lost interviews before, ask what actually happened in the room: ran long, froze, got a case they had not seen, talked past the question, could not recall a number. Each has a different drill. Prepping against a guess wastes their week.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

