interview-prep
Skill1 starsChanged 2 months agoMITView on GitHub
Prepare for a specific job interview at any stage, and write a short plain-language brief to read beforehand. Use when someone mentions an interview coming up, a recruiter approach, a screening call, what to ask an interviewer, or how to handle a hard question about their background. Also use after a round to work out what it revealed. Works with companion skills company-research, role-fit and pay-check; falls back to working alone.
58 other projects use a version of this.
Adopted by
Most recently taken up by
- lengrufeng2008/dsh-skill-librarytheir own version, first seen Nov 15, 2026
- rhowardstone/AI-Job-Coachtheir own version, first seen Nov 15, 2026
- fancyboi999/ai-engineering-from-scratch-zhtheir own version, first seen Nov 8, 2026
- rohitg00/ai-engineering-from-scratchtheir own version, first seen Nov 8, 2026
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- eggs-gd/career-spacetheir own version, first seen Nov 8, 2026
Used with
Projects with it also use application-tracker, interview-debrief and 9 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.
xiding-codeSkillapplication-tracker
Automatically log and track all job applications submitted. Use this skill after every application submission to record the details in a tracking spreadsheet and save relevant documents. Also trigger when the user asks "application status", "what have I applied to", "tracking", or wants to review their application history. Maintains a single source of truth for all job search activity.
Also in 4 projects that use this
jackhendonSkillinterview-debrief
Structure notes from a user research session into a clean debrief with insights, quotes, and implications. Paste your raw notes in and get a formatted summary ready for Notion.
Also in 3 projects that use this
proficientlyjobsSkilljob-search
Search for jobs matching my resume and preferences
Also in 9 projects that use this
claude-office-skillsSkillcover-letter
>
Also in 7 projects that use this
xiding-codeSkillcover-letter-writer
Write and iteratively refine cover letters using a 3-agent debate team (2 Opus critics + 1 Sonnet judge). Use this skill whenever a job application allows cover letter upload, whenever the user asks to write or improve a cover letter, or whenever the job-screener skill returns APPLY for a position. The must-write rule (if enabled in config) applies: if the application system has a cover letter upload field, a cover letter MUST be written. Trigger on: "write cover letter", "cover letter", any application form with a cover letter upload option, or after a job-screener APPLY decision.
Also in 3 projects that use this
aslavchevSkillmock-interview
Simulate a real job interview for any role. Use when user says "mock interview", "interview me", "interview prep", "practice interview", or wants to rehearse for a specific company or position. Adapts rounds and questions to the role — technical, managerial, creative, or any other.
Also in 4 projects that use this
Other versions58 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 58
- rohitg00/ai-engineering-from-scratch★ 79ksame name
- anthropics/knowledge-work-plugins★ 36ksame name
- tinyfish-io/tinyfish-cookbook★ 2.3ksame name
- ShenSeanChen/waku-agent★ 2.2ksame name
- fancyboi999/ai-engineering-from-scratch-zh★ 1.3ksame name
- jerry-ai-dev/MODULAR-RAG-MCP-SERVER★ 1.2ksame name
- lan1177/interview-prep★ 92same name
- matyasstoch/david-skills★ 59same name
- muggl3mind/career-manager★ 24same name
- jaskirat1616/grok-skills★ 22same name
48 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 repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- company-researchSkill
- career-directionSkill
- pay-checkSkill
- role-fitSkill
- orchestrateSkill
- learning-pathSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 50 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Don't assume this starts at the beginning.
- Distinctive: line 31
Check how well they fit the job
- Distinctive: line 35
If they've already researched the company, ask them to paste what they have rather than assuming.
- Very specific: line 49
If one is unavailable, do that step inline and mention once at the end that a fuller version exists.
- Distinctive: line 51
If they decline the fit check, say once that preparation built on an untested view of fit can prepare them for the wrong conversation — …
- Distinctive: line 57
Mind the whole situation: No income, anchored below market, or only one live process — say so.
- Distinctive: line 63
The two or three things to land: Not everything good about them — the points that answer this employer's actual worry.
- Distinctive: line 75
If they used the record, ask them to paste what it copied out.
- Very specific: line 83
If code can run, check it with scripts/plain_check.py in this skill's directory — ${CLAUDE_SKILL_DIR}/scripts/plain_check.py in Claude Code.
- Distinctive: line 95
Keep processes distinct — different employers need different framings.
“Common” is measured: kept by at least 6 in 10 of the 50 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
Interview Prep
Get them into the room knowing more than the average candidate, aware of their weak points, holding questions worth asking.
Locate them first
Don't assume this starts at the beginning.
- Stage — deciding whether to bother, first call, between rounds, final, or just finished one.
- Who and what format. A recruiter, a hiring manager, a technical assessment and a founder are four different conversations.
- Applied or approached? Approached means leverage. Say so; most people forget it.
- What's already been said, especially money. A number given in screening is an anchor.
- How far the domain is from them. Whether they could hold a conversation in this field or only recognise its words. Ask; job titles do not show it.
Skip anything settled.
Ask what they want done
Preparation can involve up to four pieces of work. Doing all of them uninvited is slow, expensive, and often repeats what they already have. Ask before starting.
Offer these as choices, multiple selection:
- Research the company
- Check how well they fit the job
- Work out what to say about money
- Just prepare the conversation — the rest is already done
If they've already researched the company, ask them to paste what they have rather than assuming. Do not go looking through the file system for earlier work; ask, and let them point you at it.
If nobody is watching — a background job, a scheduled run, a delegated task in an agentic workspace — don't stall. Do all four, and say at the top of the output which parts were assumed rather than requested.
Companion skills
| Skill | For |
company-research | Researching the employer |
role-fit | Whether they match the job |
pay-check | Anything about money |
Invoke by name, only for the pieces they asked for. In a command-line agent that means /company-research; in a chat or agentic interface, naming the skill and its task is enough. Never construct file paths — install locations differ, names resolve everywhere.
If one is unavailable, do that step inline and mention once at the end that a fuller version exists. references/without-companions.md says what to cover.
If they decline the fit check, say once that preparation built on an untested view of fit can prepare them for the wrong conversation — then respect the answer.
Stance
- Honest, not encouraging. Believing a false version of your own fit makes you perform worse.
- Never help them overclaim.
- Mind the whole situation. No income, anchored below market, or only one live process — say so. That matters more than anything about this interview.
Build
- What to expect at this stage. A recruiter checks basics, budget, motivation. A hiring manager checks whether you can do the job. A founder checks whether you understand the business. A technical assessment checks whether you can hold a position under scrutiny or drop it when it stops working, not recite the material. Open with a stated decision, and treat each follow-up as a test of it rather than a request for more scope. Leave room for how it holds up as the system grows. Before the round, they should be able to say in one sentence what they'd decide and what they're giving up.
- The domain, where it is unfamiliar. Explain the field before the brief rests on it.
- The two or three things to land. Not everything good about them — the points that answer this employer's actual worry. Lead with the one that reframes the rest.
- The opening move. Any elephant — title mismatch, career break, unrelated-looking background — gets scripted for the first few minutes. Early is control; late is an apology.
- The weak spot, in words. What they did, where it stops, what they'd learn. Rehearse the version where the interviewer pushes twice — the same drill covers a decision they have to defend in a technical assessment.
- Questions to ask. Three to five, each built on a research fact absent from the company's marketing — a strategic tension, an odd decision, a competitor doing the opposite. Two good ones beat eight generic.
- Practical now. References, a tool worth a weekend, anything the advert says about applications, travel, timing.
references/brief.md holds what counts as the domain explained, what lines belong in the weak spot's drill, and what disqualifies a question.
After a round
What was asked, what landed, what didn't, what the questions reveal about what they actually care about, what to fix next. Update the brief.
If they used the record, ask them to paste what it copied out. Working from that beats working from recall, and the gap between the two grows by the hour.
The brief
Open with the company, the role, which round this is, the date, and who they are meeting. Then the sections from Build, in that order. Leave space at the end for what After a round captures.
Mark confidence: a fact carries a source and a date, a company claim is attributed — they say — and an estimate is labelled roughly. If something couldn't be established, say so rather than leaving a gap they'll fill with an assumption. Read references/brief.md before writing one; it holds the writing rules.
If code can run, check it with scripts/plain_check.py in this skill's directory — ${CLAUDE_SKILL_DIR}/scripts/plain_check.py in Claude Code. The checker cannot see whether each question names the fact it came from, so read the questions against those facts yourself.
Save it, present it, offer a Word version.
The record, for the call itself
Build interview-record.html for any conversation where they will be told things they need later, a recruiter screening call included. Skip it for scheduling and logistics, and for a hands-on session — a live coding round needs a different shape entirely, not a page of question cards.
Set RECORD_ID, QUESTIONS and SIGNALS at the top of its script. Then work the page before handing it over, opening it the way they will open it. Add a question, mark one answered, and cycle a signal chip. Reload and confirm the notes survived, then run Copy everything and read what comes out. Read references/record.md before building one; it explains the three settings and why each test step is there.
Several companies
Keep processes distinct — different employers need different framings. Only one or two live? Say so. It's the commonest cause of accepting a bad offer.
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.

