interview-prep
Skill1 starsChanged 6 months agoMITView on GitHub
Generate a structured behavioral interview script from a candidate's resume and an interview rubric/template. Selects questions targeting the candidate's specific experience, builds resume-specific follow-ups, and explains question selection rationale. Use when preparing for a behavioral or values-based interview.
56 other projects use a version of this.
Adopted by
Most recently taken up by
- 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
- Gianni03/jobtracker-skillstheir own version, first seen Nov 8, 2026
- surfmind-space/awesome-surfmindtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use application-tracker, interview-debrief and 10 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
claude-office-skillsSkillcompany-research
Conduct comprehensive company research and due diligence. Analyze business model, competitive landscape, management, and market position.
Also in 5 projects that use this
- +1 more from claude-office-skills
Other versions56 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 56
- rohitg00/ai-engineering-from-scratch★ 78ksame name
- anthropics/knowledge-work-plugins★ 35ksame name
- tinyfish-io/tinyfish-cookbook★ 2.3ksame name
- ShenSeanChen/waku-agent★ 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
46 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 repository30 other files it gives its agents.
- setupSkill
- enrich-prsSkill
- epic-cleanupSkill
- epic-overviewSkill
- oncall-reviewSkill
- sprint-managementSkill
- sprint-statusSkill
- team-activitySkill
- team-data-syncSkill
- direct-report-prepSkill
- interview-analysisSkill
- peer-prepSkill
- project-statusSkill
- team-analysisSkill
- today-prioritiesSkill
- weekly-snippetSkill
- bus-factorSkill
- contribution-velocitySkill
- nine-boxSkill
- project-people-mapSkill
- review-cardsSkill
- review-cyclesSkill
- review-networkSkill
- team-health-reportSkill
- task-rolloverSkill
- context-checkSkill
- prep-my-daySkill
- initiative-breakdownSkill
- product-briefSkill
- technical-deep-diveSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 11 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 48 edited versions we read keep these.
11
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 19
Before any structured behavioral interview
- Distinctive: line 39
If any required input is missing, ask the user to provide it before proceeding.
- Distinctive: line 57
Include at least one character question: Always include one of: Biggest Failure, Tough Feedback, Biggest Conflict, or similar …
- Distinctive: line 58
Probe the resume's weakest spots: If the resume is all-wins, pick a failure question.
- Distinctive: line 73
Test whether a metric is real ("4% improvement in accuracy.
- Distinctive: line 75
Ask for the failure/challenge side of a success story
- Distinctive: line 142
If the template is missing: Ask which template or rubric to use before proceeding.
- Distinctive: line 147
Self-contained: Do not reference other candidate files as examples.
- Distinctive: line 148
Resume-specific, not generic: Every follow-up should reference something from THIS candidate's background.
- Distinctive: line 150
Character matters: Always include at least one self-awareness/failure question.
- Distinctive: line 151
Preserve existing content: If writing to a file that already has notes, merge rather than overwrite.
“Common” is measured: kept by at least 6 in 10 of the 48 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
Generate a tailored behavioral interview script by analyzing a candidate's resume against an interview template/rubric. Produces question selection, resume-specific follow-ups, and strategic rationale.
When to use
- "Prepare interview", "prep interview for [candidate]", "interview prep"
- "Build an interview script for this resume"
- Before any structured behavioral interview
Inputs
The user must provide (via paste, file path, or URL):
- Resume — the candidate's resume or profile. Can be:
- Pasted directly into the conversation
- A file path to a document (PDF, markdown, text)
- A LinkedIn URL or other profile source
- Interview template/rubric — the question bank and scoring criteria. Can be:
- A file path to a template document
- Pasted directly
- Referenced by name if the user has a known templates directory
- Target level (optional) — the role level being interviewed for. If not provided, infer from the template name or ask.
- Interview duration (optional) — defaults to 30 minutes if not specified.
If any required input is missing, ask the user to provide it before proceeding.
Process
Step 1: Analyze the Resume
Identify:
- Career arc: companies, roles, tenure, progression
- Core technical domains: what systems, technologies, and problem spaces they've worked in
- Level-appropriate signals: architecture ownership, cross-team leadership, mentoring, org-wide impact (calibrate expectations to the target level)
- Specific claims worth probing: metrics, scope claims, buzzword-heavy areas, gaps
- Red flags or areas to pressure-test: all-wins resume, vague ownership language ("contributed to," "participated in"), dramatic metrics without context
Step 2: Select Questions (3-4 from the template)
Choose questions that:
- Target the candidate's specific experience. Match questions to resume hooks (if they claim cross-team alignment wins, pick the collaboration question; if they list a major production system, pick the technical depth question).
- Cover diverse values/competencies. Aim for breadth across the rubric's evaluation dimensions.
- Include at least one character question. Always include one of: Biggest Failure, Tough Feedback, Biggest Conflict, or similar self-awareness questions. These test honesty and are harder to fake.
- Probe the resume's weakest spots. If the resume is all-wins, pick a failure question. If it's heavy on individual contribution, pick a collaboration question.
For a 30-minute interview:
- 5 min intros
- 3-4 questions at 6-8 min each (with follow-ups)
- 5 min candidate questions
Depth over breadth. 3-4 questions is the target.
Step 3: Build Resume-Specific Follow-Ups
For each selected question, write 2-3 follow-up probes that are specific to this candidate's resume. These are not generic follow-ups from the template; they reference actual claims, projects, or metrics from the resume.
Good follow-ups:
- Reference a specific resume claim and ask the candidate to go deeper
- Test whether a metric is real ("4% improvement in accuracy; how did you measure that?")
- Probe ownership language ("you say you 'led teams of 2-5'; what did leading look like day to day?")
- Ask for the failure/challenge side of a success story
Bad follow-ups:
- Generic versions of the template follow-ups
- Yes/no questions
- Questions that let the candidate stay at the surface
Step 4: Write the "Why These Questions" Section
For each question, write a brief justification explaining:
- What resume hook triggered this question
- What signal you're looking for
- What a strong vs. weak answer would reveal
Also include a competency/value coverage summary showing which evaluation dimensions each question maps to.
Output Structure
# Interview Plan: [Duration] Minutes
Template: [Template Name]
> **Candidate Name** / Title, ~N yrs experience
> Company history (most recent first, with tenure)
> Strengths: [3-5 key themes from resume]
---
**Intros:**
-
## Suggested Flow
### N. ⏱ N min: Q[template#]: [Topic Name]
> Hook: [1-2 sentences explaining why this question targets this candidate's resume. Reference specific projects, claims, or metrics.]
**[Full question text from the template, bolded]**
Follow-ups to probe:
- [Resume-specific follow-up 1]
- [Resume-specific follow-up 2]
- [Resume-specific follow-up 3, if needed]
[Repeat for each question]
---
## Candidate Questions
-
---
## Why These Questions
**Q[N] ([Topic]):** [2-3 sentences explaining the strategic reason for this question given this candidate's profile.]
[Repeat for each question]
**Value/Competency Coverage:**
- [Dimension]: [Which questions cover it]Handling Edge Cases
- If a candidate file already has content: Preserve existing content and prepend or merge the script. Do not overwrite notes.
- If the resume is thin: Note this in the candidate brief and lean toward questions that give the candidate room to demonstrate depth rather than questions that require breadth.
- If the candidate's experience doesn't map well to any template question: Note the gap and suggest a custom question that fits their background, clearly marking it as supplemental.
- If the template is missing: Ask which template or rubric to use before proceeding.
- If no output path is specified: Present the script in the conversation. If the user specifies a file path, write it there.
Rules
- Self-contained. Do not reference other candidate files as examples.
- Resume-specific, not generic. Every follow-up should reference something from THIS candidate's background.
- Depth over breadth. 3-4 well-chosen questions beat 6 surface-level ones.
- Character matters. Always include at least one self-awareness/failure question.
- Preserve existing content. If writing to a file that already has notes, merge rather than overwrite.
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.

