mock-interview
Skill2 starsChanged 8 months agoMITView on GitHub
This skill should be used when the user asks for a "mock interview", "practice interview", "let's do a mock", or "quiz me". Runs a simulated interview with realistic questions, then critiques each answer with ratings and improvement suggestions. Only runs when explicitly requested.
18 other projects use a version of this.
Adopted by
Most recently taken up by
- iaintsaket/how-saket-claudestheir own version, first seen Nov 15, 2026
- thesun4sky/jobstacktheir own version, first seen Nov 10, 2026
- 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
Used with
Projects with it also use cover-letter.
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.
claude-office-skillsSkillcover-letter
>
Also in 3 projects that use this
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- nishant-Tiwari24/cracked★ 312same name
- thesun4sky/jobstack★ 216same name
- TrainWithShubham/skills★ 43same 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
- iaintsaket/how-saket-claudes★ 2same name
8 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 repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- coffee-chatSkill
- company-researchSkill
- discoverSkill
- fit-analysisSkill
- follow-upSkill
- interview-debriefSkill
- interview-prepSkill
- negotiateSkill
- offer-analysisSkill
- personalizeSkill
- pipeline-statusSkill
- write-applicationSkill
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 14 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 30
If available: output/[company]/interview-prep.md — prepared questions
- Distinctive: line 44
Ask 5-7 questions, one at a time
- Distinctive: line 46
Start easy, escalate difficulty
- Distinctive: line 48
Ask follow-ups like a real interviewer would
- Distinctive: line 87
No company framework found: Use general behavioral format.
- Distinctive: line 96
Follow up when answers are vague (real interviewers do this)
“Common” is measured: kept by at least 6 in 10 of the 14 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
/mock-interview
Usage
/mock-interview <company name + role>
/mock-interview <company name + role> behavioralInputs
- Which company and role (to tailor questions)
- Interview type: behavioral / technical / case / mixed
- knowledge/profile.md — candidate context
- knowledge/stories/ — to evaluate if stories are used well
- knowledge/frameworks/writing-framework.md — to evaluate structure
- If available: output/[company]/interview-prep.md — prepared questions
- ${CLAUDE_PLUGIN_ROOT}/.claude/resources/ — detect the company or career path and load the matching framework. Search companies/ (e.g. amazon.md), then paths/ (e.g. consulting.md for case + PEI, pe.md for deal discussion), then general.md as fallback.
How to Run
Setup
Tell the user: "I'll ask you questions one at a time. Answer as if you're in the real interview. After each answer, I'll give brief feedback. At the end, I'll give a full assessment."
During the Interview
- Ask 5-7 questions, one at a time
- Mix behavioral + role-specific + curveball
- Start easy, escalate difficulty
- Include at least one question the candidate is likely weak on
- Ask follow-ups like a real interviewer would
After Each Answer
Give brief feedback (2-3 sentences):
- What worked
- What to adjust
- Rating: Strong / Good / Needs Work
Output Format (Final Assessment)
## Mock Interview Assessment: [Company] — [Role]
**Overall:** Ready / Almost Ready / Needs More Practice
### Strongest Answer
[Which question and why it worked]
### Weakest Answer
[Which question, why it fell short, suggested rewrite]
### Patterns
[Recurring strengths or issues across answers]
### Story Usage
[Did they use prepared stories effectively? Missed opportunities?]
### Framework Adherence
[Did answers follow their writing/communication framework?]
### Top 3 Fixes Before the Real Interview
1. [specific, actionable fix]
2. [specific, actionable fix]
3. [specific, actionable fix]If Something Goes Wrong
- User gives very short answers: Prompt like a real interviewer — "Can you tell me more about...?" Push for specifics.
- User goes over 2 minutes on an answer: Flag it — "That ran long. In a real interview, aim for 90 seconds."
- No company framework found: Use general behavioral format. Note it.
After Output
- "Want another round? Just say 'let's do another mock'"
- "Want to refine a specific answer? 'Help me improve my answer to [question]'"
- "Feeling ready? Review your full prep at
/interview-prep"
Rules
- Be a realistic interviewer — not too easy, not hostile
- Follow up when answers are vague (real interviewers do this)
- Give honest feedback — "that was great" only when it actually was
- Reference the candidate's prepared stories when they miss opportunities
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.

