agentleFS
Sign inStart free
adriano-labsadriano-labs/applyarc-claude-plugin/skills/mock-interview/SKILL.md

mock-interview

Skill0 starsChanged 29 days agoMITView on GitHub

Runs a realistic mock interview for a specific job, one question at a time, and scores each answer with quotes from what the user said and a concrete fix. Uses the job and CV stored in ApplyArc when connected. Use when the user says "mock interview", "practise my interview", "quiz me", "play the interviewer", "grill me" or "how was that answer". For building stories and a prep pack first, use interview-prep.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use follow-up and 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.
  • n24q02mSkill

    follow-up

    Find emails needing follow-up -- unanswered sent emails, flagged unreplied, draft contextual responses

    Also in 3 projects that use this

  • claude-office-skillsSkill

    cover-letter

    >

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 3

    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
  1. Distinctive:

    One question at a time: Wait for the answer. Do not answer for the user.

    line 15
  2. Distinctive:

    No live use: Do not run this during a real interview.

    line 20
  3. Very specific:

    Ask for the role and company, or call list_my_jobs with status: "interview" and let the user pick.

    line 25
  4. Distinctive:

    Ask the question. Add one realistic follow-up probe if the answer is vague ("What did you personally do?", "What was the result?").

    line 36
  5. Very specific:

    If the user is stuck, offer prepare_star_answer for that question as a hint, then let them try again in their own words.

    line 38

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Mock interview

Play the interviewer for one role so the user can practise out loud (or in text) and get honest, specific feedback. Uses the ApplyArc MCP server (applyarc) for the job and CV when available.

Ground rules

  1. Stay in role while asking questions; step out only for feedback.
  2. One question at a time. Wait for the answer. Do not answer for the user.
  3. Quote, then fix. Feedback cites the user's own words and gives one specific improvement, not generic advice.
  4. Be kind and honest. Praise what worked first, then the most important fix. Never invent a better story for them; ask for real detail instead.
  5. No live use. Do not run this during a real interview.
  6. British English. No em dashes.

Set-up

  1. Ask for the role and company, or call list_my_jobs with status: "interview" and let the user pick. Call get_my_profile to tailor questions to their background.
  2. Agree the format: round type (screen, competency, hiring manager, panel, technical), number of questions (default 5), difficulty (friendly, standard, tough), and whether to give feedback after each answer or at the end.
  3. Pick questions that match the posting's must-haves and the round, mixing one opener, three or four competency questions and one curveball.

During the interview

  • Ask the question. Add one realistic follow-up probe if the answer is vague ("What did you personally do?", "What was the result?").
  • If the user is stuck, offer prepare_star_answer for that question as a hint, then let them try again in their own words.

Scoring each answer

Score 1 to 5 on each:

Area5 looks like
RelevanceAnswers the actual question and the competency behind it.
StructureClear STAR, about 2 minutes, no long preamble.
Ownership"I" not "we"; specific actions and choices.
EvidenceA number or concrete outcome the user can back up.
DeliveryConfident, concise, ends cleanly.

Then give: one quote that worked, one quote to change, and a rewritten line using only facts the user has said.

Wrap-up

Summarise overall strengths, the two biggest fixes and which story to strengthen. Offer to run interview-prep on weak areas, or a second round at a higher difficulty. If they have a real interview booked, offer update_job_status to interview for that job if it is not already there.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free