agentleFS
HimadriTryingHimadriTrying/ai-job-search-agent/.claude/skills/interview-coach/SKILL.md

interview-coach

Skill1 starsChanged 3 months agoMITView on GitHub

Generate likely interview questions and strong answers from the user's real STAR bank, using hiring-side rubrics inverted to reveal what interviewers actually score. On demand.

18 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

interview-coach

The differentiated idea — hiring-side inversion

Install and read Lenny's hiring-side skills and reason from the interviewer's seat:

  • evaluating-candidates → what a hiring manager literally scores → invert to prepare
  • conducting-interviews → the interviewer's playbook → anticipate structure and probes
  • (writing-job-descriptions via company-research) → what the JD is really anxious about

The distinctive move here: feed the coach the hiring-side skills — how interviewers evaluate candidates, structure loops, and write the JD — so it prepares you from the interviewer's seat. You walk in already holding the hiring manager's own playbook.

Inputs

profile/07-interview-prep.md (STAR bank), company-research output, the JD.

Output

  • Likely questions for THIS role and level (Staff/Group probes: vision, influence without authority, systems thinking, trade-offs, an owned failure, AI depth).
  • For each: which of the user's real STAR stories answers it, and how to frame it.
  • Gaps: probes with no strong story yet → flag for more prep (don't fabricate one).

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.