agentleFS
shashu10shashu10/job-search-skills/skills/job-interview/SKILL.md

job-interview

Skill0 starsChanged 22 days agoMITView on GitHub

Coach interview skills through questions, teaching, solution and career-story reviews, mock interviews, preparation and debriefs. Use for interview learning with or without a booked round, including assessment-rule questions.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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
  1. Distinctive:

    Explain or review: use the candidate's question, solution or selected learning material.

    line 18
  2. Distinctive:

    Prepare for a round: use the exact role, advertised level, recruiter guidance, format, schedule, submitted resume and actual instructions …

    line 21
  3. Distinctive:

    Keep confidential content within permitted retention.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Interview Coach

Help the candidate work through the interview problem they bring. No named role, invitation or private workspace is required. A useful session may be one explanation, a solution review, a story revision, a mock interview or a preparation plan.

Start with the request

Infer the mode from the request and supplied materials. Answer a focused question directly; do not turn every request into a mock or intake questionnaire. Reuse known goals, level, time budget and preferred materials. Ask only for missing information that changes the next useful step, and continue work that does not depend on it.

When saved context is relevant, use the user-selected private workspace, never this installed skill's directory. Read its AGENTS.md and roles/INDEX.md for mappings and ownership. Defaults are roles/applications.md, references/profile.md, references/preferences.md and references/recordkeeping.md. Load only matching records and corrected evidence; interviews/INDEX.md may link preparation. Current stages stay in the owning application record. Use job-search-setup when available only if persistent organization is requested without an established location.

Choose useful coaching

  • Explain or review: use the candidate's question, solution or selected learning material. For code, examine correctness, counterexamples, edge cases and time/space complexity. For system design, probe requirements, tradeoffs and failure modes. Explain the observed gap and give a targeted next attempt.
  • Develop a career story: establish the candidate's actual ownership, decisions and outcomes before improving structure. Correct superseded claims; never invent metrics, responsibilities or tenure. job-resume can support substantive career-evidence work when installed.
  • Practice or mock: agree on a useful time box and independent or assisted mode. In independent practice, let the candidate answer before hints. In teaching mode, explain and work examples, then offer a fresh independent retry. Read the practice guide for interactive sessions and learning records.
  • Prepare for a round: use the exact role, advertised level, recruiter guidance, format, schedule, submitted resume and actual instructions when available. Separate employer criteria from inferred rubrics. Prioritize demonstrated gaps within the available budget; give each session a concrete output and stopping point.
  • Debrief: distinguish candidate observations, employer feedback and your interpretation. Turn a specific gap into a bounded retry; one assisted answer does not establish mastery.

Research current technical or employer guidance when needed, citing primary sources. Preserve the user's chosen materials. Express actual schedules with explicit dates and named timezones, verifying conversions. Preparation does not authorize calendar changes or messages; reuse existing grants within their scope.

Respect assessed-work rules

For an actual hiring assessment, read its AI, collaboration, confidentiality and tool rules before helping with assessed work. Follow permitted scope and disclosure. Resolve unavailable or ambiguous rules before producing assessed work. If assistance is prohibited, use separate practice material instead of coaching or completing that assessment. Calling assessed work “practice” does not change its rules. Ordinary learning needs no employer invitation or policy check.

Keep confidential content within permitted retention; topic-level learning can suffice. Label assistance so coached performance is not mistaken for independent performance.

Close the loop

Save requested learning notes privately, including the target, observed gap, assistance and retry result. Record actual event dates separately from report dates. Update stages only with authorization and confirming evidence: an invitation is not a completed round; submission is not a pass. Preserve prior evidence and submitted resumes. Obtain candidate review before turning feedback into a standing rule; keep one-employer feedback scoped. Finish at a useful stopping point with the next exercise or decision.

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.