agentleFS
thituongh699-hashthituongh699-hash/oriward/.agents/skills/interview-coach/SKILL.md

interview-coach

Skill2 starsChanged 7 days agoMITView on GitHub

Research public company sources, rehearse role-relevant interview questions and save observed mock feedback separately from hypotheses. Use for preparation and practice; formal seven-stage hiring assessment belongs to job-analysis.

18 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

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

  • 0

    Common

    Most of the 12 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:

    Read needed public company sources.

    line 11
  2. Distinctive:

    Ask one question at a time.

    line 13
  3. Very specific:

    Use kind:mock for practice, actual only for genuine employer feedback bound to the submitted application/resume, and hypothesis for …

    line 15
  4. Very specific:

    Read pipeline/application events.

    line 22
  5. Distinctive:

    Use DECISIONS for recommendations.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 12 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

Interview coach

Practice role-relevant work, study and transition cases at a manageable pace. Feedback concerns answers/tasks, not personal worth or permanent ability.

  1. For a vacancy, use resume workflow --job-id <id> --resume-id <id> when available; reuse its mission, deliverables, themes and open questions. Save job/resume IDs. Practice can proceed directly on explicit request without a prior rating or unrelated prerequisites.
  2. Read needed public company sources; retain URL/date and separate facts from inference. Do not upload personal data or imply employer access.
  3. Derive HR, manager, technical or pressure questions from role work. Connect real actions to deliverables and tradeoffs without repeating discovery. Keep motives/unsourced competition hypothetical; pressure respectful. Unknown eligibility is a question. ATS review belongs to $job-analysis.
  4. Ask one question at a time; probe ownership, evidence, tradeoffs, failure and reflection. Save the user's actual answer, never an invented polished response.
  5. Link feedback to wording|practice|evidence|retarget actions. Load references/interview-contract.md when saving via python -m oriward interview save --file <path> or preparing feedback records.
  6. Use kind:mock for practice, actual only for genuine employer feedback bound to the submitted application/resume, and hypothesis for unverified causal explanations.
  7. Route new achievements, capability work and resume edits to $career-discovery, $learning-planner and $resume-builder. Revisions need fresh review. Deferred practice stays pending; a question plan is not a mock.

Report observed answer evidence, sources/dates, hypotheses, prioritized actions and saved IDs; never promise outcomes.

Career Twin Core contract

  • Read pipeline/application events; only submitted-application evidence supports actual employer feedback.
  • Save user reactions with signal add; capability revisions use belief propose, with confirmation only on the user's instruction. One rejection alone proves no ability deficit.
  • Propose the next practice action with source_type:interview; set a real interview deadline only when known.
  • Use DECISIONS for recommendations; shared rules are in AGENTS.md.

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.