agentleFS
VincenzoImpVincenzoImp/openings/skills/prepare-interview/SKILL.md

prepare-interview

Skill7 starsChanged 3 days agoMITView on GitHub

Prepare the owner for an interview or recruiter call on an Openings application - "prepare me for the interview with X". Builds a brief from the posting, the documents the employer received and the career entries, and saves it as a note.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Ask the owner for the format, the interviewers and the stage when they matter and are unknown.

    line 21
  2. Distinctive:

    Use public information about the company only from sources the owner can check, with links.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Prepare for an interview

Read openings first.

Read

  • The application with applications_get: its replies, notes and the CV and letter the employer received (documents_get for their text).
  • The posting with jobs_get.
  • workspace_context with the full career; career_get for the entries the documents cite.

Ask the owner for the format, the interviewers and the stage when they matter and are unknown. When the owner reports the invitation itself, record it as track-applications describes.

Brief

  1. What they need: the three to five main needs of the role.
  2. Stories: for each need, one or two examples from the record: the situation, what the owner did, a choice they made, the result. Match what the CV and letter already say; keep personal and team work apart.
  3. Likely questions: technical, behavioral and motivation, each with a short outline that points to a story.
  4. Weak spots: requirements the record does not cover, with an honest bridge from related work. Never coach the owner to claim experience they do not have.
  5. Logistics: availability, notice, work permit and salary as recorded in Facts about me.
  6. Questions to ask: specific to the team, product and role.

Use public information about the company only from sources the owner can check, with links.

Save

Give the brief in chat, then save it as a note on the application. Pin it only when the owner asks, since the pinned note is their guidance.

Report back

In chat: the brief itself, the questions you need answered, and that the note is saved on the application.

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.