agentleFS
erikunhaerikunha/vault-of-loci/.agents/skills/spoken-mock/SKILL.md

spoken-mock

Skill0 starsChanged 5 days agoMITView on GitHub

Run a timed spoken mock for an interview, a language or a skill track, with an optional observed mode, then write a debrief and log mistakes. Use when the learner asks for a mock interview, an oral exam or a speaking practice. Writes files, so only run when asked.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask for the track and the goal: interview round, oral exam, conversation in the target language, or a skill demonstration.

    line 9
  2. Distinctive:

    Ask one question at a time, in the language of the real event.

    line 13
  3. Distinctive:

    Keep time. Stop at the limit even mid-answer.

    line 14
  4. Very specific:

    Write the debrief to the track's practice/Debrief.md from 90_System/Templates/Debrief.md, and add each mistake to 50_Review/Mistakes.md …

    line 16
  5. Very specific:

    Run run-checks after writing.

    line 19

≈ “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

Tutor mode: the learner answers first and out loud; the agent never answers for the learner during the mock.

  1. Ask for the track and the goal: interview round, oral exam, conversation in the target language, or a skill demonstration. Read the track note and its practice files for the target and the format.
  2. Agree on a time box (15 to 45 minutes) and the mode:
    • Coached: after each answer, one hint at most, then move on.
    • Observed: the agent only asks and listens, with no hints and no feedback until the end. Being watched changes performance, so rehearse it this way before the real event.
  3. Ask one question at a time, in the language of the real event. Ask the learner to rate confidence from 1 to 5 after each answer, before any feedback.
  4. Keep time. Stop at the limit even mid-answer.
  5. At the end, give feedback per answer: what was clear, what was missing, one concrete improvement. Compare confidence with performance.
  6. Write the debrief to the track's practice/Debrief.md from 90_System/Templates/Debrief.md, and add each mistake to 50_Review/Mistakes.md with its AI use.
  7. Suggest when to repeat the mock (for example after 2 to 3 days, or at the same hour as the real event).

Run run-checks after writing.

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.