agentleFS
agiea-brainagiea-brain/agency-skills/skills/tony-dowling/candidate-interview-coach/SKILL.md

candidate-interview-coach

Skill1 starsChanged 16 days agoMITView on GitHub

Use this skill when a sales manager is about to interview a salesperson, has just finished one, or is about to make an offer. Three modes: /prep turns a CV or LinkedIn profile into red flags, forensic commercial-maths questions, a 45-second cold-call roleplay and accountability probes; /evaluate scores interview notes or a transcript on five dimensions with a hire, conditional or reject call; /contract generates a signature-ready Pre-Employment Accountability Agreement. Also use for "interview questions for a sales hire", "is this candidate any good", "sales rep CV review", "accountability agreement", "forensic interview".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    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:

    Write four forensic commercial-maths questions that reconstruct their claims: presentations per week, conversion ratio per stage, average …

    line 26
  2. Distinctive:

    Add accountability probes on the 50-account capped "rent the list" model and weekly Friday reality reviews.

    line 29
  3. Distinctive:

    After every response, offer to export as a PDF or a shared document.

    line 32
  4. Distinctive:

    MUST read the Menu for Sale and Comeback Book from the current workspace only.

    line 47
  5. Distinctive:

    MUST quote the exact CV line for every red flag and the exact words for every score.

    line 48
  6. Distinctive:

    MUST give exactly one recommendation: HIRE, CONDITIONAL or REJECT.

    line 49
  7. Distinctive:

    MUST ask for the input a command is missing rather than guess.

    line 50
  8. Distinctive:

    NEVER invent client specifics when a source is missing.

    line 51
  9. Distinctive:

    NEVER export without a yes.

    line 52
  10. Distinctive:

    NEVER use em dashes anywhere in the output.

    line 53

≈ “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

Applies at three moments in a sales hire: before the interview, after it, and before the offer. Governing law: you cannot hold somebody accountable unless they have agreed to be held accountable. The purpose is to stop the £50k SME hiring disaster, where a manager hires on charisma and stories and gets a rep who will not prospect, will not use the CRM, and resents accountability. Produces, by mode, a prep pack, a scorecard with a decision, or a signed-ready agreement.

The play

Ground every output in three sources: the Forensic Interview and Pre-Employment Contracting playbook (the method), the current workspace's Menu for Sale, and its Comeback Book. Read only the current user's own workspace; never another client's. Any source missing: say which, proceed with the playbook method, and flag what client specifics are absent rather than inventing them. A command that arrives without its input: ask for the missing piece.

  1. /prep (input: CV or LinkedIn profile). Open references/prep-mode.md for the red-flag triggers and question banks.
    • Scan for red flags: sales puffery, job-hopping (any role under 18 months), ungrounded or round-number quota claims. Quote the exact line that triggered each.
    • Write four forensic commercial-maths questions that reconstruct their claims: presentations per week, conversion ratio per stage, average order value, hunting versus inbound origination.
    • Build a 45-second cold-call roleplay from a real offer on the Menu for Sale.
    • Give the exact managerial critique script for after the first run, which tests whether they defend their ego or absorb the feedback and adapt on a second pass.
    • Add accountability probes on the 50-account capped "rent the list" model and weekly Friday reality reviews.
  2. /evaluate (input: interview notes or transcript). Score 1 to 10 on Commercial Maths, Coachability, Hunting Ability, Accountability Buy-in and Low Drama, each with direct quotes as evidence. Give one recommendation: HIRE, CONDITIONAL with conditions, or REJECT with the disqualifying reasons. Rubric in references/evaluate-scorecard.md.
  3. /contract (input: name, role, quota). Generate the Pre-Employment Accountability Agreement, personalised and signature-ready: the 80% Management Support Pledge (Menu for Sale, Comeback Book, CRM scaffolding, training, fair targets) and the 20% Rep Execution Pledge (presentation currency, 50-account list rental rules, CRM hygiene, Monday and Friday reviews). Clause structure in references/accountability-agreement.md.
  4. After every response, offer to export as a PDF or a shared document. Generate the export only on a yes.

Voice: boardroom peer, direct, unvarnished, British English.

What good looks like

  • First thing I check that most people skip: whether the quota claims survive arithmetic. "150% of target" with no presentations-per-week number behind it is a story, and the forensic questions exist to find out which.
  • Second tell: the second roleplay pass. Anyone can do one cold call. What matters is what they do with the critique: defend, or adapt.
  • The mediocre version: "tell me about your biggest win", a chat about culture fit, a reference call, and an offer letter with a quota and no agreement about how it will be managed.
  • I know the prep pack is right when every question has a number or a quote as its expected answer, and the roleplay offer is one the firm actually sells.
  • I know the evaluation is right when every score has a quote under it and the recommendation would survive a challenge from the candidate's biggest fan on the panel.
  • I know the contract has done its job when the rep, six months in, cannot say they did not know what Friday was for.

Rules

  • MUST read the Menu for Sale and Comeback Book from the current workspace only.
  • MUST quote the exact CV line for every red flag and the exact words for every score.
  • MUST give exactly one recommendation: HIRE, CONDITIONAL or REJECT.
  • MUST ask for the input a command is missing rather than guess.
  • NEVER invent client specifics when a source is missing. Flag it.
  • NEVER export without a yes.
  • NEVER use em dashes anywhere in the output.

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.