Turn a GTM opening into a scorecard before you post it.
The outcomes the role must hit, the competencies that predict them, questions per competency, and a shared rubric.
Inside: The outcomes, the competency set, the interview questions, and the rubric.
Install it in one line, or paste it in.
~/.claude/skills/ and runs automatically when it is relevant.Connect your context. Set it to your motion.
it reads what your current strong performers in the role actually do, so the outcomes are grounded, not generic.
it can align the scorecard to your stages and keep every interviewer scoring in one place.
it can turn interview debriefs into rubric scores instead of loose impressions.
This was built for a B2B SaaS GTM org hiring quota-carrying and support roles. Set these to your role:
Weight the competencies for your motion. An outbound SDR and an expansion CSM do not share a top competency, so do not score them on the same one.
| Set this | What it is | Default / Example |
|---|---|---|
| ROLE | the opening | AESDRCSMSales ManagerRevOps |
| LEVEL | seniority | mid-market AEenterprise AEteam lead |
| MOTION | what they sell into | inboundoutboundexpansionrenewal |
| RAMP_WINDOW | when outcomes are judged | first 90 / 180 / 365 days |
| COMPETENCIES | the traits you weight | pick 5-6 from the libraryor add yours |
| ATS | your applicant tracking system | GreenhouseLeverAshby |
| SCORE_SCALE | the rubric range | 1-4 (forces a callno safe middle) |
Everything the skill does, in full.
Takes the role you are hiring for and builds the thing you should have before the first interview: a scorecard. It writes the outcomes the person must hit in their first stretch, the competencies that predict those outcomes, a set of interview questions mapped to each competency, and a rubric so every interviewer scores the same candidate on the same scale. You hire against evidence instead of a gut read at the end.
- 1Outcomes first
Before competencies, the scorecard names 3 to 5 outcomes the hire must produce inside the RAMP_WINDOW, written as results, not activities. "Sourced pipeline covering quota by day 90," not "does prospecting." Outcomes are what you are actually buying. Everything else predicts them.
- 2Competencies that predict the outcomes
For each outcome, name the 1 or 2 competencies that predict it, drawn from a library: prospecting rigor, discovery depth, deal control, multi-threading, forecasting honesty, coachability, customer empathy, commercial judgment. Cap the list at 5 or 6. A scorecard that weights everything weights nothing.
- 3Questions per competency
Each competency gets 2 or 3 interview questions, behavioral and past-tense, plus what a strong answer sounds like and what a weak one sounds like. Behavioral because past behavior predicts, and the "strong vs weak" note keeps interviewers from grading on charisma.
- 4Scoring rubric
A shared rubric on the SCORE_SCALE, with each competency defined at each level so a 3 means the same thing to every interviewer. An even scale forces a call and kills the safe middle. Each interviewer scores only the 1 or 2 competencies they own, so the debrief is coverage, not repetition.
- 5Interviewer assignment
The kit assigns competencies across the loop so every one is covered by someone and no candidate is graded twice on the same thing. The hiring manager owns outcomes fit. Coverage over consensus.
- Outcomes are written as results with a date, never as activities.
- Competencies are capped at 5 or 6, each tied to an outcome it predicts.
- Every question is behavioral and past-tense, with a strong-answer and weak-answer note.
- The rubric scale is even, so no interviewer can hide in the middle.
- Every competency is assigned to a named seat in the loop.
SCORECARD · Mid-Market AE · judged at day 180 Outcomes: 1. Self-sourced pipeline at 3x quota by day 120 2. First closed-won by day 90 3. Forecast within 15% by second full quarter Competencies (weighted): Prospecting rigor -> outcome 1 (owner: SDR manager) Discovery depth -> outcome 2 (owner: hiring manager) Deal control -> outcome 2 (owner: peer AE) Forecasting honesty -> outcome 3 (owner: sales leader) Coachability -> all (owner: hiring manager) Sample question (Discovery depth): "Tell me about a deal you lost. When did you first know, and what had you not asked?" Strong: names the missing question, owns it, changed their process. Weak: blames budget, timing, or the champion leaving. Rubric: 1-4 per competency. Advance only on avg >= 3 with no 1s on a weighted competency.
The RAMP_WINDOW, the 3x pipeline target, and the 1-4 scale are examples for illustration, not benchmarks. They suited a mid-market SaaS AE. Set outcomes to your own ramp and quota, and pick a scale your interviewers will actually use. The framework does not change. The bar is yours.
Where an operator takes this next.
The scorecard is step one. Here is where an operator takes it once the manual version proves out.
You built the bar once, now every interview gets held to it.
Feed interview notes from Gong or a meeting tool into a scheduled Claude task that scores each competency against the rubric and writes it to Greenhouse or Lever.
DM the hiring manager in Slack the moment two interviewers score the same competency more than one point apart.
Pull 90-day and 180-day actuals from Salesforce and compare them to the outcomes you wrote, so next quarter's scorecard is calibrated on your own hires, not a guess.
One skill is the on-ramp.
A single skill does one job. Chained into a playbook, or run as a full build, it becomes a system. Here is where this one plugs in.