Hire or Pass
Debriefs go wrong when the loudest interviewer wins or when everyone waits to see what the manager thinks. This skill forces the evidence into a fixed shape — per competency, strongest example and strongest counter-example, from whom — and defines the four possible outcomes before the discussion starts. The output is a distribution over those outcomes and, when it is close, the specific extra signal to go get.
Boundary. This is decision support. A person makes and owns the hiring decision, applies the company's process and the law where they are, and is accountable for it. Never let a distribution replace that.
Where this sits
After hiring-rubric (which defines the competencies) and engineering-hiring-rubric, and after the interviews. This one runs the debrief decision.
What This Skill Produces
- The evidence state — per must-have competency: strongest example, strongest counter-example, which interviewer saw it, rubric scores
- The decision —
hire / hire_at_different_level / more_signal / pass with probabilities and confidence
- Act or hold — thresholds applied; a close hire/pass is a
more_signal by definition
- The signal plan — when holding: the competency to test, the format, who runs it, by when
- The debrief record — one paragraph for the file: evidence summary, decision, who decided
Required Inputs
Ask for these; do not infer from "vibes" or an interviewer's overall thumbs:
- role — title, level, the 3–5 must-have competencies from the rubric
- evidence — per competency: strongest observed example and strongest counter-example, with the interviewer who saw it
- scores — rubric scores per interviewer per competency
- references — if taken: confirmed or contradicted what
- risks — gaps, level mismatch, red flags with the evidence behind them
- process — any missed interviews or untested competencies
Framework: Four Defined Outcomes
| Option |
It applies when |
hire |
Every must-have competency has positive evidence from at least two interviewers, and no red flag has evidence behind it |
hire_at_different_level |
The evidence supports the competencies at a different level than the role was opened at |
more_signal |
A must-have was untested, or the evidence is split between interviewers — one targeted extra conversation decides it |
pass |
A must-have competency has negative evidence, or a red flag is substantiated |
Thresholds. Act when confidence ≥ 0.65 and the winning option's probability ≥ 0.7. A close hire / pass is a more_signal outcome: name the competency and who tests it. Never decide on the distribution alone.
Evidence, not impressions. "Strong communicator" is an impression. "Explained the outage timeline to a non-engineer in the panel without being asked — seen by R." is evidence. Only evidence enters the state.
Getting probabilities. Any calibrated decision model that returns a probability per defined option serves this contract; the repo ships an adapter (node integrations/jev/decide.mjs hire-or-pass --state state.json, contract in integrations/jev/decisions/). Without one, the assistant estimates and labels it. Either way the decision is the hiring manager's.
Output Format
Debrief decision: [role, level] · candidate [initials]
Evidence by competency
| Competency |
Strongest example (who) |
Strongest counter (who) |
Scores |
| … |
… |
… |
… |
Decision
| Option |
Probability |
| hire |
0.xx |
| hire_at_different_level |
0.xx |
| more_signal |
0.xx |
| pass |
0.xx |
Confidence: 0.xx · Source: [model / estimate]
Verdict: [act: option] or [hold → more_signal: competency, format, owner, by when]
Debrief record: [one paragraph — evidence summary, the decision, who made it]
Quality Checks
Anti-Patterns
- Overall thumbs replacing per-competency evidence
- Anchoring on the manager — collect scores before anyone speaks
- "Culture fit" as an undefined competency
- Deciding a coin flip — 0.5 / 0.5 hire/pass is a
more_signal, always
- Letting the model hire — it produces evidence about evidence; a person decides
Example Trigger Phrases
- "Run the debrief — three interviewers, split panel."
- "Hire or pass on this candidate? Here are the scorecards."
- "We're at hire vs. pass 50/50 — what do we do?"
1---2name: hire-or-pass3description: "Turn a hiring debrief into a typed decision — hire, hire at a different level, get more signal, or pass — from rubric evidence only, with probabilities and confidence. Use when asked should we hire this candidate, run the debrief, hire or no-hire, or when interviewers disagree and the manager has to call it. Produces the evidence state per competency, the four-way decision with probabilities, the act-or-hold verdict, and when holding, the exact competency to test and who tests it. Decision support for a human decision — a person owns the hire."4version: 1.0.05disable-model-invocation: true # skill-optimizer6metadata:7 source: https://skillmd.com/skills/slipcast-dev/hire-or-pass8---910# Hire or Pass1112Debriefs go wrong when the loudest interviewer wins or when everyone waits to see what the manager thinks. This skill forces the evidence into a fixed shape — per competency, strongest example and strongest counter-example, from whom — and defines the four possible outcomes before the discussion starts. The output is a distribution over those outcomes and, when it is close, the *specific* extra signal to go get.1314**Boundary.** This is decision support. A person makes and owns the hiring decision, applies the company's process and the law where they are, and is accountable for it. Never let a distribution replace that.1516## Where this sits1718After [`hiring-rubric`](../hiring-rubric/SKILL.md) (which defines the competencies) and [`engineering-hiring-rubric`](../engineering-hiring-rubric/SKILL.md), and after the interviews. This one runs the debrief decision.1920## What This Skill Produces2122- **The evidence state** — per must-have competency: strongest example, strongest counter-example, which interviewer saw it, rubric scores23- **The decision** — `hire` / `hire_at_different_level` / `more_signal` / `pass` with probabilities and confidence24- **Act or hold** — thresholds applied; a close hire/pass is a `more_signal` by definition25- **The signal plan** — when holding: the competency to test, the format, who runs it, by when26- **The debrief record** — one paragraph for the file: evidence summary, decision, who decided2728## Required Inputs2930Ask for these; do not infer from "vibes" or an interviewer's overall thumbs:31- **role** — title, level, the 3–5 must-have competencies from the rubric32- **evidence** — per competency: strongest observed example and strongest counter-example, with the interviewer who saw it33- **scores** — rubric scores per interviewer per competency34- **references** — if taken: confirmed or contradicted what35- **risks** — gaps, level mismatch, red flags *with the evidence behind them*36- **process** — any missed interviews or untested competencies3738## Framework: Four Defined Outcomes3940| Option | It applies when |41|---|---|42| `hire` | Every must-have competency has positive evidence from at least two interviewers, and no red flag has evidence behind it |43| `hire_at_different_level` | The evidence supports the competencies at a different level than the role was opened at |44| `more_signal` | A must-have was untested, or the evidence is split between interviewers — one targeted extra conversation decides it |45| `pass` | A must-have competency has negative evidence, or a red flag is substantiated |4647**Thresholds.** Act when confidence ≥ 0.65 and the winning option's probability ≥ 0.7. A close `hire` / `pass` **is** a `more_signal` outcome: name the competency and who tests it. Never decide on the distribution alone.4849**Evidence, not impressions.** "Strong communicator" is an impression. "Explained the outage timeline to a non-engineer in the panel without being asked — seen by R." is evidence. Only evidence enters the state.5051**Getting probabilities.** Any calibrated decision model that returns a probability per defined option serves this contract; the repo ships an adapter (`node integrations/jev/decide.mjs hire-or-pass --state state.json`, contract in `integrations/jev/decisions/`). Without one, the assistant estimates and labels it. Either way the decision is the hiring manager's.5253## Output Format5455### Debrief decision: [role, level] · candidate [initials]5657**Evidence by competency**58| Competency | Strongest example (who) | Strongest counter (who) | Scores |59|---|---|---|---|60| … | … | … | … |6162**Decision**63| Option | Probability |64|---|---|65| hire | 0.xx |66| hire_at_different_level | 0.xx |67| more_signal | 0.xx |68| pass | 0.xx |6970Confidence: 0.xx · Source: [model / estimate]7172**Verdict:** **[act: option]** or **[hold → more_signal: competency, format, owner, by when]**73**Debrief record:** [one paragraph — evidence summary, the decision, who made it]7475## Quality Checks76- [ ] Every must-have has an evidence row; untested ones are marked and force `more_signal`77- [ ] Counter-examples are recorded, not just the good moments78- [ ] Red flags are listed with evidence or dropped79- [ ] All four probabilities shown; the verdict cites the thresholds80- [ ] The record names the human who decided81- [ ] Nothing in the state is a protected characteristic or a proxy for one8283## Anti-Patterns84- **Overall thumbs** replacing per-competency evidence85- **Anchoring on the manager** — collect scores before anyone speaks86- **"Culture fit"** as an undefined competency87- **Deciding a coin flip** — 0.5 / 0.5 hire/pass is a `more_signal`, always88- **Letting the model hire** — it produces evidence about evidence; a person decides8990## Example Trigger Phrases91- "Run the debrief — three interviewers, split panel."92- "Hire or pass on this candidate? Here are the scorecards."93- "We're at hire vs. pass 50/50 — what do we do?"