Interview ScorecardSAFE

An agent skill published by revfactory.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: interview-scorecard
description: "structure interview design and evaluation form framework. interview-designer agent interview process designand assessment standard tablelevelto do when reference. 'interview design', 'evaluation form', 'structure interview' request when usage. However, interview actualwhen pass scope outside."
---

# Interview Scorecard — structure interview design

interview-designer agent interview process design competency .

## structure interview principle

### structure vs structure

| item | structure | structure |
|------|---------|--------|
| question | interviewer specialist | companybefore design |
| assessment | /person | scorecard |
| example also | 0.2~0.4 | 0.5~0.7 |
| legal risk | High | Low |
| interviewer | High | minimization |

### interview typeby purpose

| type | purpose | time | competency assessment |
|------|------|------|----------|
| action interview (BEI) | action based competency | 45~60minute | skill |
| technical interview | technicalquality competency | 60~90minute | skill |
| interview | problem capability | 45~60minute | analysis/ |
| document interview | qualitynature | 30~45minute | value/ also |
| presentation | communication | 30~45minute | presentation/persuasion |

## BEI (Behavioral Event Interview) question design

### STAR question official

```
S (Situation): situation question → specific context
T (Task): task → person role
A (Action): action → specificas 
R (Result): result → quality performance, 

question pattern:
"[competency] needed specificperson basis weektax.
 when situation , role,
 specificas action , result ?"
```

### competencyby question (examplewhen)

| competency | question | afterwithin question |
|------|------|----------|
| problem | " technicalquality problem Korean ?" | "versusplan ?", " method optional?" |
| | "teamKRW and ?" | " ?", "result?" |
| leadership | "team goal natureKorean ?" | " ?", "teamKRW ?" |
| learning | " technical ?" | " learning?", " ?" |

## assessment scorecard design

### 4point also (recommendation)

| score | etc.grade | standard |
|------|------|------|
| 4 | month (Strong Hire) | expected exceeding, i.e.when |
| 3 | quality (Hire) | expected , planquality perform |
| 2 | insufficient (Lean No) | departmentminute , risk re- |
| 1 | un- (No Hire) | standard un- |

### scorecard template

```markdown
# interview evaluation form

- candidate: _________ | job: _________
- interviewer: _________ | daywhen: _________

## competencyby assessment

| competency | question | answer summary | score(1~4) |
|------|------|----------|-----------|
| [competency 1] | [question] | [core content] |  |
| [competency 2] | [question] | [core content] |  |
| [competency 3] | [question] | [core content] |  |

## comprehensive assessment
- totalpoint: __ / __ (pyeongbalanced: __.__)
- comprehensive : □ Strong Hire □ Hire □ Lean No □ No Hire
- strength: 
- matters: 
- matters: 

frompeople: _________ daywhen: _________
```

## interviewer degree

### key and response

| | description | response |
|------|------|------|
| after and | person | competencyby assessment |
| companynature | and Korean company | Korean interviewer |
| | judgment confirm only | STAR question |
| nature | degree afterreport basis00M | i.e.when score basisrecord |
| versus/ | score | examplewhen provide |

### interviewer guideperson

```
DO:
- all afterreportto day question
- answer during (after score)
- STAR afterwithin questionas identify
- (10 versusbasis)

DON'T:
- also question ("annual X when?")
- itemspersonquality question (, , value)
- interview during pass/fail grade
- afterreport and comparison grade
```

## hiring pipeline beforeexchange value

| stage | beforeexchange | calculation |
|------|--------|------|
| degreeKRW → from and | 20~30% | 100people → 25people |
| from → 1gap interview | 40~60% | 25people → 12people |
| 1gap → 2gap interview | 40~60% | 12people → 6people |
| 2gap → final interview | 50~70% | 6people → 3people |
| final → offer | 60~80% | 3people → 2people |
| offer → number | 70~90% | 2people → 1.5people |

## quality checklist

| item | standard |
|------|------|
| structure | question companybefore design, day applied |
| STAR | all BEI question STAR structure |
| scorecard | 4point , examplewhen |
| degree | interviewer guide deployment |
| afterwithin question | competency 2~3items preparation |
| basisrecord | i.e.when basisrecord, 24time within |

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.