2.6k
GitHub Stars
6
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill openclaw/skills --skill interview-system-designer- _meta.json310 B
- hiring_calibrator.py60.6 KB
- loop_designer.py44.7 KB
- question_bank_generator.py51.3 KB
- README.md11.4 KB
- SKILL.md19.8 KB
Overview
This skill designs end-to-end interview systems, competency matrices, and calibrated hiring pipelines for role-specific hiring needs. It produces interview loops, question banks, scoring rubrics, and bias-detection reports to improve consistency and hiring quality. Use it to create standardized, level-appropriate processes that scale interviewer training and calibration.
How this skill works
The skill ingests role definitions (title, level, team, competency priorities) and outputs structured interview loops with rounds, time allocation, and scorecards. It generates competency-based question banks with rubrics and calibration examples, and analyzes interview data to detect bias, miscalibration, and score distribution issues. Outputs include interview templates, question sets, calibration reports, and interviewer coaching recommendations.
When to use it
- Design a role-specific interview loop for hiring at a given level
- Create competency matrices and standardized scorecards for a team
- Generate behavioral and technical question banks with scoring rubrics
- Analyze historical interview results to find bias or calibration gaps
- Run regular hiring-bar calibration and interviewer training sessions
Best practices
- Start with a clear role definition: responsibilities, success metrics, and top competencies
- Use structured interviews and standardized rubrics to reduce variance and bias
- Limit interview length and rounds to purposeful assessments tied to competencies
- Rotate interviewers and anonymize early-stage screens to prevent pattern bias
- Hold regular calibration sessions with sample answers to align scoring
- Track scoring distributions by interviewer and demographic to detect drift
Example use cases
- Design a 4-hour interview loop for a senior software engineer with system design, coding, leadership rounds
- Generate a behavioral and metrics-focused question bank for product managers with STAR-based rubrics
- Create hiring-bar calibration reports from six months of interview scores to identify over- and under-confident interviewers
- Build a competency matrix mapping levels to expected behaviors and scoring thresholds
- Produce interviewer training materials and anti-bias checklists for new interviewers
FAQ
Yes. It produces level-appropriate rounds, question difficulty, and scoring expectations for junior through staff+ roles.
What data is needed for calibration analysis?
Calibration works best with candidate scores, interviewer IDs, role/context tags, and optional demographic fields to identify scoring patterns and bias.