interview-kit
Skill0 starsChanged 36 days agoMITView on GitHub
Prepare a structured interview plan with job-related questions, follow-up probes, evidence notes, and calibrated assessment guidance.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- Maudeunfledged834/startup-founder-skillstheir own version, first seen Oct 25, 2026
- brianshepardpss/structured-hiringtheir own version, first seen Oct 2, 2026
- shawnpang/startup-founder-skillstheir own version, first seen Mar 16, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- shawnpang/startup-founder-skills★ 331same name
- Maudeunfledged834/startup-founder-skills★ 8same name
- brianshepardpss/structured-hiring★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- candidate-outreachSkill
- candidate-presentationSkill
- candidate-screeningSkill
- hiring-scorecardSkill
- interview-invitationSkill
- job-intakeSkill
- recruitment-workflowSkill
- sourcing-strategySkill
- vitaeSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
Distinctive
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
- Distinctive: line 13
Use the approved brief and scorecard, interview stage and duration, interviewer roles, and evidence already gathered.
- Distinctive: line 19
Write a common core question for each selected criterion.
- Distinctive: line 20
Add neutral probes that separate personal contribution from team achievement.
- Distinctive: line 22
Ask interviewers to record independent assessments before the group debrief, then discuss evidence and disagreements.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Interview kit
Inputs
Use the approved brief and scorecard, interview stage and duration, interviewer roles, and evidence already gathered. Candidate-specific follow-ups should resolve job-related uncertainties, not introduce new selection criteria.
Procedure
- Choose which criteria this stage will assess. Avoid attempting to measure every capability in one short interview or asking each interviewer to repeat the same material.
- Allocate time to introductions, evidence questions, candidate questions, and next steps. Ensure the plan fits the actual duration.
- Write a common core question for each selected criterion. Ask for a specific situation, the candidate's own actions, reasoning, tradeoffs, and outcome.
- Add neutral probes that separate personal contribution from team achievement. Do not coach toward the expected answer or assume the CV proves a claim.
- Attach the agreed scorecard anchors and a notes template. Capture observations before ratings. Do not use a first impression to fill missing evidence.
- Ask interviewers to record independent assessments before the group debrief, then discuss evidence and disagreements. Keep the final decision with the authorized hiring team.
Output
Provide a timed agenda, interviewer ownership, core questions, optional candidate-specific probes, evidence fields, rating anchors, candidate questions, and next-step wording. Include an “insufficient evidence” outcome.
Example
Criterion: incident analysis. Question: “Tell me about a production incident you helped resolve. How did you decide what to investigate first?” Probes: “What did you personally do?”, “What alternatives did you rule out?”, “How did you know the fix worked?”, “What changed to prevent recurrence?” Notes should distinguish actions, rationale, and observed result. Do not equate confidence of delivery with technical ability.
Quality check
Tie every scored question to the job. Avoid questions about age, family plans, health, religion, nationality, or other protected traits. Route role-specific eligibility questions through the employer's approved process. Offer equivalent ways to demonstrate the same capability when an adjustment is requested; do not score the adjustment itself.
With Vitae
Use verified read tools for role and candidate context. If a live question-set creation tool supports the intended format, show the proposed set and use the server's approval process. Do not invent its schema or claim that writing a kit schedules an interview. Capturing actual interview responses is a separate authorized action.
Completion and handoff
The kit is ready when it fits the time, uses calibrated criteria, and makes evidence collection clear. After the interview, synthesize supplied notes without inventing missing answers; use candidate-presentation for a recruiter-reviewed summary.
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
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.

