interview-prep-kit
Skill0 starsChanged 3 months agoMITView on GitHub
Generate a written interview prep-kit document from the user's resume and a specific job posting — resume-to-JD gap mapping, a STAR story bank, a company/domain fluency cheat sheet, and questions to ask. Use when the user provides (or points to) a resume and a job posting and wants a prep document, distinct from running a live mock-interview.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- book-studySkill
- mock-interviewSkill
- quick-recapSkill
- quiz-flashcardsSkill
- spaced-reviewSkill
- train-topicSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 51
If the kit surfaces a real skill gap, suggest a matching train-topic session to close it before the interview, don't just note it and move …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Interview Prep Kit
Produces a durable written artifact, not a live roleplay — use mock-interview for the
interactive practice; this skill builds the reference doc that feeds it.
Inputs
- Resume: a file path the user provides, or pasted text. If neither is given, ask for one — don't fabricate work history. Never send resume content anywhere outside this project; it's processed locally into the kit doc only.
- Job posting: a URL (fetch it) or pasted text. If a
topics/interview-prep/<company-slug>/orTRAINING.mdcompany row already has notes, use them as background, but re-derive requirements from the actual posting, not memory.
Building the kit
Write to topics/interview-prep/<company-role-slug>-prep-kit.md:
- One-page summary (top of the doc) — role, company, the 3-4 things this interview loop will most likely probe, and the candidate's single strongest angle for this specific role. This is the part to skim right before the interview.
- Requirement-by-requirement mapping — take each requirement/responsibility from the posting and map it to specific resume evidence (a project, a metric, a line item). Where there's a genuine gap (skill/experience not on the resume), say so plainly and suggest how to address it honestly in conversation (a related transferable experience, or "I'd frame this as...") rather than inventing experience or hiding the gap.
- STAR story bank — 4-8 stories pulled from the resume, each with Situation/Task/Action/
Result filled in from what the user actually did (ask follow-up questions to fill gaps, don't
guess at outcomes/metrics). Tag each story with the competencies/values it demonstrates (e.g.
Amazon Leadership Principles, or the role's stated qualities) so it's easy to pick the right
story live in
mock-interview. - Company/domain fluency cheat sheet — product lineup, recent moves relevant to the role,
likely technical stack, and anything from
TRAINING.md's company-prep or platform-basics rows worth citing. Flag anything time-sensitive (funding, recent launches) as something to verify is still current closer to the actual interview. - Questions to ask — 4-6 real questions calibrated to this role/company, split between "shows genuine technical curiosity" and "surfaces something the candidate actually needs to know to evaluate the offer."
After building
- Note the kit's path in
TRAINING.md's "Company / role prep" row for this company (add one if missing). - Suggest running
mock-interviewnext using the story bank and gap list as live material, rather than starting a mock round cold. - If the kit surfaces a real skill gap, suggest a matching
train-topicsession to close it before the interview, don't just note it and move on.
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.

