interview-coach – skill Viết lách & Nội dung cho agent AI

Interview Coach

Overview

A persistent, adaptive coaching system for the full job search lifecycle.

Not a question bank — an opinionated system that tracks your patterns,

scores your answers, and gets sharper the more you use it. Persist state to coaching_state.md only when requested, in an authorized private location; retain verified facts and user-approved examples. The host may not recover it automatically.

Package availability

This AAS entry contains the guide, not the 23-command implementation. /coach is an external package/host convention; discover actual availability before claiming it ran. Basic coaching can proceed directly with supplied role, CV and examples. Verify current company process/salary sources and dates; never invent achievements, hiring steps or ATS scores. Avoid unnecessary transcript identifiers and ask before third-party uploads.

Direct coaching workflow

Without the optional command package, start with the supplied job description, CV and target interview. Extract five role requirements and map each to a verified example or a stated gap. Ask one behavioral question at a time; after the answer, assess relevance, concrete evidence, personal contribution, structure and reflection using a stated rubric. Draft a STAR revision using only supplied facts, then repeat the weakest portion as a drill. Return a short preparation plan and unresolved research questions. Coaching scores reflect that rubric, not an employer’s actual assessment or an ATS prediction.

Install

# Review an immutable upstream revision/license, then install only into the explicitly authorized workspace/host path.

Then type /coach → kickoff.

When to Use This Skill

• Use when starting a job search and need a structured system
• Use when preparing for a specific interview (company research, mock, hype)
• Use when you want to analyze a past interview transcript
• Use when negotiating an offer or handling comp questions on recruiter screens
• Use when building or maintaining a storybank of interview-ready stories

What It Covers

• JD decoding — six lenses, fit verdict, recruiter questions to ask
• Resume + LinkedIn — ATS audit, bullet rewrites, platform-native optimization
• Mock interviews — behavioral, system design, case, panel, technical formats
• Transcript analysis — paste from Otter/Zoom/Grain, auto-detected format
• Storybank — STAR stories with earned secrets, retrieval drills, portfolio optimization
• Comp + negotiation — pre-offer scripting, offer analysis, exact negotiation scripts
• Upstream advertises 23 commands across the full search lifecycle; not bundled here

Examples

Example 1: Start your job search

/coach
kickoff

The coach asks for your resume, target role, and timeline — then builds

your profile and gives you a prioritized action plan.

Example 2: Prep for a specific company

/coach
prep Stripe Senior PM

Runs company research, generates a role-specific prep brief, and queues

up mock interview questions tailored to Stripe's process.

Example 3: Analyze an interview transcript

/coach
analyze

Paste a raw transcript from Otter, Zoom, or any tool. The coach

auto-detects the format, scores each answer across five dimensions,

and gives you a drill plan targeting your specific gaps.

Example 4: Handle a comp question

/coach
salary

Coaches you through the recruiter screen "what are your salary

expectations?" moment with a defensible range and exact scripts.

Source

https://github.com/dbhat93/job-search-os

Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.