interview-coach

interview-coach is a skill for Claude Code, Codex from Remotivated/job-hunt-skills. It costs 32 tokens per session (1,548 once invoked), scanned A, original, MIT.

An interview-preparation workflow for a specific role at a specific company. It creates a prep brief using the user's experience and keeps a reusable bank of STAR+R stories, meaning structured examples of situations, actions, results, and reflection.

In plain words
What is it for?
Use it to prepare likely questions, talking points, questions for the employer, and an honest review of weaknesses.
Why use it?
It turns an interview invitation into focused preparation based on real experience rather than generic questions.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **State layer:** selects either `resume.md` or `cv.md` as the source work document, reads `applications.md`, reads and appends to `story-bank.md`, writes an int.

Part of the job-hunt-skills plugin — 11 skills shipped together

Good fit Use it to prepare likely questions, talking points, questions for the employer, and an honest review of weaknesses.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Remotivated/job-hunt-skills
agentmods
npx agentmods add skills/remotivated/job-hunt-skills/interview-coach

Made for: Claude Code, Codex.

Or install job-hunt-skills, the plugin that ships this one along with the rest of its 11 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for interview-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/remotivated/job-hunt-skills/interview-coach/github.svg)](https://agentmods.dev/skills/remotivated/job-hunt-skills/interview-coach)
Your own site
<a href="https://agentmods.dev/skills/remotivated/job-hunt-skills/interview-coach"><img src="https://agentmods.dev/badge/skills/remotivated/job-hunt-skills/interview-coach/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for interview-coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/remotivated/job-hunt-skills/interview-coach"><img src="https://agentmods.dev/badge/skills/remotivated/job-hunt-skills/interview-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,548 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01548
Opus 5 $0.00016 $0.00774
Sonnet 5 $0.00006 $0.00310
Haiku 4.5 $0.00003 $0.00155

Measured 11d ago against content hash 61d4f02e754a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

interview-coach scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/interview-coach/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Generate an interview prep brief with likely questions, talking points from the user's actual experience, evaluative questions to ask the company, and honest assessment of weaknesses. Reuse and grow the persistent STAR+R story bank so every prep session compounds instead of starting from zero.

For interview process tracking, post-interview notes, and follow-up drafts, use interviewing. This skill focuses on prep quality.

Workflow

State layer: selects either resume.md or cv.md as the source work document, reads applications.md, reads and appends to story-bank.md, writes an interview prep artifact, and writes a numbered report. See state-layer contract.

0. Scaffold, tracker check, and source selection

Run node "{job_hunt_skills_root}/scripts/scaffold-state.mjs" if the state layer is missing.

Read my-documents/applications.md. If no row exists for this company + role, warn but do not block:

I don't see a tracked application for {Role} at {Company}. Interview prep still works. Want me to create a tracker row with status: interviewing, or skip the tracker?

If the user confirms tracker creation, insert a new row with status: interviewing. This is allowed by state-layer section 4 because interviews can predate the tracker.

If a row exists at saved or applied, ask whether to advance it to interviewing. Only advance after user confirmation.

Select the source work document using state-layer section 6. If both resume.md and cv.md exist and the user did not imply which one maps to the interview, ask. Use the selected file's label in user-facing prose.

1. Gather inputs

  • Company name: required.
  • Role title: required.
  • Job posting: URL or pasted text. If unavailable, ask what the user knows about the requirements and interview loop.
  • Interview details: stage, date/time if known, format, interviewer names or functions, expected topics, and anything the recruiter mentioned.
  • Source work document: selected resume.md or cv.md.

Read the full file on GitHub · 127 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 127 lines · 32 tokens per session scan A 61d4f02e754a

Subscribe to this mod's changes

interview-coach is a skill published in the GitHub repository Remotivated/job-hunt-skills (9 stars, last pushed 19d ago), licensed MIT. It adds 32 tokens to every session and 1,548 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

principal-agent

A Chinese-language guide based on the principal-agent idea: the person who owns a decision or its result may have different incentives from someone acting on another person's behalf. It applies this lens to jobs, companies, and partnerships.

kangarooking/cangjie-skill · 134 tokens

cv-resume-builder

Optimize resumes and CVs for impact, ATS compatibility, and audience targeting. Supports multiple formats (chronological, functional, hybrid), accomplishment framing (STAR/XYZ), and tailoring for specific roles. Triggers on resume review, CV update, job application prep, or career document requests.

organvm-iv-taxis/a-i--skills · 62 tokens

mock-interviewer

Run a realistic, pressure-tested mock interview for a specific role, one question at a time, with honest feedback at the end. Use when the user wants interview practice, a mock interview, or to rehearse answers for an upcoming interview.

squerne/open-career-skills · 52 tokens

mock-interview-coach

Practice mock interviews with AI coaching — build STAR stories, rehearse behavioral answers, craft "tell me about yourself" scripts, and prep references.

art2url/career-agent-skills · 34 tokens

spiritual

A Buddhist-inspired AI coach for spiritual reflection, meditation guidance, and questions about the nature of the mind.

joyozhang333-lgtm/sage-coach · 21 tokens

career

An AI coach for people who feel stuck in their career or are considering a career change. It guides conversations about work, personal strengths, values, possible directions, and practical experiments.

joyozhang333-lgtm/sage-coach · 16 tokens