interview-debrief

interview-debrief is a skill for Claude Code from palashjain95/jobhunter. It costs 75 tokens per session (1,092 once invoked), scanned A, original, MIT.

A post-interview review workflow that examines how an interview went and prepares a follow-up thank-you message.

In plain words
What is it for?
Use it after an interview to review your answers, identify improvements, understand possible next steps, and draft a personalized thank-you email.
Why use it?
It turns scattered memories or a meeting transcript into clear lessons, signals, and a tailored response.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is If you see unfamiliar `~~` placeholders, see [CONNECTORS.md](../../CONNECTORS.md)..

Part of the jobhunter plugin — 13 skills, 3 agents, 2 hooks, 7 MCP servers shipped together

Good fit Use it after an interview to review your answers, identify improvements, understand possible next steps, and draft a personalized thank-you email.

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/palashjain95/jobhunter
agentmods
npx agentmods add skills/palashjain95/jobhunter/interview-debrief

Made for: Claude Code.

Or install jobhunter, the plugin that ships this one along with the rest of its 13 skills, 3 agents, 2 hooks, 7 MCP servers.

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-debrief

README.md
[![agentmods](https://agentmods.dev/badge/skills/palashjain95/jobhunter/interview-debrief/github.svg)](https://agentmods.dev/skills/palashjain95/jobhunter/interview-debrief)
Your own site
<a href="https://agentmods.dev/skills/palashjain95/jobhunter/interview-debrief"><img src="https://agentmods.dev/badge/skills/palashjain95/jobhunter/interview-debrief/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-debrief

Your own site · 80×15
<a href="https://agentmods.dev/skills/palashjain95/jobhunter/interview-debrief"><img src="https://agentmods.dev/badge/skills/palashjain95/jobhunter/interview-debrief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,092 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 $0.00075 $0.01092
Opus 5 $0.00037 $0.00546
Sonnet 5 $0.00015 $0.00218
Haiku 4.5 $0.00007 $0.00109

Measured 8d ago against content hash e05cb2ae93c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

interview-debrief 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 8d 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.

.claude/skills/interview-debrief/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/interview-debrief

If you see unfamiliar ~~ placeholders, see CONNECTORS.md.

Usage

/interview-debrief <company name>
/interview-debrief I just finished my Google PM interview

One skill for everything after a formal interview: analyze performance, extract lessons, and draft the thank-you.

Inputs

Auto-detect from ~~transcription (if available)

Before asking the user anything, check if ~~transcription is connected. If yes: query recent meetings for interviews at the target company. If a transcript exists, pull it — this replaces most of the questions below. Tell the user: "I found your interview transcript. Let me analyze it."

Ask the user (if no transcript found)

Ask these one at a time. Wait for each answer before asking the next. After gathering context, briefly confirm what you heard before analyzing.

  1. "Which company and role was this for?"
  2. "What round? (phone screen, technical, HM, final)"
  3. "Who did you interview with? (name and role if known)"
  4. "What went well? What moment felt strongest?"
  5. "What stumbled? Any question that caught you off guard?"
  6. "Did they mention next steps or timeline?"

Also load

  • output/[company]/interview-prep.md — what was prepared
  • knowledge/stories/ — check if prepared stories were used effectively
  • knowledge/frameworks/writing-framework.md — for thank-you tone

Produce

1. Performance Analysis

  • Strong moments: what worked and why
  • Weak moments: what didn't land and why
  • Missed opportunities: stories or points you should have made

2. Signal Reading

  • What their questions reveal about their concerns
  • What their reactions suggest about your fit
  • Likelihood of advancing (be honest)

3. Gap Analysis

  • Questions you weren't prepared for → note for future prep
  • Stories that didn't land → refine or replace
  • Topics they probed deeply → they care about this

4. Next Round Prep

  • What to expect in the next stage
  • What to emphasize based on what resonated
  • What to address based on concerns

Read the full file on GitHub · 145 lines

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. 8d ago First seen · 145 lines · 75 tokens per session scan A e05cb2ae93c3

Subscribe to this mod's changes

interview-debrief is a skill published in the GitHub repository palashjain95/jobhunter (2 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 1,092 once invoked, about $0.0004 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

mix-compression

Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.

oliver-kriska/claude-elixir-phoenix · 48 tokens

quick

Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.

oliver-kriska/claude-elixir-phoenix · 31 tokens

phx-mix-compression

Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.

oliver-kriska/claude-elixir-phoenix · 51 tokens

i-have-adhd

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

ayghri/i-have-adhd · 62 tokens

phx-freeze

Apply an advisory edit scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.

oliver-kriska/claude-elixir-phoenix · 30 tokens

service-desk

Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…

cbrock84/headcount · 73 tokens