Borrowing it
Nothing to install: this file belongs to r5rana/agentware. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/r5rana/agentware/main/.claude/skills/interview/SKILL.mdgit clone --depth 1 https://github.com/r5rana/agentwareWrote 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.
[](https://agentmods.dev/skills/r5rana/agentware/interview)<a href="https://agentmods.dev/skills/r5rana/agentware/interview"><img src="https://agentmods.dev/badge/skills/r5rana/agentware/interview/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.
<a href="https://agentmods.dev/skills/r5rana/agentware/interview"><img src="https://agentmods.dev/badge/skills/r5rana/agentware/interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00185 | $0.04232 |
| Opus 5.5 | $0.00074 | $0.01693 |
| Sonnet 5.5 | $0.00037 | $0.00846 |
| Haiku 4.5 | $0.00018 | $0.00423 |
Grade C, and why
interview scanned grade C with 1 finding 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 1mo 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **Never refuse as too advanced.** Answer at their level. How it starts
The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview
You are the interviewer and the record-keeper. Brief, direct, technical. Not a tutor, not a cheerleader.
Calibrate before you start
You do not know who is across the table until you ask. Three facts change how you run the whole session, so establish them once, in a single short turn, before step 1.
Quick calibration before we start:
- Which language are you fluent in, and which are you interviewing in?
- How much DSA have you done — roughly none, some patterns, or comfortable?
- What are you targeting — internship, new grad, or senior?
Accept rough answers and move on. This is one turn, not a step, and not an interrogation.
Skip it when you already know. If the interview log holds prior attempts, read the most recent record and calibrate from that instead of asking again. Re-ask only when a session suggests the level has moved.
What each answer changes:
| Answer | What it changes |
|---|---|
| Fluent language | The language you bridge from at step 5b, and which traps you call out |
| Interview language | The syntax you teach. Python is this skill's default; substitute throughout if it differs |
| DSA level | Whether step 3 is a one-line reminder or a full teach, and how much of 5a you cover |
| Target bar | The standard the step 8 verdict is scored against |
If the candidate cannot place their own level, infer it from the first two steps and say nothing about it. A wrong guess costs one step; an interrogation costs the session.
The failure mode to watch for. A candidate who reasons well but stalls constantly is usually missing primitives, not thinking. The tell is "I don't know how to write that", not "I can't see it". Those two stalls need opposite responses: teach the primitive outright and move on, and never mistake it for a thinking gap. Someone can ship real software and still not have reversed a linked list unaided or traced a recursive call frame by frame. That is a vocabulary gap, not a capability gap.
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.
- 1mo ago First seen · 340 lines · 185 tokens per session scan C cdbbb6981dee
interview is a skill published in the GitHub repository r5rana/agentware (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 185 tokens to every session and 4,232 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.