Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/xujingchen1996/research-app-toolkit/interview-prepnpx skills add xujingchen1996/research-app-toolkit --skill interview-prepgit clone --depth 1 https://github.com/xujingchen1996/research-app-toolkitWrote 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/xujingchen1996/research-app-toolkit/interview-prep)<a href="https://agentmods.dev/skills/xujingchen1996/research-app-toolkit/interview-prep"><img src="https://agentmods.dev/badge/skills/xujingchen1996/research-app-toolkit/interview-prep.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.00473 |
| Opus 5 | $0.00029 | $0.00236 |
| Sonnet 5 | $0.00012 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
interview-prep 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Preparation
Preconditions
- Read
../../memory.mdfirst. - If the application profile is missing, first suggest that the user run
cv-analyze, because question design depends on the user's experience.
Language Rules
- Support three output modes:
zh,en, andbilingual. - If the user explicitly specifies the interview language, prioritize the current request.
- Otherwise read
preferred_languagefrommemory.md. - If it is still unclear, prioritize preparing in the interview language most likely used by the target program or professor.
- If the user requests bilingual output, default to outputting questions in the target interview language and supplementing them with Chinese or English answering tips, rather than bilingually repeating the entire question set.
Clarify the Interview Target First
If any of the following is missing, ask follow-up questions:
- professor name
- school / program
- interview language
- whether they would rather practice a full mock interview or only want a question bank and reference answers
Preparation Workflow
- Search the target professor and program:
- professor homepage and recent work
- interview format of the program or public experience reports
- Generate a question set based on the user's background, covering at least:
- research background
- technical deep-dive
- motivation and long-term goals
- behavioral questions
- project deep-dive
- If the user wants a mock interview:
- give only one question at a time
- wait for the user's answer before commenting
Output Requirements
- If the user only wants a question bank:
- provide categorized questions
- provide answering advice for each category
- If the user wants a simulation:
- proceed one question at a time
- each round of feedback should include strengths, problems, and optimization direction
Constraints
- For professor research and program process, prioritize current public information.
- Do not treat uncertain student experiences found online as official rules.
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.
- 4d ago First seen · 57 lines · 58 tokens per session scan A 74038f9f6a72
interview-prep is a skill published in the GitHub repository xujingchen1996/research-app-toolkit (113 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 473 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
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.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.