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 skills add zhiweio/resume-as-code --skill interview-preparationgit clone --depth 1 https://github.com/zhiweio/resume-as-codeWrote 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/zhiweio/resume-as-code/interview-preparation)<a href="https://agentmods.dev/skills/zhiweio/resume-as-code/interview-preparation"><img src="https://agentmods.dev/badge/skills/zhiweio/resume-as-code/interview-preparation.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 5.1 | $0.00098 | $0.01471 |
| Opus 5 | $0.00049 | $0.00736 |
| Sonnet 5 | $0.00020 | $0.00294 |
| Haiku 4.5 | $0.00010 | $0.00147 |
Grade A, and why
interview-preparation 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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Preparation
Produce a thorough, role-tailored interview preparation guide in Markdown. The guide covers risk profiling and assessment framework, personal pitch, project deep-dives (STAR), and three parallel interview-type sections — Deep-Probing Technical Q&A, Breadth Probe Questions, Behavioral & Cultural Fit — where every question carries quantifiable Scoring Points and a structured Reference Answer. Closes with reverse-interview questions.
When to trigger
Activate when the user has all three of the following and asks for interview prep:
- A Resume (YAML from
data/resumes/ordata/profiles/). - A JD Analysis (e.g.
data/.cache/<Timestamp>/job-analysis.yml). - A Company Business Analysis (e.g.
data/.cache/<Timestamp>/company-business-analysis.yml).
If any of the three is missing, ask the user to provide it (or to run the resume-generation skill first, which produces the latter two as side effects).
Inputs you must read
- The provided Resume YAML.
- The provided JD Analysis YAML (the
languagefield governs the output language; supported:en,zh-hans,zh-hant-hk,zh-hant-tw,es,fr,no). - The provided Company Business Analysis YAML.
Outputs you will produce
A single Markdown guide:
- Path:
data/interviews/{CandidateName}_{Company}_Interview_Guide.mdCandidateName— from Resumebasics.name.Company— from JD Analysiscompany.- Replace spaces with underscores
_.
Workflow
Generate the guide following the detailed prompt in references/interview-guide.md. Required sections:
- Technical Deep-Probing Reconnaissance — Cross-validate resume vs JD, identify gaps, contradictions, and "smokescreens." Generate a "One-Sentence Risk Assessment," "Top 3 Core Skepticisms," and a prioritized Assessment Framework table (
Assessment Area | Relevant Tech Points | Assessment Priority). Infer experience level (Junior / Mid / Senior / Lead / Manager) from the resume and adjust depth of all subsequent sections accordingly. - Best-Practices Research — For every high-priority assessment area, search authoritative sources (DeepWiki, Context7, Web Search, WebFetch) to gather current best practices, canonical patterns, and pitfalls. These findings anchor the Reference Answers and Scoring Points in sections 5–7, so the guide reflects what a strong practitioner would actually say, not generic textbook material.
- Personal Introduction Strategy — "Tell me about yourself" script tying business background, technical background, and alignment with the target JD and company. Reference the Risk Profile to frame strengths as counterpoints to identified skepticisms. For senior candidates (>5 years), explicitly cover Project Management, Leadership, and Strategic Thinking.
- Project Deep Dives — STAR analysis for every project on the resume, with both breadth (architecture) and depth (implementation) coverage.
- Deep-Probing Technical Q&A — 10–15 targeted questions (8–10 for Junior candidates), each with 2–3 follow-up questions, quantifiable Scoring Points, and a structured Reference Answer. ~80% anchored to resume tech stack / project experience / JD requirements. Questions progress from shallow (implementation) to deep (architecture). Categories: Specific Technical, Architecture/Design, Domain-Specific.
- Breadth Probe Questions — 3–5 questions targeting technologies the resume lists as "familiar with," "exposure to," or "knowledge of" that are NOT core JD requirements. Each question carries follow-ups, quantifiable Scoring Points, and a Reference Answer. These assess intellectual honesty, learning breadth, and transferable reasoning.
- Behavioral & Cultural Fit — 3–5 level-appropriate behavioral questions. Each carries a scenario, quantifiable Scoring Points, and a STAR-structured Reference Answer connecting to resume experiences. Where possible, frame scenarios around risks identified in the Reconnaissance phase.
- Questions to Ask (Reverse Interview) — 3 high-quality questions: Business-level, Team/Technical, Current Challenges.
What ships with it
2 files 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.
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.
- 7d ago First seen · 66 lines · 98 tokens per session scan A e2cfa8eaf481
interview-preparation is a skill published in the GitHub repository zhiweio/resume-as-code (89 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,471 once invoked, about $0.0005 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
us-program-research
This skill should be used when the user needs structured research and ranking of US academic programs (PhD, Master.
ai-mentor
An AI career mentor for improving CVs, preparing for interviews, planning a career, negotiating pay, and creating different CV versions.
cangjie-skill
A process for turning a book, course, podcast, interview, long video, or other long material into reusable instructions for an AI agent. It extracts methods and principles, checks them, and packages them as skills.
reading-metaskill
A reading and learning guide based on building a regular reading habit, choosing books, and understanding difficult subjects through original works and explanation.
life-meaning
A guide for reflecting on personal purpose, effort, suffering, and mortality when life feels empty or directionless.
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.