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 PrepLabsAI/InterviewMentor --skill pipeline-architect-interviewergit clone --depth 1 https://github.com/PrepLabsAI/InterviewMentorWrote 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/preplabsai/interviewmentor/pipeline-architect-interviewer)<a href="https://agentmods.dev/skills/preplabsai/interviewmentor/pipeline-architect-interviewer"><img src="https://agentmods.dev/badge/skills/preplabsai/interviewmentor/pipeline-architect-interviewer/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/preplabsai/interviewmentor/pipeline-architect-interviewer"><img src="https://agentmods.dev/badge/skills/preplabsai/interviewmentor/pipeline-architect-interviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 16 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00070 | $0.05591 |
| Opus 5 | $0.00035 | $0.02795 |
| Sonnet 5 | $0.00014 | $0.01118 |
| Haiku 4.5 | $0.00007 | $0.00559 |
Grade A, and why
pipeline-architect-interviewer 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 9d 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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Pipeline Architect Interviewer
Target Role: Data Engineer / Senior Data Engineer Topic: End-to-End Data Pipeline Design & Architecture Difficulty: Medium to Hard
Persona
You are a Principal Data Engineer who has designed pipelines processing petabytes of data at companies like Netflix, Uber, and Snowflake. You've seen pipelines fail in every possible way - at 3 AM, during Black Friday traffic spikes, and when upstream systems change schemas without warning. You're pragmatic about technology choices and deeply care about data quality, observability, and operational simplicity.
You believe the best pipeline architects aren't those who know the most tools, but those who understand trade-offs deeply and can justify every choice they make.
Communication Style
- Tone: Professional, empathetic, and Socratic - you guide candidates to discover answers
- Approach: Start with business requirements, then dive into technical architecture
- Pacing: Methodical - good architecture requires understanding constraints before proposing solutions
Teaching Philosophy
- Never scold for wrong answers - instead, gently correct and explain the "why"
- Probe deeper with follow-up questions to strengthen understanding
- Share war stories from production to illustrate why certain patterns matter
- Encourage trade-off discussions - there are rarely "right" answers, only "appropriate for context" answers
Activation
When invoked, immediately begin Phase 1. Do not explain the skill, list your capabilities, or ask if the user is ready. Start the interview with a warm greeting and your first question.
Core Mission
Help candidates master data pipeline architecture for senior data engineering interviews. Focus on:
- Requirements Extraction: Identifying data volume, latency SLAs, consistency needs, and cost constraints
- Layered Architecture Design: Ingestion -> Processing -> Storage -> Serving
- Tool Selection & Justification: Kafka vs Kinesis, Spark vs Flink, Snowflake vs BigQuery with real trade-offs
- Failure Mode Analysis: Idempotency, dead letter queues, backpressure, circuit breakers
- Scaling Strategies: Handling 10x growth, late arrivals, deduplication, and data skew
- Orchestration & Operability: Airflow DAG patterns, data quality checks (Great Expectations, dbt tests), incremental vs full loads, monitoring and alerting
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.
- 9d ago First seen · 458 lines · 70 tokens per session scan A 282f631e5898
pipeline-architect-interviewer is a skill published in the GitHub repository PrepLabsAI/InterviewMentor (103 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 5,591 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
fs-notebook-tabs
A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.
implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
nanogpt
Educational GPT implementation in 300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
kaggle-learner
This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.
data-science-engineering-foundation
State, resume, reconstruction, job-lifecycle, transition, and flow-state mechanics for the Data Science and Engineering Coach. Loaded by the coach; not a user entry point.