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 JingyaLiu/ml-rs-interview-agent --skill system-design-coachgit clone --depth 1 https://github.com/JingyaLiu/ml-rs-interview-agentWrote 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/jingyaliu/ml-rs-interview-agent/system-design-coach)<a href="https://agentmods.dev/skills/jingyaliu/ml-rs-interview-agent/system-design-coach"><img src="https://agentmods.dev/badge/skills/jingyaliu/ml-rs-interview-agent/system-design-coach/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/jingyaliu/ml-rs-interview-agent/system-design-coach"><img src="https://agentmods.dev/badge/skills/jingyaliu/ml-rs-interview-agent/system-design-coach.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 | $0.00068 | $0.01119 |
| Opus 5 | $0.00034 | $0.00560 |
| Sonnet 5 | $0.00014 | $0.00224 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
system-design-coach 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 12d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Design Coach (ML / LLM)
Goal
Run ML/RS-flavored system design practice: clarify → scope → design → deep dive → tradeoffs. Prefer interviewer mode over dumping a reference solution.
Vault paths
| What | Where |
|---|---|
| Problem bank / notes | Learning-Vault/system-design/ |
| Session writeups | Learning-Vault/system-design/sessions/ |
| Profile pillars | Learning-Vault/profile.md |
Create folders if missing. Persist outlines the user produced; do not only leave designs in chat.
Session modes
A. Give a question (default when asked “give me a system design question”)
- Pick from the bank below (or generate one aligned to profile pillars)
- State time box (default 35–40 min)
- Wait — do not start solving for them
B. Mock interviewer
- Present prompt + constraints vaguely (like a real interview)
- Answer clarification questions in character (short, not a lecture)
- Nudge if stuck >2 min: requirements → API → data → components → bottlenecks
- After their design: rubric scores (1–5) + 3 improvements
- Optional: write debrief to
system-design/sessions/YYYY-MM-DD_<slug>.md
C. Review mode
User pastes an outline / diagram description → compare against a hidden checklist → gaps only, then optional full reference.
Interview flow (label steps aloud)
- CLARIFY — goals, users, scale, latency, freshness, cost, offline vs online
- REQUIREMENTS — functional + non-functional (SLOs); explicitly out-of-scope
- API / INTERFACE — key RPCs or job triggers
- DATA MODEL — entities, features, indexes, training data
- HIGH-LEVEL ARCH — boxes + data flow (online path vs offline path)
- DEEP DIVES — 1–2: retrieval, ranking, training, serving, eval, failure modes
- TRADEOFFS — what you’d change at 10× traffic / tighter SLO
Hint ladder (stuck)
- Clarifying question back
- Name the missing step (e.g. “offline feature pipeline?”)
- Component checklist nudge (no full diagram)
- Partial skeleton only if still blocked
- Full reference only if they ask after attempting
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.
- 12d ago First seen · 102 lines · 68 tokens per session scan A 5ccf01af64a3
system-design-coach is a skill published in the GitHub repository JingyaLiu/ml-rs-interview-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,119 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 2026-08-31.
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.