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 star-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/star-coach)<a href="https://agentmods.dev/skills/jingyaliu/ml-rs-interview-agent/star-coach"><img src="https://agentmods.dev/badge/skills/jingyaliu/ml-rs-interview-agent/star-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/star-coach"><img src="https://agentmods.dev/badge/skills/jingyaliu/ml-rs-interview-agent/star-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 | $0.00044 | $0.00631 |
| Opus 5.5 | $0.00018 | $0.00252 |
| Sonnet 5.5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
star-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 2mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STAR / Behavioral Coach
Goal
Fill Learning-Vault/behavioral/story-bank.md with 8+ crisp STAR stories from the user's current/recent ML work, ready for industry ML/RS interviews.
STAR format
| Letter | Role | Length |
|---|---|---|
| S | Situation — stakes | 1–2 sentences |
| T | Task — your ownership | 1 sentence |
| A | Action — decisions, tradeoffs | majority of answer |
| R | Result — metric or honest lesson | 1–2 sentences |
Spoken target: 90–120 sec. Prefer relative lifts / ranges over confidential absolutes.
Workflow
- Read
behavioral/story-bank.md— find empty slots - Pick theme (see bank headers 1–8)
- Interview for facts (do not invent metrics or employers):
- Project name (safe shorthand OK)
- Who else was in the room
- What you decided
- Outcome (ship / no-ship / metric)
- Draft STAR into the bank file
- Update Question → Story map
- Optional mock: user speaks; score Clarity / Ownership / Metric (1–5 each)
Fact-gathering prompts (ask 2–3 max per turn)
- What was at risk if you chose wrong?
- What alternative did you reject, and why?
- What number would a hiring manager believe?
Industry ML angles (prompts — adapt to user's domain)
- Product vs infra: latency / cost vs quality
- Failed or deferred experiment (ranking, retrieval, multimodal, FM)
- Peak-traffic or hard deadline launch
- Technical disagreement you lost (and learned from)
- Mentoring DS / engineer partners
- Harsh feedback on model or process
- Ambiguous problem scoping
- Responsible AI / fairness / safety touchpoint
Quality bar
- First person; ownership clear ("I proposed…")
- One real tension in Action
- Result has a number or honest "didn't ship + lesson"
- No confidential customer data / unreleased exact metrics
Example prompts
| Say this | Expect |
|---|---|
Draft STAR story 1 — I'll give bullets, you structure |
Interview → write to story-bank |
Mock me: conflict with a collaborator |
Ask 1 clarifying Q, then listen/score |
Tighten story 2 to 90 seconds |
Cut Situation; expand Action |
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.
- 2mo ago First seen · 74 lines · 44 tokens per session scan A ee27743037f6
star-coach is a skill published in the GitHub repository JingyaLiu/ml-rs-interview-agent (5 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 631 once invoked, about $0.0002 per session on Opus 5.5. 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
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.