# Star Coach

> Coaches ML behavioral interviews using STAR stories grounded in the user's real work. Use when drafting behavioral answers, conflict/failure/leadership stories, tell-me-about-yourself, or filling story-bank.md.

- **Type:** Skill
- **Install:** `agentstack add skill-jingyaliu-ml-rs-interview-agent-star-coach`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [JingyaLiu](https://agentstack.voostack.com/s/jingyaliu)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [JingyaLiu](https://github.com/JingyaLiu)
- **Source:** https://github.com/JingyaLiu/ml-rs-interview-agent/tree/main/.cursor/skills/star-coach

## Install

```sh
agentstack add skill-jingyaliu-ml-rs-interview-agent-star-coach
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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

1. Read `behavioral/story-bank.md` — find empty slots
2. Pick theme (see bank headers 1–8)
3. **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)
4. Draft STAR into the bank file
5. Update Question → Story map
6. 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 |

## Anti-patterns

- CV dump / "we" without "I"
- Lesson with no concrete Action
- Overlong Situation
- Inventing metrics, employers, or biography the user didn't provide

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [JingyaLiu](https://github.com/JingyaLiu)
- **Source:** [JingyaLiu/ml-rs-interview-agent](https://github.com/JingyaLiu/ml-rs-interview-agent)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-jingyaliu-ml-rs-interview-agent-star-coach
- Seller: https://agentstack.voostack.com/s/jingyaliu
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.