yanliudesign/offer-toolkit-skill / bq-skill
bq-skill
Verified行为面试 skill。帮求职者挖掘真实经历、用 STAR/CAR 结构化、映射能力标签、构建可复用的中英双语故事库(Story Bank);并能接入 JD + 简历,针对具体岗位生成 Top 20 BQ 选题 + 基于真实经历的 STAR 准备模板(HTML 报告)。不是背答案,而是建立可复用的职业叙事体系,让任何行为面试题都能自然作答。关键词:behavioral question, BQ, 行为面试, STAR, 故事库, Amazon LP, 职业故事, tell me about a time, 面试准备, JD 面试题预测, top 20 题。
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 19 B |
| README.md | markdown | 6.1 KB |
| README.zh.md | markdown | 5.0 KB |
| SKILL.md | skill md | 7.0 KB |
| assets/bq-prep-report.md | markdown | 3.9 KB |
| assets/demo-report.html | other | 34.6 KB |
| assets/en/.gitkeep | other | 119 B |
| assets/preview.png | binary | 200.3 KB |
| assets/zh/.gitkeep | other | 103 B |
| frameworks/company-profiles.md | markdown | 2.5 KB |
| frameworks/competency-tags.md | markdown | 2.3 KB |
| frameworks/star-car.md | markdown | 1.9 KB |
| prompts/jd-driven-prep.md | markdown | 6.1 KB |
| prompts/story-mining.md | markdown | 6.7 KB |
| prompts/structuring.md | markdown | 1.5 KB |
| story-bank/_index.md | markdown | 870 B |
| story-bank/_story-template.md | markdown | 1005 B |
| story-bank/convince-team-rewrite.md | markdown | 2.2 KB |
README.md
View on GitHub<div align="center">
[中文](./README.zh.md) · **English**
# 💭 BQ Skill
---
**Turn real experience into a reusable behavioral interview story bank.**
[](../LICENSE)
[]()
[]()
[]()
[]()
[]()
[](https://github.com/yanliudesign/Behavior-question-skill/stargazers)
[](https://claude.ai/code)
[]()
[]()
[]()
[]()
</div>
> 📦 Part of the **[offer-toolkit-skill](https://github.com/yanliudesign/offer-toolkit-skill)** — the full job-hunt bundle (Search · JD · Resume · BQ · Compare · Negotiate). Install the bundle to get all six in one shot.
A Claude skill for behavioral interview prep. Instead of handing you canned answers, it helps you dig your real past experiences out and organize them into a story bank you can reuse. It asks about your experience step by step, uses STAR/CAR to shape each story, tags them ("took ownership", "handled ambiguity", etc.), and saves each one in English and Chinese — so next time you get a different behavioral question, the same story still works.

<sub>JD-driven prep output: a Top 20 question set reverse-engineered from a JD, with STAR templates and editable model answers. <i>(Demo uses a fictional candidate — no real personal data.)</i></sub>
<sub>More screenshots: [English gallery](assets/en/) · [中文相册](assets/zh/)</sub>
## Layout
```
bq-skill/
├── SKILL.md # Entry point: intent routing + five flows
├── prompts/
│ ├── story-mining.md # ★ Four-layer probing engine (story mining)
│ ├── structuring.md # Diagnose + rewrite an existing answer (polishing)
│ └── jd-driven-prep.md # ★ JD × resume → Top 20 questions + STAR templates (JD-driven prep)
├── frameworks/
│ ├── star-car.md # STAR/CAR/SOAR selection + one story, many questions
│ ├── competency-tags.md # Competency dictionary + BQ reverse-lookup
│ └── company-profiles.md # Amazon LP / Meta / Anthropic / OpenAI styles
├── assets/
│ └── bq-prep-report.md # Editorial HTML report spec for JD-driven prep
└── story-bank/ # User asset — one .md per story
├── _index.md # Competency → story reverse-lookup table
├── _story-template.md # Story template
└── convince-team-rewrite.md # Example story (safe to delete)
```
## What it can do
- **Mine a new story** — pulls real, quantifiable events out of someone who thinks *"I have nothing to talk about,"* then deepens one into a bank-ready story.
- **Answer a specific BQ** — check the bank first, reuse a hit, or mine a new one on the spot.
- **Polish an existing answer** — diagnose structure problems (Situation too long, "I" vs "we", no quantified result) and rewrite.
- **Mock interview** — one question at a time in the target company's style, with feedback.
- **JD-driven prep** — reads a JD + your resume, reverse-engineers a Top 20 interview-question set for that role, and builds a STAR prep template for each question. (See next.)
## Hooks into job-description-skill
JD-driven prep reuses the **Must-Haves + Hidden Signals** decoded by
[job-description-skill](https://github.com/yanliudesign/job-description-skill) to reverse-engineer a
**Top 20 interview-question set** for one specific role, builds a STAR prep template per question
from your real resume, and outputs an HTML report.
## Usage
Tell Claude *"help me prep for behavioral interviews"*, *"mine a story for my bank"*,
*"here's a BQ, help me answer it"*, or just run `/bq-skill`.
## Principles
1. **Bank first.** Always check `story-bank/_index.md` before mining — reuse beats re-digging.
2. **One question at a time.** Mining is a conversation, not a questionnaire.
3. **Never fabricate.** All material comes from the user's real experience; every metric is verified with them.
## Making it your own
The probing scripts in `prompts/story-mining.md` and the competency dictionary in
`frameworks/competency-tags.md` are where to inject your own phrasing and vocabulary — the more you
put in, the more the skill sounds like you.
## Related skills
- [offer-toolkit-skill](https://github.com/yanliudesign/offer-toolkit-skill) — the all-in-one bundle (Search · JD · Resume · BQ · Compare · Negotiate)
- [job-hunt-skill](https://github.com/yanliudesign/job-hunt-skill) — Job discovery and searchable opportunity list
- [job-description-skill](https://github.com/yanliudesign/job-description-skill) — Job Description Decoder
- [resume-builder-skill](https://github.com/yanliudesign/resume-builder-skill) — Resume generation & beautification
## License
MIT — fork it, remix it, ship your own version.
Created by [Dreameryanyan](https://www.linkedin.com/in/yanliudesign/) ·
[LinkedIn](https://www.linkedin.com/in/yanliudesign/) ·
[X](https://x.com/yanliudreamer) ·
[Xiaohongshu](https://www.xiaohongshu.com/notification)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |