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。
npx skills add https://github.com/yanliudesign/offer-toolkit-skill --skill bq-skill
把"会回答某道 BQ"升级成"拥有一套可复用的职业故事库"。核心循环:
挖掘 (Mine) → 结构化 (Structure) → 打标 (Map) → 存库 (Save) → 复用 (Reuse)
第一原则:先查库,再开工。 任何 BQ 进来,先看 story-bank/_index.md 有没有能命中的故事;能复用就复用/微调,不能再触发新一轮挖掘。这就是"越用越懂用户"。
第二原则:一次只问一个问题。 挖掘是对话,不是问卷。问一个 → 等回答 → 顺着答案追问。永远不要一次抛一串问题。
第三原则:不替用户编故事。 所有素材必须来自用户真实经历。可以引导、可以追问、可以帮他把模糊的说清楚,但绝不杜撰 Task / Action / Result。量化数字一律向用户求证。
| 用户说的话 | 走哪条流程 |
|---|---|
| "帮我准备面试" / "我要建故事库" / 给一段经历 | 挖掘新故事 → prompts/story-mining.md |
| 贴出一道具体 BQ("Tell me about a time…") | 回答一道题(先查库,下方流程) |
| "我这个故事讲得好吗" / 贴出已有答案 | 打磨已有故事 → prompts/structuring.md |
| "模拟面试" / "出几道题考我" | 模拟面试(v1 轻量版,下方) |
| 给了 JD + 简历 / "针对这个岗位帮我准备 BQ" / "这家会问什么、我怎么答" | JD 驱动的 BQ 选题 + 准备 → prompts/jd-driven-prep.md |
| "看看我的故事库" / "我有哪些故事" | 读 story-bank/_index.md 汇报 |
判断不了就问一句:"你是想挖新故事建库,还是针对某道具体题目准备?"
完整执行 prompts/story-mining.md 里的四层追问引擎:
frameworks/competency-tags.md)+ 判断能打哪些公司维度(frameworks/company-profiles.md)。story-bank/_story-template.md 写成一个故事文件,并更新 _index.md。一次会话聚焦挖 挖透 1 个完整故事就够了,挖深比挖多重要。挖完问用户要不要继续下一个。
frameworks/competency-tags.md 反查)story-bank/_index.md,找 tags / competencies 命中的故事。frameworks/star-car.md)。执行 prompts/structuring.md:诊断用户现有答案的结构问题(常见:Situation 太长、看不出"我"做了什么、没有量化 Result、能力标签不清晰),给出改写。改完可存库。
frameworks/company-profiles.md 对应风格。针对某个具体岗位做定向 BQ 准备。完整执行 prompts/jd-driven-prep.md,五步流程:
① 上传 JD → ② 上传简历 → ③ 生成 Top 20 选题(对着 JD)→ ④ 基于你的经历给 STAR 准备模板 → ⑤ 输出 HTML 报告
../job-description-skill/jd-bank/ 里已解码的 Must Have + Hidden Signals;没有就让用户贴 JD,先过一遍解码。~/Desktop/Claude skills/bq-prep-<company>-<role>-<YYYYMM>.html(视觉规范见 assets/bq-prep-report.md)。> 这是 job-description-skill 面试预测流程的下游深化:那边给「会问什么」,这里给「用你的真实经历怎么答 + 模板」。
story-bank/,每个故事一个 .md。_index.md 是反查表:能力标签 → 故事文件,是「答题」 复用的入口。_index.md。prompts/story-mining.md — 四层追问引擎(「挖新故事」 核心)prompts/structuring.md — 结构化诊断与改写(「打磨已有故事」)prompts/jd-driven-prep.md — JD × 简历 → Top 20 选题 + 准备模板(「JD 驱动准备」,挂钩 job-description-skill)assets/bq-prep-report.md — 「JD 驱动准备」 的 HTML 报告视觉规范frameworks/star-car.md — STAR / CAR / SOAR 何时用哪个、同一故事多角度复用frameworks/competency-tags.md — 能力标签词典 + BQ 题型反查frameworks/company-profiles.md — Amazon LP / Meta / Anthropic / OpenAI 等评价风格story-bank/_story-template.md — 故事文件模板story-bank/_index.md — 故事索引Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Take yanliudesign/bq-skill from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.