SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsbq-skill

bq-skill

General & other

View repository

Updated 10-16 08:43

About this skill

BQ Skill

Upgrade from "being able to answer a certain BQ" to "owning a reusable career story bank." Core loop:

挖掘 (Mine) → 结构化 (Structure) → 打标 (Map) → 存库 (Save) → 复用 (Reuse)

First principle: check the bank first, then start work. Whenever any BQ comes in, first look at story-bank/_index.md whether there is a story that can match; if it can be reused, reuse/tweak it, and if not, trigger a new round of digging. This is "the more it is used, the better it understands the user."

Second principle: ask only one question at a time. Digging is a conversation, not a questionnaire. Ask one question → wait for the answer → follow up based on the answer. Never throw out a string of questions all at once.

Third principle: do not make up stories for the user. All material must come from the user's real experiences. You can guide, follow up, and help them articulate vague things clearly, but never fabricate Task / Action / Result. Always verify quantified numbers with the user.

Routing: when the user comes in, first determine the intent

What the user says Which process to follow
"Help me prepare for an interview" / "I want to build a story bank" / providing an experience Dig new stories → prompts/story-mining.md
Posting a specific BQ ("Tell me about a time...") Answer one question(check the bank first, process below)
"Is my story told well?" / posting an existing answer Polish an existing story → prompts/structuring.md
"Mock interview" / "Give me a few questions to test me" Mock interview(v1 lightweight version, below)
Provided JD + resume / "help me prepare BQ for this role" / "what will this company ask, and how should I answer" JD-driven BQ selection + preparation → prompts/jd-driven-prep.md
"Look at my story bank" / "What stories do I have" Read story-bank/_index.md and report

If you cannot tell, just ask: "Do you want todig new stories and build the bank, orprepare for a specific question?"

Dig new stories

Fully execute prompts/story-mining.md the four-layer follow-up engine:

  1. Icebreaker layer — specifically for "I do not have any highlights." Use counterfactual questions + four-quadrant time anchor scanning to first fish out 3-5 candidate events.
  2. Deep-dig layer — for the selected events, complete STAR one by one, focusing on forcing out the most commonly missing T (what you specifically did, not the team) and R (quantified result)。
  3. Tagging layer — after digging, map competency tags (frameworks/competency-tags.md) + determine which company dimensions it can target (frameworks/company-profiles.md）。
  4. Save into the story bank — according to story-bank/_story-template.md write it as a story file, and update _index.md。

One session focuses on digging Digging through 1 complete storyis enough; depth matters more than quantity. After digging, ask the user whether to continue to the next one.

Answer a specific BQ

  1. Analyze the question: what competency is this question testing? (refer to frameworks/competency-tags.md for reverse lookup)
  2. Check the story bank: read story-bank/_index.md, and find stories where the tags / competencies match.
    • Match → pull out the story and reorganize the opening and closing from the angle of this question (the same story can answer multiple questions; for the framework, see frameworks/star-car.md）。
    • No match → switch to "Dig New Stories" and dig one out on the spot, then answer after digging.
  3. Produce the answer: default to bilingual Chinese and English — the English version is the one you can say directly in an interview, withChinese key pointsattached for review.
  4. Conveniently save it into the story bank: if it was newly dug on the spot, save it into the bank.

Polish existing stories

Run prompts/structuring.md: diagnose the structural problems in the user's existing answer (common ones: Situation is too long, can't see what "I" did, no quantified Result, competency tags are unclear), and give a rewrite. After rewriting, it can be saved to the bank.

Mock interview

  1. Ask for the target company/role, and load frameworks/company-profiles.md the corresponding style.
  2. Ask 1 question based on the dimensions the company commonly tests,one question at a time。
  3. after the user answers, give feedback: structure (whether STAR is complete), whether the competency signals are clear, whether quantification is in place, and fit with the company's dimensions.
  4. Prompt the user to save well-answered stories to the bank.

JD-driven BQ question selection + preparation

Targetinga specific roledo targeted BQ preparation. Fully run prompts/jd-driven-prep.md, a five-step process:

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
  1. Get the JD — prioritize reusing ../job-description-skill/jd-bank/ the already-decoded Must Have + Hidden Signals; if there are none, have the user paste the JD and decode it first.
  2. Get the full resume text — assign competency tags to each experience to prepare for matching. If the resume is too thin → switch to "Dig New Stories" and dig a few stories first.
  3. Cross-analysis → Top 20 selected questions — four categories (general Behavior / customized to company values / role-specific / customized to Level and stage). Each question must include "what is being tested + why this company would ask it(pointing to a certain Must Have / Hidden Signal in the JD) + which story to pair with it".
  4. Prepare a template question by question — by default for the Top 5 must-practice questionswrite a complete STAR template: fill S/T solidly with facts from the resume,leave A/R as placeholdersguide the user to fill in real actions and numbers,never fabricate. Mark it as reusable for multiple drafts.
  5. Gap list — truthfully list the questions the JD requires but the resume has no material for, and redirect to "Dig New Stories" to dig on the spot.
  6. HTML report — by default output to ~/Desktop/Claude skills/bq-prep-<company>-<role>-<YYYYMM>.html(for visual specifications, see assets/bq-prep-report.md）。
  7. Write back — write the JD↔story mapping back to the job-description-skill's jd-bank file under "Predicted Questions", forming a complete job-search chain.

This is the downstream deepening of the job-description-skill interview prediction process: over there it gives "what will be asked", here it gives "how to answer using your real experience + templates」。

Story Bank

  • Location: under this skill's directory story-bank/, one per story .md。
  • Metadata relies on frontmatter (tags / competencies / company_fit / metrics / framework / status).
  • _index.md is a reverse lookup table:competency labels → story files, and is the entry point reused by "Answer Questions".
  • Every time a story is added or modified,be sure to update in sync _index.md。

reference files (read on demand, don't load them all at once)

  • prompts/story-mining.md — four-layer probing engine (the core of "Dig New Stories")
  • prompts/structuring.md — structured diagnosis and rewriting ("Polish Existing Stories")
  • prompts/jd-driven-prep.md — JD × resume → Top 20 topic selections + preparation templates ("JD-Driven Preparation", linked to job-description-skill)
  • assets/bq-prep-report.md — HTML report visual specification for "JD-Driven Preparation"
  • frameworks/star-car.md — when to use STAR / CAR / SOAR, and reusing the same story from multiple angles
  • frameworks/competency-tags.md — competency label dictionary + BQ question type reverse lookup
  • frameworks/company-profiles.md — evaluation styles such as Amazon LP / Meta / Anthropic / OpenAI
  • story-bank/_story-template.md — story file template
  • story-bank/_index.md — story index