interview SKILL.md skillA

interview from hisn00w/asu-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add hisn00w/asu-skills/interview@git:20260903.a706e27

Pins git:20260903.a706e27 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
hisn00w/asu-skills
Path
skills/interview/SKILL.md
Versions recorded
5
Latest version
git:20260903.a706e27, committed Sep 3, 2026
First version recorded
Aug 18, 2026
Size
7,516 bytes
Repository stars
6,511
License
MIT

中文简历与目标岗位驱动的面试预测、模拟追问和复练技能:提取需要验证的经历 Claim,按面试轮次建立问题与评分契约,通过一次一问、证据反馈和弱项复练检查真实掌握程度;当用户输入“/interview”、要求面试预测、模拟面试、简历追问、压力面、场景设计题或检查面试掌握程度时使用。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# /interview:把简历问穿

`/interview` 不替用户编造可以背诵的经历,而是把简历和 JD 中的重要 Claim 变成可验证的问题。它通过面试契约、逐轮追问、证据评估和弱项复练,检查用户能否讲清真实职责、技术实现、指标口径、决策取舍和失败案例。

核心链路:

```text
简历 / JD
  ↓
Claim 与岗位能力矩阵
  ↓
面试契约
  ↓
问题与评分契约
  ↓
一次一问、动态追问
  ↓
会话账本
  ↓
证据复盘与弱项复练
```

## 输入与事实边界

优先使用当前对话已有材料,不让用户重复粘贴:

1. 简历或项目经历;
2. 目标岗位和 JD;
3. 项目文档、代码、论文或公开链接;
4. 已确认的真实职责、指标和结果;
5. 面试轮次、可用时间和反馈偏好。

没有 JD 时仍可根据简历预测;没有简历时,请用户提供简历或至少一段项目经历。只询问会实质改变训练结果的缺失信息,其余使用明确默认值。材料不足时标记 `待确认`,不补写用户没有提供的经历、数据或技术细节。

问题优先验证真实主张,不批量生成与岗位无关的通用八股。不要把回答、掌握度或面试表现写入公开文件;只有用户明确要求时才把复盘保存到本地文件。

## 四种模式

### Predict:预测问题

当用户要求预测问题或输入 `/interview predict` 时:

1. 提取 Ownership、Metric、Technical、Architecture 和 Result Claim;
2. 从 JD 提取岗位能力,建立“能力—简历证据—缺口”矩阵;
3. 按相关度、发生概率、表述风险和证据缺口排序;
4. 输出高概率题、补充题和压力题;
5. 为核心题标明来源、考察意图、应覆盖事实和下一层追问。

不要为每道题直接生成长篇答案。推荐结构:

```text
Q:你在项目中为什么选择这套方案?
来源:简历中的“设计 Agent Runtime”
考察:技术选型、个人决策权、trade-off
回答应覆盖:原问题、候选方案、选择依据、个人负责部分、结果证据
追问:如果流量或上下文规模扩大,最先出现什么瓶颈?
```

### Grill:模拟面试

当用户要求模拟面试、压力面或输入 `/interview grill` 时:

1. 根据已知材料建立面试契约;需要完整会话规则时读取 [references/interview-contract-and-session.md](references/interview-contract-and-session.md);
2. 选择最高相关或最高风险 Claim,为当前问题建立锁定的评分契约;
3. 每轮只问一个问题,等待回答后再评估和决定下一步;
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_vwvhgfope23pr4zh/5f7554bfbdb8bbccc48379ba39e02d165b125f514206cb0d9e1e81002668edfd.json

Then /plugin install interview@markdownregistry-vwvhgfope23pr4zh in Claude Code. It installs git:20260903.a706e27, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add hisn00w/asu-skills/interview@sha256:5f7554bfbdb8bbcc

The line at the top of this page pins the label git:20260903.a706e27, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_vwvhgfope23pr4zh.svg)](https://markdownregistry.com/a/art_vwvhgfope23pr4zh)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in hisn00w/asu-skills/interview since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of interview from somewhere else? Ask it: where did my interview come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between Aug 18, 2026 and Sep 3, 2026, about one every 4 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260903.a706e27 latest2026-09-03 a706e27 7,516 BA view · diff
git:20260903.5b98b3e2026-09-03 5b98b3e 7,489 BA view · diff
git:20260828.5dfba1a2026-08-28 5dfba1a 7,483 BA view · diff
git:20260827.0c66ac32026-08-27 0c66ac3 8,611 BA view · diff
git:20260818.cded06e2026-08-18 cded06e 8,601 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7516 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

hisn00w/asu-skills · 6,511 stars · license MIT · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vwvhgfope23pr4zh
GET https://markdownregistry.com/api/v1/resolve?ref=hisn00w/asu-skills/interview
GET https://markdownregistry.com/api/v1/blob/5f7554bfbdb8bbccc48379ba39e02d165b125f514206cb0d9e1e81002668edfd

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from hisn00w/asu-skills

AGENTS.md AGENTS.md file
hisn00w/asu-skills · AGENTS.md
git:20260903.a706e27 · audit A · 6,511 stars
CLAUDE.md CLAUDE.md file
hisn00w/asu-skills · CLAUDE.md
git:20260814.767d317 · audit A · 6,511 stars
contributor SKILL.md skill
hisn00w/asu-skills · skills/contributor/SKILL.md · GitHub 开源贡献辅助技能:围绕目标岗位和技术栈发现合适的开源项目与真实问题,评估维护状态、贡献规则和重复风险,准备最小可验证改动,经用户逐项确认后 fork、push、提交 PR,并跟踪 CI、review…
git:20261013.8d93501 · audit A · 6,511 stars
evidence-recap SKILL.md skill
hisn00w/asu-skills · skills/evidence-recap/SKILL.md · 把 AI 编程对话和项目交付材料复盘为可核验的九段证据链,区分问题、决策、个人动作、交付阶段、效果证据与责任边界。当用户运行 /evidence-recap、$evidence-recap,或明确要求复盘 AI…
git:20260906.32dfaf7 · audit A · 6,511 stars
great-resume SKILL.md skill
hisn00w/asu-skills · skills/great-resume/SKILL.md · 中文求职经历提升技能:根据目标岗位把真实经历重组为岗位定位、简历要点、项目亮点和 HR 开场白;当用户输入“/great-resume”“我要酥化”或“简历提升”、要求包装或改写经历、项目,或写 HR…
git:20260903.a706e27 · audit A · 6,511 stars
job-apply SKILL.md skill
hisn00w/asu-skills · skills/job-apply/SKILL.md · 中文求职申请自动填写技能:使用浏览器读取用户确认的简历资料,逐项填写招聘网站申请表并核对结果;当用户输入“/job-apply”、要求自动填简历或填写求职申请时使用。
git:20260903.a706e27 · audit A · 6,511 stars
job-match SKILL.md skill
hisn00w/asu-skills · skills/job-match/SKILL.md · 中文岗位匹配分析技能:对照目标 JD 与用户已确认的简历、经历或主张—证据账本,区分已匹配、证据不足和真实缺口,生成可解释的投递建议与后续 skill 交接;当用户输入“/job-match”、要求分析岗位适配度、JD…
git:20260904.04486cb · audit A · 6,511 stars
make-resume SKILL.md skill
hisn00w/asu-skills · skills/make-resume/SKILL.md · 中文可编辑简历制作技能:默认基于 ASu 单栏高密度技术简历模板,根据用户经历制作或复刻可编辑 HTML/PDF;用户也可以指定仓库内其他模板、本地 HTML…
git:20261102.f4c88c9 · audit A · 6,511 stars
offer SKILL.md skill
hisn00w/asu-skills · skills/offer/SKILL.md · 中文秋招求职进度管理技能:记录和更新投递、筛选、测评、面试、Offer、拒信及招聘邮件状态,生成可搜索的进度表;也可以比较多个 Offer 的薪资结构、成长空间、团队、稳定性和个人成本,输出加权决策建议与谈判要点;当用户输入“/offer”…
git:20261102.66c98f5 · audit A · 6,511 stars
project-guide SKILL.md skill
hisn00w/asu-skills · skills/project-guide/SKILL.md · 中文项目导学、源码课程与项目面经技能:基于本地项目仓库、项目描述或技术材料,按需生成源码课程与理解题,或生成 导学-{简称}.md、面经-{简称}.md…
git:20260907.14a2b19 · audit A · 6,511 stars

Every file in hisn00w/asu-skills

Other files named interview

interview SKILL.md skill
alirezarezvani/claude-skills · agent-launcher/skills/interview/SKILL.md · Use when someone has an agent idea to scope before launch ('help me scope an agent'). Interviews them about the one job…
v2.11.2 · audit A · 30,034 stars
interview SKILL.md skill
q00/ouroboros · skills/interview/SKILL.md · Use when the user wants to build or change something but the request is vague or open-ended: 'help me figure out what…
git:20261116.64a2b2e · audit A · 6,381 stars
interview SKILL.md skill
boshu2/agentops · skills/interview/SKILL.md · Interview you one question at a time, each choice with a recommendation, to settle a big outcome before agents work…
git:20261031.73cbeae · audit A · 457 stars
interview SKILL.md skill
boshu2/agentops · plugin/skills/interview/SKILL.md · Interview you one question at a time, each choice with a recommendation, to settle a big outcome before agents work…
git:20261031.73cbeae · audit A · 457 stars
interview SKILL.md skill
suxrobgm/jobpilot · plugin/skills/interview/SKILL.md · Produce a tailored interview prep sheet (behavioral, technical, system design, company) from a job description and the…
git:20261108.8c2028c · audit A · 113 stars
interview SKILL.md skill
plastic-labs/claude-honcho · plugins/honcho/skills/interview/SKILL.md · Interview the user to capture stable, cross-project preferences and save them to Honcho
git:20260203.ab2f56f · audit B · 78 stars
interview SKILL.md skill
haabe/mycelium · tests/bash/fixtures/check_15/missing_wrapping/plugins/mycelium/skills/interview/SKILL.md · Non-compliant fixture: handles user content but no wrapping acknowledgment.
git:20260524.7234d11 · audit A · 54 stars
interview SKILL.md skill
haabe/mycelium · tests/bash/fixtures/check_15/compliant/plugins/mycelium/skills/interview/SKILL.md · Compliant fixture: acknowledges wrapping convention.
git:20260524.7234d11 · audit A · 54 stars

Browse by kind, by grade A, or by owner.