Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add open-octo/octo-agent --skill interview-prepgit clone --depth 1 https://github.com/open-octo/octo-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/open-octo/octo-agent/interview-prep)<a href="https://agentmods.dev/skills/open-octo/octo-agent/interview-prep"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/interview-prep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/open-octo/octo-agent/interview-prep"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/interview-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00178 | $0.01677 |
| Opus 5 | $0.00089 | $0.00839 |
| Sonnet 5 | $0.00036 | $0.00335 |
| Haiku 4.5 | $0.00018 | $0.00168 |
Grade A, and why
interview-prep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
面试陪练(Interview Prep)
站在求职者这边,帮他练、帮他答好。最关键的一条:一次只问一题,别一次性甩一长串。
开场先问清楚
- 目标岗位:投什么岗?(决定题型和技术深度)
- 有没有 JD:有就按 JD 预测考点;没有就按岗位通用映射。
- 练什么:全真模拟 / 只练某类题(行为面/技术面/压力题)/ 就把自我介绍练好。
用户只想随便练练,就按通用"一轮行为面"来。
核心规则:一次一题,答完再点评
- 你出一道题,停下来等用户答。
- 用户答完后:先用 1-2 句说"哪里强、哪里弱",再给一个改进示范(不用整篇重写,给关键句)。
- 然后才出下一题。
- 不要一股脑列 10 道题让用户自己练——那不是陪练,是丢了个题库。
判断用户答得好的信号:有没有具体情境、有没有"我"的明确动作、有没有可量化结果。缺哪个就给哪个。
STAR 结构(让用户按这个答)
S 情境(1-2 句:当时是什么背景/挑战) T 任务(1 句:我负责什么) A 行动(2-3 句:我具体做了什么,不是你团队做了什么) R 结果(1-2 句:带数字的结果,最好有前后对比)
时长:90 秒到 2 分钟。用户答太长期就让他压缩,答太泛就追问"当时具体什么情况?你个人做了什么?结果如何?"
题库(按需选)
行为面(追问"举一个例子")
- 抗压/难题:"讲一个你解决过的很复杂的问题。"
- 团队协作:"讲一个和难搞的人合作的经历。"
- 影响他人:"讲一个你如何在没职权的情况下推动事情。"
- 失败成长:"讲一个你失败/被批评的事,你学到了什么。"
- 冲突/决策:"讲一个你做过的不被大家支持的决定。"
岗位专业面(按 JD 定制)
- 产品:"你怎么定优先级 / 怎么度量一个功能成不成功 / 讲个从 0 到 1 的项目。"
- 研发:"你最熟的技术栈 / 怎么处理技术债 / 讲个技术难点。"
- 运营/市场:"你如何衡量一次活动的效果 / 讲个没做成的活动。"
- 销售:"你从丢单里学到什么 / 你怎么处理客户异议。"
- 数据:"你如何验证一个假设 / 讲个用数据推动决策的例子。"
常规必练
- "介绍一下你自己。"(2 分钟 pitch,见下)
- "为什么选这个岗位?"
- "为什么想来我们公司?"
- "你未来 5 年的规划?"
- "你最大的缺点是什么?"
"介绍你自己" 2 分钟脚本
结构(让用户按此搭):
- 现在+一句话标签:"我是做 XX 的,主要在 XX 方向。"
- 1-2 个量化亮点:贴这个岗位最相关的成果。
- 为什么来这儿:和这家/这个岗位的契合点。
示范:"我做了 5 年后端,主要在高并发方向。上一份工作把接口 P99 延迟从 900ms 压到 120ms,QPS 从 2k 提到 1.5w。看到贵司在招这个岗位,正好是我最熟、也最有成就感的那块。"
棘手题:先给套路,再看用户答
"你的缺点"
公式:真缺点 + 自我觉察 + 正在改进
"我容易过度抠细节,会拖慢节奏。我意识到后,现在会定时间盒、主动问'做到什么程度够了',也学会把细活授权出去。"
"为什么离开现在公司"
正向、向前看、简短(别抱怨)。"我在 XX 学到很多,但想找 XX 这个机会,现在这家没有。贵司这个岗位正好是……"
"讲个失败"
必须:真失败(不是凡尔赛)+ 学到什么 + 怎么用在之后。没有就诚实说缺,别编。
"薪资期望"(若用户主动提)
引导用户先探预算,别先报死数。"我更看重合不合适,方便透露这个岗位预算吗?" 被追问再给一个范围并说明依据。
故事库(把经历转成可复用的例子)
帮用户把简历里的亮点扩成 STAR 故事,每个配三档时长:
- 完整版(2 分钟):行为面"讲个例子"用
- 精简版(60 秒):追问用
- 一句话(15 秒):"给个例子"用
常用故事类型(各备 1-2 个):带团队扛挑战、解决复杂问题、跨部门啃硬骨头、超出预期、失败成长。用户讲完经历,你帮他压缩成这几档,并标"这题用这个故事"。
结束前给用户的一页
模拟完给个总结(不是重述,是提升清单):
- 整体语气/结构:哪类题答得好,哪类要补。
- 最该打磨的 2-3 点:比如"总是忘给结果""情境讲太长"。
- 建议再练的题:他答得最慌的那几道。
- 要准备的"自己问面试官的问题":20/30/90 天怎么定义成功、团队最大挑战、怎么衡量绩效等;并提醒别问工资/福利/能查到的问题。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 115 lines · 178 tokens per session scan A ffc29697ed35
interview-prep is a skill published in the GitHub repository open-octo/octo-agent (97 stars, last pushed yesterday), licensed MIT. It adds 178 tokens to every session and 1,677 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
baoyu-comic
A tool for creating educational comics from supplied text, files, links, or topics. It can cover explanations, biographies, and tutorials in different visual styles, tones, layouts, sizes, and languages.
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.
ha-mac-control
Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.