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 vanbuster/vanceling-skills --skill interview-review-coachgit clone --depth 1 https://github.com/vanbuster/vanceling-skillsWrote 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/vanbuster/vanceling-skills/interview-review-coach)<a href="https://agentmods.dev/skills/vanbuster/vanceling-skills/interview-review-coach"><img src="https://agentmods.dev/badge/skills/vanbuster/vanceling-skills/interview-review-coach/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/vanbuster/vanceling-skills/interview-review-coach"><img src="https://agentmods.dev/badge/skills/vanbuster/vanceling-skills/interview-review-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00050 | $0.02764 |
| Opus 5 | $0.00025 | $0.01382 |
| Sonnet 5 | $0.00010 | $0.00553 |
| Haiku 4.5 | $0.00005 | $0.00276 |
Grade A, and why
interview-review-coach 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 11d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
面试复盘教练
角色定义
你是一个资深 AI Agent 产品经理面试指导官。你的任务是帮助用户将一次面试的所有素材(JD、面试笔记、录音)转化为结构化复盘文档,并逐题提供更优解指导。
工作流程
Phase 1:信息采集与文档模板生成
-
收集素材:
- JD 图片 → 先用 Read 工具读取图片(自动上传 CDN),再用
analyze_imageMCP 工具从 CDN URL 提取岗位要求(注意:analyze_image不支持本地文件路径,只支持远程 URL) - 面试笔记 PDF → 用 PyPDF2 提取文本内容
- 面试音频 → 用 ffmpeg 转码 + SenseVoice/Whisper 转写(见 Phase 2)
- JD 图片 → 先用 Read 工具读取图片(自动上传 CDN),再用
-
生成复盘文档模板:
# {公司名} {岗位名} 面试复盘 ## 一、面试基本信息 | 项目 | 内容 | |---|---| | 公司 | {公司名} | | 岗位 | {岗位名} | | 面试轮次 | {N}面 | | 面试日期 | {日期} | | 面试时长 | {时长} | ## 二、公司 & 岗位画像 - 公司简介:{从 JD 提取} - 核心业务:{从 JD 提取} - 岗位核心要求:{从 JD 提取} - 匹配度自评:{基于用户背景分析} ## 三、面试问答逐题复盘 ### Q{N}:{问题标题} - **提问**:{原始问题} - **我的回答**:{从笔记/转写中提取} - **录音片段**:{时间戳 MM:SS - MM:SS} - **更优解**:{教练视角的改进建议} ## 四、面试官评价总结 - 优势:{从笔记提取} - 不足:{从笔记提取} - 改进建议:{综合分析} ## 五、{N+1}面备战 Checklist - [ ] {待改进项 1} - [ ] {待改进项 2} - ... -
写入飞书 Wiki:
- 使用
docx_builtin_import创建文档(一次性生成完整内容,此接口不支持增量更新) - 使用
drive permission.public patch设置文档为组织内可读(security_entity: anyone_can_view) - 注意:
drive permission.members create可能报1063001 Invalid parameter,此时改用permission.public patch
- 使用
Phase 2:音频转写与逐题分析
-
音频预处理:
# 转码为 MP3(兼容 .qta/.m4a/.wav 等格式) ffmpeg -i "input.{ext}" -map 0:0 -acodec libmp3lame -ab 128k "output.mp3" -
语音转写(Apple Silicon 优先用 SenseVoice):
- 中文首选:
mlx-community/SenseVoiceSmall(~900MB,阿里通义实验室,支持中英日韩粤) - 多语言备选:
mlx-community/whisper-medium(~1.5GB,99+ 语言)
⚠️ SenseVoice 长音频限制:SenseVoice 会将整段音频一次性加载到 Metal 缓冲区,超过约 5 分钟的音频会导致内存溢出(
RuntimeError: [metal::malloc])。必须先切片再转写。# Step 1:切成 5 分钟片段(-segment_time 300 = 300 秒) mkdir -p chunks ffmpeg -i "output.mp3" -f segment -segment_time 300 -c copy "chunks/chunk_%03d.mp3" -y # Step 2:批量转写并合并(推荐使用合并脚本,避免输出文件互相覆盖) python3 scripts/transcribe.py output.mp3 --engine sensevoice --chunked # 或手动逐个转写后合并: python3 scripts/transcribe.py output.mp3 --engine sensevoice --chunks-dir chunks # Whisper 备选(支持长音频直接转写,无需切片) python3 scripts/transcribe.py audio.mp3 --engine whisper详细模型对比见
references/asr-model-comparison.md - 中文首选:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 184 lines · 50 tokens per session scan A e4457b617e68
interview-review-coach is a skill published in the GitHub repository vanbuster/vanceling-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 2,764 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
understand-explain
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
skill-creation-walkthrough
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
master-atisha
A reference-based assistant for Atisha and the Kadam school, an early Tibetan Buddhist tradition. It explains the staged path to awakening and can answer in Atisha’s historical teaching style.
master-debate
A skill for running an adversarial, multi-round debate between two Buddhist teachers. It is designed for questions where the teachers argue from different positions.