A command that reviews an interview record, finds weaknesses and repeated problems, and saves a detailed improvement report. It covers technical skills, communication, time management, thinking patterns, and other issues.

For analysing a saved interview record, tracking repeated weaknesses, and creating a Markdown improvement report with learning suggestions.

It turns scattered interview notes into a structured view of recurring problems and what to improve first.

How huifer/claude-code-interview configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to huifer/claude-code-interview. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/huifer/claude-code-interview/main/.claude/commands/interview/feedback.md

Clone the repo

git clone --depth 1 https://github.com/huifer/claude-code-interview

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/huifer/claude-code-interview/feedback/github.svg)](https://agentmods.dev/commands/huifer/claude-code-interview/feedback)

Your own site

<a href="https://agentmods.dev/commands/huifer/claude-code-interview/feedback"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-interview/feedback/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/huifer/claude-code-interview/feedback"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-interview/feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 549 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00019	$0.00549
Opus 5.5	$0.00008	$0.00220
Sonnet 5.5	$0.00004	$0.00110
Haiku 4.5	$0.00002	$0.00055

Measured 2mo ago against content hash c995a6d3efb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

feedback 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 2mo 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.

.claude/commands/interview/feedback.md · 56 lines

What it actually says

面试不足分析

您正在分析面试记录，系统将：

读取面试记录中的详细表现
使用 AI 深度分析各类不足
识别重复出现的问题
生成详细改进报告并保存

正在分析...

请提供面试记录的 ID（格式：YYYYMMDD_company_round，例如：20250109_google_2）

系统将执行以下步骤：

步骤 1: 读取面试记录

从 data/interviews/{{interview_id}}.json 读取面试数据

步骤 2: AI 深度分析

使用 interview-coach Skill 进行不足分析：

技术类不足（technical）：算法、数据结构、编码、系统设计、领域知识
沟通类不足（communication）：清晰度、结构、术语、简洁性、倾听
时间管理（time_management）：分析时间、编码速度、规划、优先级
思维模式（thinking_pattern）：分解、抽象、模式识别、优化、权衡
其他不足（other）：领域知识、工具、语言、自信、压力管理

步骤 3: 重复不足识别

与全局不足追踪系统对比：

计算语义相似度（文本相似度 70% + 关键词重叠 30%）
相似度阈值 ≥ 0.75 判定为重复
标注重复出现的不足

步骤 4: 更新全局追踪

更新 data/analytics/weaknesses.json：

增加出现历史
更新统计信息
计算优先级分数
记录改善状态

步骤 5: 生成详细报告

生成 Markdown 报告并保存到 exports/weakness-reports/{{interview_id}}_weakness_analysis.md，包含：

基本信息（面试 ID、公司、类型、日期）
总体评估（评分、问题数量、严重问题数、重复问题数）
🔴 紧急改进（重复出现的问题）
🟡 短期改进（高优先级问题）
🟢 长期提升（其他问题）
详细改进计划
推荐学习资源

请提供面试 ID，开始分析。

Changes

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.

2mo ago First seen · 56 lines · 19 tokens per session scan A c995a6d3efb9

Subscribe to this mod's changes

feedback is a command published in the GitHub repository huifer/claude-code-interview (27 stars, last pushed 10mo ago), licensed MIT. It adds 19 tokens to every session and 549 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Learning and teaching

feedback next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
feedbackhuifer/claude-code-interview	Command	27	10mo ago	MIT	A	19	Claude Code
learn-story-flowIntai/story-flow	Command	16	2d ago	MIT	A	10	Claude Code
start-10-1minicoohei/ai-agent-camp	Command	347	1mo ago	none	A	2	Claude Code
start-0-8minicoohei/ai-agent-camp	Command	347	1mo ago	none	A	2	Claude Code
setup-m365cli.esminicoohei/ai-agent-camp	Command	347	1mo ago	none	A	8	Claude Code
prep-rolefourleafai/clover-public	Command	8	1mo ago	MIT	A	0	Claude Code
setup-vercel.esminicoohei/ai-agent-camp	Command	347	1mo ago	none	B	2	Claude Code

claude-code-interview: Command for Claude Code