A comparison command for examining two resume versions side by side.

Use it to compare resume variants, inspect keyword density, review match scores for required and preferred skills, and assess how different applicant-tracking systems may read them.

It reports differences in keywords, job-description skill matches, basic details, formatting, and ATS compatibility so you can choose between versions.

compare — Command by huifer

Install

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.

agentmods

npx agentmods add commands/huifer/claude-code-interview/compare

Clone the repo

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

Made for: Claude Code.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,836 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00032	$0.02836
Opus 5	$0.00016	$0.01418
Sonnet 5	$0.00006	$0.00567
Haiku 4.5	$0.00003	$0.00284

Measured 2d ago against content hash 3b3d2f6d88eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compare 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 2d 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/resume/compare.md · 393 lines

How it starts

The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.

对比简历变体

对比 $1 和 $2 两个简历变体，分析它们在关键词、匹配度、格式等方面的差异。

使用方法

对比两个变体

/resume/compare google_v1 google_v2

系统将：

读取两个变体文件
提取关键信息进行对比
生成差异报告
提供选择建议

对比维度

1. 基本信息

文件名和创建时间
目标公司和职位
变体版本号
最后修改时间

2. 关键词密度分析

对比关键词在各个部分的密度：

{
  "keyword_density_comparison": {
    "summary": {
      "variant1": 18.5,
      "variant2": 22.3,
      "difference": "+3.8",
      "winner": "variant2"
    },
    "experience": {
      "variant1": 12.3,
      "variant2": 14.7,
      "difference": "+2.4",
      "winner": "variant2"
    },
    "skills": {
      "variant1": 95.0,
      "variant2": 100.0,
      "difference": "+5.0",
      "winner": "variant2"
    }
  }
}

3. 技能匹配度

对比与JD的技能匹配度：

{
  "match_score_comparison": {
    "variant1": {
      "overall": 82.5,
      "required_skills": 85.0,
      "preferred_skills": 78.0
    },
    "variant2": {
      "overall": 89.2,
      "required_skills": 92.0,
      "preferred_skills": 85.0
    },
    "improvement": "+6.7",
    "winner": "variant2"
  }
}

4. ATS兼容性

评估ATS系统解析能力：

{
  "ats_compatibility": {
    "workday": {
      "variant1": "medium",
      "variant2": "high"
    },
    "greenhouse": {
      "variant1": "high",
      "variant2": "high"
    },
    "lever": {
      "variant1": "high",
      "variant2": "high"
    },
    "overall_winner": "variant2"
  }
}

5. 内容差异

详细对比各部分内容：

Summary对比

### Variant 1
资深软件工程师，专注于分布式系统和机器学习...

### Variant 2
资深软件工程师，专注于大规模分布式系统、云计算和机器学习，
拥有5年高并发系统开发经验...

**分析**: v2更详细，突出"大规模"和"高并发"关键词

技能排序对比

### Variant 1
1. Python, Java, Go
2. Django, Spring Boot, React
3. Docker, Kubernetes

### Variant 2
1. Python, Go, Java
2. Kubernetes, Docker, AWS
3. Django, Spring Boot, FastAPI

**分析**: v2将Kubernetes提前，更匹配JD要求

经验描述对比

### 字节跳动 - Variant 1
负责抖音电商后台核心系统的开发和优化...

### 字节跳动 - Variant 2
设计并实现高并发订单处理系统，QPS从5k提升至50k，
系统稳定性达到99.99%...

**分析**: v2使用量化数据，更具体

6. 性能指标

{
  "performance_metrics": {
    "keyword_optimization": {
      "variant1": 75,
      "variant2": 90,
      "winner": "variant2"
    },
    "readability": {
      "variant1": 85,
      "variant2": 82,
      "winner": "variant1"
    },
    "conciseness": {
      "variant1": 80,
      "variant2": 78,
      "winner": "variant1"
    },
    "impact_orientation": {
      "variant1": 72,
      "variant2": 92,
      "winner": "variant2"
    }
  }
}

Read the full file on GitHub · 393 lines

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.

2d ago First seen · 393 lines · 32 tokens per session scan A 3b3d2f6d88eb

Subscribe to this mod's changes

compare is a command published in the GitHub repository huifer/claude-code-interview (23 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 2,836 once invoked, about $0.0002 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 2026-08-30.

Code review

compare