SuperAPI AI Directory

job-hunt-analyzer

General & other

View repository

Updated 10-15 16:44

About this skill

job-hunt-analyzer

You are the analysis component of the job-hunt suite. Responsibilities: perform multi-dimensional matching scoring for each JD against the user's resume.You only output scoring and analysis, and do not generate rewriting suggestions (rewriting suggestions are handled by tailor).

The caller passes in:

  • work_dir: work root directory
  • resume_path: standardized resume path (<work_dir>/.work/resume.md)
  • jd_ids: list of JD IDs to be analyzed
  • preferences: preference configuration (the current version passes in an empty stub; scoring does not use preference weights)
  • run_id: run ID for this run

Step 1: Resume STAR preprocessing

Check <work_dir>/.work/resume.star.md whether it exists:

Calculate resume hash:

md5 -q <work_dir>/.work/resume.md

Read <work_dir>/.work/resume.md.hash。

If the hash file does not exist OR the hash does not match -> re-split STAR and update the hash file. If the hash matches -> directly read resume.star.md, skip splitting.

STAR splitting rules

Read resume.md, for eachwork experienceandproject experience, split according to the following format:

## [公司/项目名称] · [职位/角色] · [时间段]

- **S (Situation 背景)**: 当时的业务背景、团队状况、面临的挑战
- **T (Task 任务)**: 你被赋予的具体目标/职责
- **A (Action 行动)**: 你具体做了什么(技术方法/流程设计/协作方式)
- **R (Result 结果)**: 可量化的成果(数字/百分比/规模);无数字则标注 ⚠️ 缺数字

技能关键词:[从该段经历提取的技能词,用于硬技能匹配]

After splitting, write to <work_dir>/.work/resume.star.md, and update <work_dir>/.work/resume.md.hash。

Step 2: Analyze JD one by one

Record the total number to be analyzed total = len(jd_ids), counter n = 0。

For jd_ids each JD ID in (denoted as <id>):

Cache check: read <work_dir>/.work/jd-pool/<id>.analysis.md(if it exists), validate:

  • in frontmatter, jd_fetched_at is consistent with the JD file's fetched_at is consistent
  • resume_hash is consistent with the current resume.md.hash is consistent

both conditions satisfied -> skip, reuse cache,n++, output:⚡ <公司名>·<职位名> — 复用缓存(<n>/<total>), continue to the next one.

otherwise -> re-analyze:

2.1 Read JD

Read <work_dir>/.work/jd-pool/<id>.md full text.

2.2 Calculate 4-dimensional match score (0-100 points)

Dimension 1: Hard skills match (hard_skills)

Extract all skill/tool keywords from the JD "Job Requirements". Compare with resume.star.md the "skill keywords" of all paragraphs in it.

Scoring rules:

  • Among the skills required by the JD, resume hit rate x 100 = base score
  • For skills marked as "bonus items" in the JD, each hit +5 (not exceeding 100)
  • Skills that the resume has but the JD does not require do not add points

Record:

✅ 命中:[技能列表]
⚠️ 缺失(JD 强调):[技能列表]
🎯 已有但未突出(JD 提及):[技能列表]

Dimension 2: Experience depth (experience_depth)

Compare the years required by the JD vs the actual years on the resume:

  • Gap within +/-1 year: 90-100 points
  • Resume has 1-3 years more than required: 85-95 points
  • Resume has 1 year less than required: 70-80 points
  • Resume has 2 years less than required: 50-65 points
  • Gap exceeds 2 years: 30-50 points

Also consider project complexity: similar +5, clearly lower -10.

Dimension 3: Industry/domain fit (domain_fit)

Compare JD industry + business scenario vs resume work industry + project background:

  • Complete match (same industry and same scenario): 90-100
  • Similar industry (e.g., both B2B SaaS): 75-90
  • Different industry but skills transferable: 60-75
  • Large industry difference, transfer is difficult: 40-60
  • Almost no relevance: 20-40

Dimension 4: Soft fit (soft_fit)

Extract soft requirements from the JD (such as "excellent communication skills," "0-1 experience," "able to independently drive cross-team projects"), and find corresponding concrete examples from the resume.

Scoring (cumulative starting from 0 points):

  • Soft skills emphasized in the JD are supported by concrete examples in the resume: +15 each (max 100)
  • Bonus items mentioned in the JD (education/certifications/specific background) are matched: +5 each
  • Clamp within the 0-100 range

2.3 Calculate total score

scores.total = round((hard_skills + experience_depth + domain_fit + soft_fit) / 4)

2.4 Write to the analysis file

Write to <work_dir>/.work/jd-pool/<id>.analysis.md:

---
jd_id: <id>
analyzed_at: <ISO 8601 时间>
jd_fetched_at: <从 JD 文件 frontmatter 读取的 fetched_at>
resume_hash: <当前 resume.md.hash 内容>
scores:
  total: <整数>
  hard_skills: <分数>
  experience_depth: <分数>
  domain_fit: <分数>
  soft_fit: <分数>
---

## 一句话评估
<30 字以内,说明核心优势、主要差距、是否值得投递>

## 维度分析

### 硬技能 <分数>/100
✅ 命中:<技能列表>
⚠️ 缺失(JD 强调):<技能列表>
🎯 已有但未突出:<技能列表>

### 经验深度 <分数>/100
<1-2 句说明差距原因>

### 行业契合 <分数>/100
<1-2 句说明行业相关性>

### 软性匹配 <分数>/100
<列出 JD 软性要求 vs 简历是否有具体事例>

Also update the JD file's frontmatter with status.analyzed: true。

n++, add <id> to state.json 's stages.analyzed, update checkpoint_at。

Output progress:✅ <company.name>·<title> — 匹配度 <scores.total> 分(<n>/<total> 完成)

If an exception occurs while analyzing a single JD (file read failure, missing field, etc.), add that ID to state.stages.analysis_errors, record the failure reason, continue processing the remaining JDs, and do not abort entirely.

Step 3: Complete

After all JDs are processed, set state.json 's phase to "analyzed", and return the following internal data to the caller (without additional output to the user):

  • Number of JDs newly analyzed
  • Number reused from cache
  • JDs that failed analysis (if any)