Evaluates how well a candidate's resume matches a target job description (JD) and produces a clean, professional HTML assessment report. Parses the resume (v...
Documents
Jd Truth Detector
Try itReverse-engineer job descriptions: translate jargon ("5 years" → 3), infer company culture (red flags, vibes), match to your resume, detect negotiation signa...
What it does
Reverse-engineer job descriptions: translate jargon ("5 years" → 3), infer company culture (red flags, vibes), match to your resume, detect negotiation signals. Outputs Markdown + shareable HTML report. Works with any OpenAI-compatible LLM (Ollama, DeepSeek, OpenAI, etc.). Supports text paste (primary), URL scraping (BOSS/拉勾/LinkedIn), and file input (.txt/.md/.docx/.pdf).
The skill document
jd-truth-detector
Reverse-engineer job descriptions across 4 dimensions: jargon translation, company culture inference, resume match analysis, negotiation signals.
Quick Start
pip install -r requirements.txt
# Analyze from text
python scripts/jd_analyze.py --jd-text ""
# From URL (experimental)
python scripts/jd_analyze.py --jd-url "https://www.zhipin.com/job_detail/..."
# With resume
python scripts/jd_analyze.py --jd-file jd.txt --resume-file resume.md
Configuration
export JTD_BASE_URL=http://localhost:11434/v1
export JTD_API_KEY=ollama
export JTD_MODEL=qwen2.5:72b
Or ~/.config/jd-truth-detector/config.yaml:
base_url: https://api.deepseek.com/v1
api_key: sk-...
model: deepseek-chat
Four Dimensions
| Dimension | What it does |
|---|---|
| 黑话翻译 | "5年经验" → 实际3年即可 |
| 公司体感 | 红旗词频率、技术成熟度、业务清晰度 |
| 简历匹配 | (可选) 对比 JD 和你的简历 |
| 议价信号 | 薪资透明度、职级明确性、急招信号 |
Privacy
JD + resume sent only to your configured LLM endpoint. No telemetry.
Related skills
Tailor and polish an existing resume in Google Docs for a particular job without inventing qualifications, experience, metrics, or outcomes. Use when the user provides an editable GDocs resume link plus either direct recruiter feedback for the hiring role or a direct link to the role description
Searches LinkedIn, Poslovi Infostud, and HelloWorld.rs for jobs matching your target roles. Scores each listing against your resume PDF (1-10).
Researches job postings, hiring signals, and freelance gigs via the Crawlora API — Indeed, Google/Amazon/Apple/Meta/Tesla careers sites, any company's ATS board (Greenhouse, Lever, Workday, SmartRecruiters, Ashby, and more), plus Upwork and Fiverr — returning clean JSON. Use when the user wants to search job postings, see what a specific company is hiring for, aggregate hiring signals for a company, or research freelance gigs and sellers.
Use for WorkorAI talent marketplace requests. Candidate triggers: "найди мне работу", "ищу работу", "подбери вакансию", "find me a job", "I need work", "help...
Turn flat resume bullets ('Responsible for X') into quantified STAR-method achievement narratives, score resumes against job descriptions for ATS keyword coverage and weak-phrase hazards, and expand each bullet into interview-ready stories with likely follow-up questions. Use when the user is writing or updating a resume/CV, preparing bullets for a job application, tailoring a resume to a specific job posting, or preparing interview stories from their experience.