菜单
Use when searching or explaining InternAgent job discovery, recommendation, match scoring, source labels, query expansion, city filters, or missing skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when inspecting AI assistant file-based long-term memory, session JSONL archives, soft consolidation, Dream updates, or assistant context isolation.
Use when running Agent golden-case evaluation, checking intent accuracy, tool-call accuracy, RAG grounding, job matching, interview follow-up policy, or resume rubric compliance.
Use when reading saved jobs, application status counts, manual follow-up notes, or the user's application tracking state.
Use when inspecting FastAPI routes, controllers, backend service boundaries, repository-backed endpoints, API surface, or route availability.
Use when inspecting or explaining Qingcheng AI chat complexity classification, prompt-template injection, SupervisorAgent routing, selected tool allowlists, or agent planning for a user message.
Use when changing or reviewing the Next.js frontend UI, Tailwind layout, chat/interview pages, resume/job/application screens, or frontend API wrappers.
| name | job-search-tool |
| description | Use when searching or explaining InternAgent job discovery, recommendation, match scoring, source labels, query expansion, city filters, or missing skills. |
Use this skill to run the project job discovery pipeline through JobService.discover_jobs. It reuses repository search, taxonomy, dedupe, recommendation scoring, and resume-aware matching when a user is supplied.
Run inside the API container:
docker compose exec api python /app/skills/job-search-tool/scripts/discover_jobs.py --keyword Java --city 北京 --experience intern --email admin@example.com
Inputs: --keyword, --city, --experience, --skills, --limit, optional --user-id or --email.
The script emits compact JSON: total, source_kind, fallback_notice, query_expansions, and jobs[] with title, company, city, source, URL, recommendation score, matched/missing skills, and priority. It never claims a static fallback is live market evidence.
Present only returned jobs. Mention source and fallback notices. For resume-aware results, explain matched and missing skills. Never say the system submitted an application.
python skills/job-search-tool/scripts/discover_jobs.py --self-test
python skills/job-search-tool/scripts/discover_jobs.py --help
docker compose exec api python /app/skills/job-search-tool/scripts/discover_jobs.py --keyword 产品 --city 北京 --limit 5