job-rank
Skill48 starsChanged 5 days agoMITView on GitHub
给抓到还没评的岗批量打分,排出可以投的 不给参数时:把还没评的全部评完,分批循环直到队列排空 触发词:给这些岗打分、排个序、哪个岗值得投、评一评、job rank
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- job-add-portalSkill
- job-add-templateSkill
- job-application-assistantSkill
- job-applySkill
- job-autoSkill
- job-cvSkill
- job-dashboardSkill
- job-expandSkill
- job-gmail-syncSkill
- job-html-reportSkill
- job-interviewSkill
- job-notion-syncSkill
- job-offerSkill
- job-outcomeSkill
- job-refreshSkill
- job-resetSkill
- job-resumeSkill
- job-scrapeSkill
- job-setupSkill
- job-upskillSkill
- job-userSkill
- liepin-searchSkill
- job-add-portalSkill
- job-add-templateSkill
- job-application-assistantSkill
- job-applySkill
- job-autoSkill
- job-cvSkill
- job-dashboardSkill
- job-expandSkill
- job-gmail-syncSkill
- job-html-reportSkill
- job-interviewSkill
- job-notion-syncSkill
- job-offerSkill
- job-outcomeSkill
- job-rankSkill
- job-refreshSkill
- job-resetSkill
- job-resumeSkill
- job-scrapeSkill
- job-setupSkill
- job-upskillSkill
- job-userSkill
The file
Files
<!-- 由 tools/gen_entries.py 生成:改 workflows/INDEX.md 或 tools/_entries.py,别改这里 -->job-rank(壳)
读取并严格执行 workflows/job-rank.md。
allowed-tools 是支持该字段的宿主使用的权限声明;其它宿主按当前会话实际工具与权限执行,不把工具别名差异当成能力缺失。
涉及浏览器时,先按当前会话实际提供的工具自动选择,执行 workflows/reference/cdp-portals.md「执行时自动选择浏览器」;不要只查某一家扩展,也不要从工具名推断已有登录态。
用户在这条命令后面给的内容(链接、公司名、方向词、整段职位描述)原样带进工作流。
个人数据路径(profile/…、documents/…、resume/main.typ 这类)在这条命令里一律指活动用户目录 users/<活动用户>/ 下的那一份,解析规则见 AGENTS.md「活动用户与多用户」。
裸命令的行为:把还没评的全部评完,分批循环直到队列排空。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

