cheat-on-content
给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP
$ npx -y skills add LiHongwei-cn/lihongwei-cn --skill ai-dev-jobs-mcp --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ai-dev-jobs-mcpContext preview
The summary Claude sees to decide when to auto-load this skill.
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP
name: ai-dev-jobs-mcp description: "Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP" category: mcp risk: safe source: "https://aidevboard.com" source_type: community date_added: "2026-04-16" author: unitedideas tags: [mcp, jobs, ai-jobs, ml-jobs, recruiting, job-search, career] tools: [claude, cursor, gemini]
AI Dev Jobs is a remote MCP server that gives AI agents access to a live index of AI and ML job listings. As of April 17, 2026, the live MCP stats report 8,405 active roles across 489 companies, a $213,500 median salary, and 600 new jobs this week. Agents can search jobs by role, location, or company, retrieve full job details, list hiring companies, match roles to a profile, and get salary or aggregate market statistics. It is designed for AI agents that assist with job searching, recruiting, or labor market analysis.
Add the AI Dev Jobs MCP server to your client configuration. The endpoint uses streamable HTTP and requires no authentication.
{
"mcpServers": {
"ai-dev-jobs": {
"url": "https://aidevboard.com/mcp"
}
}
}No API key or authentication is required.
Search the job index by keyword, location, company, or work arrangement. Returns matching listings with title, company, location, and salary information.
search_jobs({ query: "machine learning engineer", location: "remote" })Retrieve full details for a specific job listing by ID, including description, requirements, salary range, and application link.
get_job({ id: "abc123" })List all companies in the index with their open position counts. Useful for discovering which companies are actively hiring.
list_companies({})Retrieve details for a specific company, including available AI roles when exposed by the endpoint.
get_company({ id: "openai" })Get aggregate statistics about the job market: total listings, top companies by open roles, role distribution, and location breakdown.
get_stats({})Match jobs against a candidate profile, skills list, or preferences.
match_jobs({ skills: ["python", "llm", "pytorch"], workplace: "remote" })Retrieve salary statistics for roles, tags, levels, or locations when available.
get_salary_data({ tag: "llm", level: "senior" })List indexed tags that can be used to filter searches or salary analysis.
list_tags({})Use @ai-dev-jobs-mcp to find remote machine learning engineer positions.
The agent will call `search_jobs({ query: "machine learning engineer", location: "remote" })` and return matching listings.
Use @ai-dev-jobs-mcp to list all companies currently hiring for AI roles.
The agent will call `list_companies({})` and return companies sorted by number of open positions.
Use @ai-dev-jobs-mcp to show current AI job market statistics.
The agent will call `get_stats({})` and return aggregate data on listings, top employers, and role distribution.
Use @ai-dev-jobs-mcp to get the full details for job ID abc123.
The agent will call `get_job({ id: "abc123" })` and return the complete listing with requirements and application link.
Use @ai-dev-jobs-mcp to match remote LLM roles to a senior Python and PyTorch profile.
The agent will call `match_jobs({ skills: ["python", "llm", "pytorch"], workplace: "remote" })` and return suitable listings.
Use @ai-dev-jobs-mcp to compare senior LLM salary data.
The agent will call `get_salary_data({ tag: "llm", level: "senior" })` and summarize available compensation ranges.
MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.
Repo: LiHongwei-cn/lihongwei-cn
给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…
提议并执行 rubric 或 bucket 升级。两种模式:**完整 rubric bump**(最高风险动作,5 步强制 + 跨模型审核)和 **--bucket-only 轻量重校**(只换 bucket 边界,不动 rubric 公式)。**Phase 2 强制走 cheat-score-blind…
cheat-on-content 的首次 onboarding 与脚手架创建器。统一流程——所有用户都走相同 5 阶段闭环,唯一区别是"发过视频的人"会在 init 时多一步:抓取已有视频建立历史 context(用于后续 cheat-seed 给更贴合的选题、更准的…
从对标账号导入 script + 数据 → 拆 pattern + 派生 base rubric 信号 → 写到 benchmark.md / script_patterns.md / rubric_notes.md。**这是工具最早期信号的来源**——cold-start…
把老用户的 .cheat-state.json 升级到当前 schema_version。读 migrations/registry.md 算迁移链,按顺序应用每一步迁移文件。幂等:跑两次结果一样。失败停在中间版本不前进。触发词:"迁移"/"升级 state"/"migrate"/"我的 state…
从复盘评论数据派生 / 刷新账号的受众画像,写入 audience.md。这是和 rubric 平行的第二个派生物——rubric 答"怎么打分",persona 答"谁在看"。cheat-seed 选题 / 写稿时读它。**audience.md 含实绩信号,cheat-score-blind…