菜单
Web search, code context, company research, and deep research via Exa API. Use when searching the web, finding code examples/docs, researching companies, crawling URLs, or running deep AI research tasks. Triggers on: web search, find code, research company, crawl page, people search.
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
Ask the user structured questions (single choice, multi-select, or free text) using the ask_questions tool. Use this when you need clear, normalized answers.
Unified browser automation skill. Single entry point for Rodney CLI, agent-browser CLI, dev-browser (TypeScript/Playwright), and browser-tools helper scripts.
Query up-to-date library documentation and code examples using the Context7 MCP server. Requires CONTEXT7_API_KEY.
Methodical investigation and root-cause analysis of bugs and issues before proposing solutions. Use when asked to investigate a bug, diagnose an issue, find the root cause of a problem, debug unexpected behavior, trace an error, or figure out why something is broken. Enforces hypothesis-driven debugging and avoids premature fixes.
Quick patch version bump workflow — run tests, bump version in package.json and all version references, commit, push, relink binaries, and verify. Use when asked to bump the version, do a patch release, increment the version number, cut a patch, or publish a new version.
Create well-structured atomic git commits from uncommitted changes using conventional commit messages. Use when asked to commit, stage, create commits, clean up uncommitted work, or prepare changes for push. Handles grouping related changes into logical commits and writing proper commit messages.
| name | exa-search |
| description | Web search, code context, company research, and deep research via Exa API. Use when searching the web, finding code examples/docs, researching companies, crawling URLs, or running deep AI research tasks. Triggers on: web search, find code, research company, crawl page, people search. |
Search the web and extract content via Exa's AI-powered search API.
mcporter install exa-cli
exa-cliAll commands support --output json for machine-readable output.
# Basic search
exa-cli web-search-exa --query "latest AI news"
# With options
exa-cli web-search-exa --query "React hooks tutorial" --num-results 5 --type fast
Find code examples, docs, and solutions from GitHub, Stack Overflow, and official docs.
exa-cli get-code-context-exa --query "Node.js streams examples"
exa-cli get-code-context-exa --query "Python pandas filtering" --tokens-num 10000
exa-cli company-research-exa --company-name "Anthropic"
exa-cli company-research-exa --company-name "OpenAI" --num-results 5
Extract full content from a specific URL.
exa-cli crawling-exa --url "https://example.com/article"
exa-cli crawling-exa --url "https://docs.example.com" --max-characters 5000
Find professionals and their profiles.
exa-cli people-search-exa --query "AI researchers at Google"
Full control over filters, domains, dates, and content options.
exa-cli web-search-advanced-exa --query "machine learning" \
--category "research paper" \
--include-domains "arxiv.org,github.com" \
--num-results 10
Categories: company, research paper, news, pdf, github, tweet, personal site, people, financial report
Start an AI research agent for complex questions (15s-2min).
# Start research
exa-cli deep-researcher-start --instructions "Compare transformer architectures for NLP"
# Check status (use returned task ID)
exa-cli deep-researcher-check --task-id "abc123"
Models: exa-research (faster, default) | exa-research-pro (comprehensive)
deep-researcher-check