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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/BEKO2210/Firstbrain --skill keyword-extractor命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | keyword-extractor |
| description | > |
| type | skill |
| created | 2026-02-27T00:00:00.000Z |
| domain | business-marketing |
| category | marketing |
| risk | safe |
| source | original |
| tags | ["skill","business-marketing","marketing","keyword","extractor"] |
Extracts max 50 relevant keywords from text and formats them in a strict machine-ready structure.
Jump to any section:
Return exactly one comma-separated line of keywords, following these rules:
Use this skill when the user wants to generate or extract SEO-friendly keywords or tags from text including:
This skill should be triggered for all text-based keyword extraction requests, regardless of phrasing, as long as the goal is SEO, tagging, or metadata generation.
Do NOT trigger this skill for:
Prefer noun phrases over verbs or adjectives. Prefer keywords useful for:
Prioritize:
Avoid weak keywords like:
IMPORTANT: Each keyword must strictly represent a phrase that a user would type into a search engine
Identify:
Ignore filler words.
Generate up to 50 strictly SEO-friendly keywords directly from the text.
Include:
Allowed formats:
Example:
machine learning, neural networks, deep learning models, ai algorithms, data science tools
Avoid vague keywords, filler phrases, adjectives without nouns like:
important methods, different ideas, various techniques, things
Keywords must not exceed 4 words.
Order keywords by SEO importance using these signals:
Most important keywords should always appear first.
Ensure:
Before returning output ensure:
If any rule fails regenerate the list.
If text is very short, infer likely topics and still generate keywords. Never exceed 50 keywords.
