AGENT SKILL

keyword-extractor

Extracts up to 50 highly relevant SEO keywords from text. Use when user wants to generate or extract keywords for given text.

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
keyword-extractor
risk
safe
source
original
date_added
2026-03-11
description
Extracts up to 50 highly relevant SEO keywords from text. Use when user wants to generate or extract keywords for given text.

03 SKILL.md 正文

Keyword Extractor

Extracts max 50 relevant keywords from text and formats them in a strict machine-ready structure.


QUICK START

Jump to any section:

  1. CORE MANDATE – Output rules and formatting
  2. WHEN TO USE – Trigger conditions for this skill
  3. KEYWORD QUALITY RULES – Priorities and forbidden keywords
  4. WORKFLOW – Step-by-step generation and processing
  5. FAILURE HANDLING – Short text or edge cases

CORE MANDATE

Return exactly one comma-separated line of keywords, following these rules:

  • max 50 keywords
  • ordered by relevance
  • all lowercase
  • no duplicates or near-duplicates
  • mix of single words and 2–4 word phrases
  • no numbering, bullets, explanations, or trailing period

When to Use

Use this skill when the user wants to generate or extract SEO-friendly keywords or tags from text including:

  • Extracting keywords or tags for any given text or paragraph
  • Creating comma-separated keywords or tags suitable for SEO, search, or metadata
  • Generating topic-specific keywords or tags based on the content’s main subjects and concepts

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:

  • Summaries or paraphrasing requests
  • Text analysis without keyword generation

KEYWORD QUALITY RULES

Prefer noun phrases over verbs or adjectives. Prefer keywords useful for:

  • SEO and search
  • tagging
  • metadata

Prioritize:

  • domain terminology
  • meaningful nouns
  • search phrases
  • entities
  • technical concepts

Avoid weak keywords like:

  • things and various topics
  • general concepts
  • important ideas
  • methods

IMPORTANT: Each keyword must strictly represent a phrase that a user would type into a search engine


WORKFLOW

Step 1 — Analyze

Identify:

  • main subject
  • key topics
  • domain terminology
  • entities
  • concepts

Ignore filler words.


Step 2 — Generate Keywords

Generate up to 50 strictly SEO-friendly keywords directly from the text.

Include:

  • core topics
  • domain terminology
  • related concepts
  • common search queries

Allowed formats:

  • single words
  • 2 word phrases
  • 3 word phrases
  • 4 word phrases

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.


Step 3 — Rank

Order keywords by SEO importance using these signals:

  1. main topic of the text
  2. high-value domain terminology
  3. technologies, tools, or entities mentioned
  4. common search queries related to the topic
  5. supporting contextual topics

Most important keywords should always appear first.


Step 4 — Normalize

Ensure:

  • lowercase, comma separated, no duplicates
  • ≤50 keywords
  • Remove near-duplicate keywords that represent the same concept.
  • Keep only the most common search phrase.
  • If two keywords represent the same concept, keep only the more common search phrase.

Step 5 — Validate

Before returning output ensure:

  • keyword_count <= 50
  • no duplicates and near-duplicates
  • all lowercase and comma separated
  • no trailing period
  • each keyword is a clear searchable topic
  • keywords do not exceed 4 words

If any rule fails regenerate the list.


FAILURE HANDLING

If text is very short, infer likely topics and still generate keywords. Never exceed 50 keywords.


Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1