Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.
Skill
content-research-writer
Original text · EnglishContent research and SEO writing methodology. Guides the agent through topic research, keyword identification, competitive analysis, and writing SEO-optimized content that ranks well and provides genuine value to readers.
Republished in full under its license, with attribution. The source is authoritative.
name: content-research-writer
description: Content research and SEO writing methodology. Guides the agent through topic research, keyword identification, competitive analysis, and writing SEO-optimized content that ranks well and provides genuine value to readers.
Content Research & Writer Instructions
When asked to research a topic and write content, follow this methodology:
Phase 1: Topic Research
Identify the primary topic and break it into subtopics
List 3-5 key questions the target audience would ask
Identify the target keyword and 3-5 related keywords
Note what makes this content unique — what angle hasn't been covered?
Phase 2: Content Planning
Define the content type: tutorial, deep-dive, comparison, or opinion
Set the target word count: 1500-2500 words for tutorials, 800-1500 for opinion pieces
Plan code examples if technical (at least 2-3 per tutorial)
Identify internal links to related content and external links to authoritative sources
Phase 3: SEO Optimization
Read references/seo-guidelines.md for detailed SEO rules using load_skill_resource.
Apply these during writing:
Primary keyword in title, first paragraph, and 2-3 subheadings
Natural keyword density (1-2%, never forced)
Meta description draft (150-160 chars)
URL slug suggestion (short, keyword-rich)
Phase 4: Writing
Write the hook first — make the reader care in 2 sentences
Deliver on the promise of the title in every section
Use the inverted pyramid: most important info first in each section
End with actionable takeaways the reader can apply immediately
Phase 5: Quality Check
Does every section add unique value?
Are all claims supported by evidence or code?
Would you share this with a colleague? If not, what's missing?
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`,…
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar…
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use after generating code, after accepting AI suggestions, or when reviewing AI-written modules. Also use when code works but feels brittle, when error handling seems thin, when orphaned resources or missing cleanup are suspected, or when the agent claims done but hidden debt may exist. Catches the specific failure patterns AI agents produce that humans would not.