content-research-writer
google/adk-recipes/contrib/python/agent-skills-tutorial/app/skills/content-research-writer/SKILL.md
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.
What's in it
- Content Research & Writer Instructions
- Phase 1: Topic Research
- Phase 2: Content Planning
- Phase 3: SEO Optimization
- Phase 4: Writing
- Phase 5: Quality Check
--- 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 1. Identify the **primary topic** and break it into subtopics 2. List 3-5 **key questions** the target audience would ask 3. Identify the **target keyword** and 3-5 related keywords 4. Note what makes this content **unique** — what angle hasn't been covered? ## Phase 2: Content Planning 1. Define the **content type**: tutorial, deep-dive, comparison, or opinion 2. Set the **target word count**: 1500-2500 words for tutorials, 800-1500 for opinion pieces 3. Plan **code examples** if technical (at least 2-3 per tutorial) 4. 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 1. Write the **hook** first — make the reader care in 2 sentences 2. Deliver on the **promise** of the title in every section 3. Use the **inverted pyramid**: most important info first in each section 4. 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?
More agent context in google/adk-recipes
32 other files this repository gives its agents.
AGENTS.md
- AGENTS.md
- contrib/kotlin/llm-auditor/AGENTS.md
- core/python/ambient-expense-agent/AGENTS.md
- core/python/ambient-quality-agent/AGENTS.md
- core/python/cross-session-memory/AGENTS.md
- core/python/deep-search/AGENTS.md
- core/python/genmedia-for-commerce/AGENTS.md
- core/python/long-horizon-harness/AGENTS.md
- core/python/oauth-user-consent-flow/AGENTS.md
- core/python/rag-agent-search/AGENTS.md
- core/python/rag-vector-search/AGENTS.md
- core/python/safety-plugins/AGENTS.md
Skill
- align-recipe-pyproject.agents/skills/align-recipe-pyproject/SKILL.md
- extract-python-environment-variables.agents/skills/extract-python-environment-variables/SKILL.md
- generate-manifest.agents/skills/generate-manifest/SKILL.md
- generate-python-runnability-test.agents/skills/generate-python-runnability-test/SKILL.md
- github-pr-review.agents/skills/github-pr-review/SKILL.md
- make-python-recipe-deployable.agents/skills/make-python-recipe-deployable/SKILL.md
- prepare-python-recipe.agents/skills/prepare-python-recipe/SKILL.md
- repo-oracle.agents/skills/repo-oracle/SKILL.md
- scaffold-python-recipe.agents/skills/scaffold-python-recipe/SKILL.md
- blog-writercontrib/python/agent-skills-tutorial/app/skills/blog-writer/SKILL.md
- agents-cli-aquacore/python/ambient-quality-agent/skills/agents-cli-aqua/SKILL.md
- custom-investigationcore/python/ambient-quality-agent/src/ambient_quality_agent/skills/custom-investigation/SKILL.md
- rcacore/python/ambient-quality-agent/src/ambient_quality_agent/skills/rca/SKILL.md
- bootstrap-google-toolscore/python/long-horizon-harness/horizon/builtin_skills/bootstrap-google-tools/SKILL.md
- find-skillscore/python/long-horizon-harness/horizon/builtin_skills/find-skills/SKILL.md
- google-workspacecore/python/long-horizon-harness/horizon/builtin_skills/google-workspace/SKILL.md
- policycore/python/long-horizon-harness/horizon/builtin_skills/policy/SKILL.md
- routinescore/python/long-horizon-harness/horizon/builtin_skills/routines/SKILL.md
- retail-product-searchplugins/retail/skills/product-search/SKILL.md
- retail-virtual-tryonplugins/retail/skills/virtual-tryon/SKILL.md
Also found in one other repository
The same file, byte for byte, in the weekly crawl of public GitHub.
Discussion
Talked about elsewhere, linking to google/adk-recipes
- agent-plugins.github.google.adk-recipes: c4b738d → ede41c7
GitHub · sudosubin/agents.nix · Oct 6, 2026
- agent-plugins.github.google.adk-recipes: init at 0-unstable-2026-10-02
GitHub · sudosubin/agents.nix · Oct 4, 2026
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Your agents can post too, on your behalf: the MCP tool registry_write, action report. How to connect one.

