SEO Geo
ReScienceLab/opc-skills
SEO & GEO (Generative Engine Optimization) for websites. An agent skill from ReScienceLab/opc-skills.
When the user wants to understand or optimize for SERP feature types (PAA, sitelinks, rich results, AI Overviews).
Install Serp Features
$ npx skills add kostja94/marketing-skills --skill serp-features -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kostja94/marketing-skills serp-features --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/seo/on-page/serp-features .claude/skills/serp-features && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "serp-features" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/seo/on-page/serp-features into .claude/skills/serp-features/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serp-features", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/kostja94/marketing-skills/tree/main/skills/seo/on-page/serp-featuresType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kostja94/marketing-skills --skill serp-features -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kostja94/marketing-skills serp-features --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/seo/on-page/serp-features .agents/skills/serp-features && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "serp-features" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/seo/on-page/serp-features into .agents/skills/serp-features/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serp-features", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kostja94/marketing-skills --skill serp-features -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kostja94/marketing-skills serp-features --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/seo/on-page/serp-features .cursor/skills/serp-features && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "serp-features" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/seo/on-page/serp-features into .cursor/skills/serp-features/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serp-features", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/kostja94/marketing-skills.git --path skills/seo/on-page/serp-features--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kostja94/marketing-skills --skill serp-features -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kostja94/marketing-skills serp-features --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/seo/on-page/serp-features .gemini/skills/serp-features && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "serp-features" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/seo/on-page/serp-features into .gemini/skills/serp-features/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serp-features", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install kostja94/marketing-skills serp-featuresInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add kostja94/marketing-skills --skill serp-features -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/seo/on-page/serp-features .github/skills/serp-features && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "serp-features" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/seo/on-page/serp-features into .github/skills/serp-features/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serp-features", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kostja94/marketing-skills --skill serp-features -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kostja94/marketing-skills serp-features --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kostja94/marketing-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/seo/on-page/serp-features .opencode/skills/serp-features && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "serp-features" agent skill from https://github.com/kostja94/marketing-skills/tree/main/skills/seo/on-page/serp-features into .opencode/skills/serp-features/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serp-features", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
serp-features- GitHub stars
- 1k
- Token cost
- ~3.5k tokens
- SKILL.md length
- 1,516 words
- Files
- 1
- Skills in repo
- 102
- Repo updated
- First seen
- Licence
- MIT
At a glance
When the user wants to understand or optimize for SERP feature types (PAA, sitelinks, rich results, AI Overviews).
- Works in 6 steps: Organic Enhancements (Achievable) → Universal Results → Knowledge / Entity (Limited Obtainability) → …
- Wants to understand
- SKILL.md covers Scope, What Is a SERP Feature?, Rich Results vs Featured… and SERP Features ↔ Schema ↔ Rich…, plus 8 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Serp Features is an agent skill from kostja94/marketing-skills. When the user wants to understand or optimize for SERP feature types (PAA, sitelinks, rich results, AI Overviews). Also use when the user mentions "SERP," "SERP features," "search result features," "People Also Ask," "PAA," "sitelinks," "knowledge panel," "local pack," "rich results," "zero-click," "SERP types," "AI Overviews," "Bing Copilot," or "Yandex AI." For JSON-LD and rich result implementation, use schema-markup. For organic strategy and roadmap, use seo-strategy.
Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Marketing & SEO, covering Schema markup. The repository describes itself as: Agent Skills for Marketing — SEO, Social, Influencer & More. 160+ open-source skills for SEO, content, 40+ page types, paid ads, channels, and strategies. Add project context… The licence is MIT.
When your agent uses it
- Wants to understand
- Optimize for SERP feature types (PAA
- The user mentions SERP
- Search result features
Example prompts
- “SERP features,”
- “search result features,”
- “People Also Ask,”
- “/serp-features”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 8dd89c5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
onely.comseranking.comsearchengineland.comyandex.comgeneo.appaiso-hub.comsearch.google.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Serp Features loads about 3.5k tokens when it runs. Until then it costs about 123 tokens; SKILL.md has 1,516 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from kostja94/marketing-skills at commit 8dd89c5, republished under its MIT licence (© kostja94). 1,516 words, ~3,529 tokens.
Download SKILL.mdSave it as
.claude/skills/serp-features/SKILL.md (or your agent's skills folder).- name
- serp-features
- description
- When the user wants to understand or optimize for SERP feature types (PAA, sitelinks, rich results, AI Overviews). Also use when the user mentions "SERP," "SERP features," "search result features," "People Also Ask," "PAA," "sitelinks," "knowledge panel," "local pack," "rich results," "zero-click," "SERP types," "AI Overviews," "Bing Copilot," or "Yandex AI." For JSON-LD and rich result implementation, use schema-markup. For organic strategy and roadmap, use seo-strategy.
- metadata.version
- 1.1.0
SEO On-Page: SERP Features
Guides SERP (Search Engine Results Page) features: types, obtainability, and optimization. ~98.5% of Google's first page includes SERP features; rich results receive ~58% of clicks vs 41% for standard listings. Understanding SERP features helps prioritize keywords and content strategy.
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Scope
- SERP feature types: Organic enhancements, universal results, paid, knowledge
- Obtainability: Which features are achievable; which require authority/partnerships
- Optimization: Content, schema, and structure for each feature type
- Impact: CTR, zero-click, traffic implications
What Is a SERP Feature?
A SERP feature is any result on a search results page that is not a traditional organic blue link. Features provide quick answers, visual enhancements, or alternative result types (images, local, news, etc.).
Rich Results vs Featured Snippets
| Dimension | Rich Results | Featured Snippets |
|---|---|---|
| Location | Within standard organic listings; enhance a blue link | Above organic results; "position zero" |
| Generation | Structured data (Schema/JSON-LD) added by site owner | Google extracts from page content; no schema required |
| Display | Star ratings, prices, images, breadcrumbs, FAQ dropdowns | Extracted text in highlighted box; paragraph, list, table, or video |
| Ranking | Do not require high organic rank to appear | Page must rank in top ~10 for the query |
| Industry | Often content-specific (recipes, products, events, reviews) | Versatile; most industries |
| CTR | Typically increase CTR (up to ~35%); enhanced visibility | Can increase or reduce clicks (zero-click when answer suffices) |
Rich results = schema-powered enhancements to regular listings. Featured snippets = Google-extracted answer boxes at position zero. Both are SERP features; rich results are a subset driven by structured data. Onely, Seranking
SERP Features ↔ Schema ↔ Rich Results (Strongly Related)
SERP features, schema, and rich results are strongly related. Most achievable SERP enhancements depend on or benefit from Schema.org structured data. Schema makes content machine-readable so search engines can extract and display rich results.
| SERP Feature | Schema Type | Relationship |
|---|---|---|
| PAA / FAQ dropdown | FAQPage | Required or strongly recommended; FAQ schema triggers PAA-style display |
| Breadcrumbs | BreadcrumbList | Required; no schema = no breadcrumb rich result |
| Reviews / Stars | AggregateRating, Review | Required; star display depends on review schema |
| Featured Snippet | FAQPage, HowTo, Article | Supporting; schema helps identify extractable blocks; not required |
| Sitelinks | WebSite + SearchAction | Supporting; SearchAction can enable sitelinks |
| Video | VideoObject | Required; video thumbnail; Google prioritizes YouTube. See video-optimization |
| Product | Product, Offer | Required; shopping results |
| Recipe | Recipe | Required; recipe rich result |
| Job | JobPosting | Required; Google Jobs |
| Event | Event | Required; event rich result |
| In-Depth Articles | Article + author | Supporting; Article schema, authorship |
Workflow: When targeting a SERP feature, check schema-markup for the schema type; after implementing schema, use serp-features to assess display and optimization.
SERP Feature Categories
1. Organic Enhancements (Achievable)
| Feature | Description | Obtainability |
|---|---|---|
| Featured Snippet | Direct answer above organic results; paragraph, list, or table | Content that answers query in 40–60 words; positions 2–5 often win. See featured-snippet |
| People Also Ask (PAA) | Expandable question boxes with brief answers | FAQ-style content; FAQ schema; match question phrasing |
| Sitelinks | Additional links below main result (brand queries) | Site structure, internal links, SearchAction schema; mainly branded |
| Reviews / Stars | Star ratings on product/service results | Review schema (AggregateRating); eligibility varies by vertical |
| Breadcrumbs | Path shown in result | BreadcrumbList schema; clear site structure |
| Video | Video thumbnail in results | Video schema; Google prioritizes YouTube; see video-optimization |
| Image Pack | Horizontal row of images | Alt, captions, file names, responsive; see image-optimization |
2. Universal Results
| Feature | Description | Obtainability |
|---|---|---|
| News Box | Time-sensitive news block | Google News inclusion; publisher eligibility |
| In-Depth Articles | Long-form block (broad terms) | Large publishers; 2000–5000 words; authorship, Article schema |
| Tweet | Twitter results in SERP | Brand presence; not directly controllable |
| Shopping | Product listings with images/price | Paid (PLAs) or Product schema for organic |
3. Knowledge / Entity (Limited Obtainability)
| Feature | Description | Obtainability |
|---|---|---|
| Knowledge Panel | Entity info (brand, person, place) | WikiData, partnerships; see entity-seo |
| Knowledge Card | Top-of-SERP semantic answer | Same as Knowledge Panel |
| Local Pack | 3 local business results + map | Local SEO; GMB, NAP, reviews |
| Local Teaser | Hotels, restaurants with map/sort | Local SEO |
4. Paid
| Feature | Description |
|---|---|
| AdWords (Top/Bottom) | Sponsored results; [Ad] label |
| Shopping (PLAs) | Product ads with images |
| Google Flights | Flight search in SERP |
5. AI Search Summaries (SERP Feature)
AI-generated answer blocks at the top of search results. These are SERP features—they occupy prime SERP real estate and replace or supplement traditional blue links. Optimize via generative-engine-optimization (GEO).
| Engine | Feature | Description | Availability |
|---|---|---|---|
| AI Overviews | Multi-source AI summary at top; Gemini; cites top 10–12 organic results; 2–3 paragraphs or bullets | ~47% US searches; opt-in/experimental in 120+ countries | |
| Bing | Copilot Search | Curated summaries with cited sources; GPT-4; grouped answers with resources per section; follow-up questions in-search | bing.com/copilotsearch; Edge; standard across Bing |
| Yandex | Search with Yandex AI / Neuro | YandexGPT synthesizes from real-time search; cited sources; conversational follow-ups; image upload; Russia-focused | Yandex Browser, Yandex app; Russia location |
| Perplexity | — | Standalone AI search; not a SERP feature; 200B+ URL index; live web search | perplexity.ai |
| ChatGPT | — | Web search via GPTbot; not a SERP feature; high-authority, LLM-friendly content | chat.openai.com |
Source selection: Google pulls from top organic; Bing uses Bing index (9.81% domain overlap with Google); Yandex uses real-time search; Perplexity has independent crawl. AI Overview citations can drive 20–35% higher CTR than equivalent organic positions. SEJ, Yandex, Geneo
6. Other Newer (2025+)
| Feature | Description |
|---|---|
| Related Searches | Alternative queries at bottom |
| People Also Search For (PASF) | Related queries after user bounces from result; 6-8 suggestions; different from PAA; comprehensive content reduces bounce. See faq-page-generator |
Show full SKILL.md (615 more words)Show less
Optimization by Feature
| Feature | Key Actions |
|---|---|
| Featured Snippet | Answer-first (40–60 words); H2/H3; semantic lists/tables. See featured-snippet |
| PAA | FAQ content; FAQ schema; natural question phrasing; faq-page-generator |
| Sitelinks | Clear site structure; internal links; SearchAction; website-structure |
| Reviews | AggregateRating schema; schema-markup |
| Breadcrumbs | BreadcrumbList schema; breadcrumb-generator |
| Video | VideoObject schema; video-optimization; Google prioritizes YouTube |
| Image Pack | Alt, captions, file names, responsive; see image-optimization |
| Local Pack | Local SEO; GMB; NAP consistency |
| AI Overview / Copilot / Yandex AI | GEO; structured content; citable paragraphs; entity signals; see generative-engine-optimization, entity-seo |
Zero-Click: SERP Features That Satisfy Intent Without a Click
Zero-click = user gets the answer directly on the SERP and does not click through to any website. SERP features are a major driver of zero-click—they answer queries in-place, reducing organic traffic to publishers.
SERP Features That Cause Zero-Click
| Feature | Zero-Click Risk | Why |
|---|---|---|
| Featured Snippet | High | Direct answer in position zero; user may not need to visit |
| People Also Ask (PAA) | High | Expandable answers; full answer visible without click |
| AI Overviews | Very high | ~83% of searches with AI Overview may end without click |
| Bing Copilot / Yandex AI | Very high | Full AI summary with sources; answer in-place |
| Knowledge Panel / Card | High | Entity info; no click needed for simple facts |
| Rich results (reviews, recipe) | Medium | Can reduce clicks when answer is complete (e.g. recipe steps) |
Implications
- Traffic: Expect lower organic clicks when zero-click features dominate the SERP
- Strategy: Prioritize citation over click—being cited in AI Overview, Featured Snippet, or PAA still delivers brand visibility and trust
- GEO: Optimize for citation (see generative-engine-optimization) so your content is used even when users don't click
- Keyword research: Screen keywords for zero-click SERP features; adjust traffic forecasts and prioritize commercial/transactional queries where clicks matter more
When Zero-Click Matters Most
- Informational queries ("what is X," "how to Y")—highest zero-click
- Commercial/transactional—users often need to visit (compare, buy)
- Brand queries—sitelinks and Knowledge Panel can still drive clicks to specific pages
SERP Analysis for Strategy
- SERP check: Search target keyword—observe which features appear
- Intent signals: Knowledge card → informational; product lists → commercial; brand → navigational
- Zero-click assessment: Identify features that satisfy intent without click; factor into traffic expectations
- Keyword research: keyword-research uses SERP features (Featured Snippet, PAA, zero-click) in screening
Rich Results: Types & Impact
Rich results are enhanced search listings powered by structured data. They appear within organic positions (unlike Featured Snippets at position zero). High-impact types: Product, Review snippets, HowTo (desktop), Article/News, Video, Recipe, LocalBusiness, Event, Breadcrumb, Sitelinks searchbox, JobPosting. Limited/context-dependent: HowTo (mobile), FAQ (restricted to government/health for many sites), Education Q&A, Course, SoftwareApplication. AISO Hub
Rich results do not directly boost rankings but can increase CTR by up to 35%. They also make content machine-readable for AI Overviews, Gemini, Copilot, and Perplexity. Validate with Google Rich Results Test.
CTR Impact
- Zero-click trade-off: SERP features can increase CTR (rich results, sitelinks) or reduce it (Featured Snippet, PAA, AI Overviews when answer suffices). See Zero-Click section above.
- Rich results: ~58% of clicks vs 41% for standard listings
- Featured snippets: ~42.9% CTR boost; position zero ~35% of clicks when present
- Review stars: Higher CTR
- Sitelinks: Dominate SERP for brand queries; faster path to target page
Output Format
- SERP features present for target keyword
- Zero-click assessment (which features satisfy intent without click)
- Obtainability assessment
- Optimization priorities (schema, content, structure; citation vs click)
- Related skills for each feature
Related Skills
- schema-markup: Strongly related—schema type maps to SERP feature; see mapping table above
- featured-snippet: Featured Snippet / Position Zero optimization
- howto-section-generator: HowTo step sections; list snippets; HowTo vs FAQ in SERP context
- faq-page-generator: PAA optimization; FAQ format
- keyword-research: SERP features in keyword screening
- website-structure: Sitelinks; site architecture
- generative-engine-optimization: AI Overviews, Bing Copilot, Yandex AI; GEO strategy
- image-optimization: Image Pack; alt, captions, file names
- video-optimization: Video SEO; VideoObject; YouTube prioritization
- entity-seo: Knowledge Panel; Organization, Person schema
© kostja94, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/seo/on-page/serp-features of kostja94/marketing-skills.
Open the folder on GitHubat commit 8dd89c5
Compare with similar skills
Serp Features next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Serp Features this skillkostja94/marketing-skills | 1k | — | ~3.5k | Automated safety check: Pass | MIT | |
| SEO GeoReScienceLab/opc-skills | 1.8k | 4 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| GEO-First SEO Audit Toolzubair-trabzada/geo-seo-claude | 11k | — | ~2.8k | Automated safety check: Notes | MIT | |
| Portaljs Add Dcatdatopian/portaljs | 2.4k | 1 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Schema Markupfreekmurze/dotfiles | 1k | 15 repos | ~1.2k | Automated safety check: Pass | None | |
| SEO Optimizerailabs-393/ai-labs-claude-skills | 454 | 1 repos | ~3.2k | Automated safety check: Pass | MIT |
Similar skills
GEO-First SEO Audit Tool
zubair-trabzada/geo-seo-claude
Audits a website for AI search visibility across ChatGPT, Claude, Perplexity and Google AI Overviews while checking traditional SEO, schema and E-E-A-T content quality.
Portaljs Add Dcat
datopian/portaljs
Make a PortalJS portal harvestable by national/EU/US open-data portals — emit standards-compliant DCAT catalog feeds (DCAT 2/3, DCAT-AP, DCAT-US, national profiles) in JSON-LD, Turtle, and RDF/XML…
Schema Markup
freekmurze/dotfiles
When the user wants to add, fix, or optimize schema markup and structured data on their site.
SEO Optimizer
ailabs-393/ai-labs-claude-skills
This skill should be used when analyzing HTML/CSS websites for SEO optimization, fixing SEO issues, generating SEO reports, or implementing SEO best practices.
Geo
liangdabiao/GEO-Content-Optimizer-Skill
完整的 GEO（生成式引擎优化）服务流水线：给一个产品官网 URL 和介绍材料， 做站点诊断与 AI 答案采样、生成带验收标准的执行工单、产出可直接部署的资产 （llms.txt / JSON-LD / 定义块 / FAQ / 内容大纲与初稿）、自动验收工单是否闭环、 并打包成可直接发给客户的交付物。可按周期复跑，做长期 GEO 运营与月报。
More from kostja94/marketing-skills
All 102 skills in this repoGrokipedia Recommendations
kostja94/marketing-skills
When the user wants to add recommendations, links, or content to Grokipedia.
AI Traffic Tracking
kostja94/marketing-skills
When the user wants to track AI search traffic in GA4 or GSC.
Analytics Tracking
kostja94/marketing-skills
When the user wants to set up, audit, or optimize analytics tracking (GA4, events, conversions).
Brand Visual Generator
kostja94/marketing-skills
When the user wants to define, audit, or apply visual identity (typography, colors, spacing, design tokens, frontend aesthetics).
Canonical Tag
kostja94/marketing-skills
When the user wants to configure canonical URLs, fix duplicate content, or consolidate URL signals.
Content Strategy
kostja94/marketing-skills
When the user wants to plan content for SEO, create content calendar, or build topic clusters.
Related
Categories
Questions about Serp Features
What does Serp Features do?
When the user wants to understand or optimize for SERP feature types (PAA, sitelinks, rich results, AI Overviews). Serp Features is an agent skill from kostja94/marketing-skills. When the user wants to understand or optimize for SERP feature types (PAA, sitelinks, rich results, AI Overviews).
When should I use Serp Features?
Serp Features fits situations like: wants to understand; optimize for SERP feature types (PAA; the user mentions SERP; search result features.
How do I install Serp Features in Claude Code?
Run `npx skills add kostja94/marketing-skills --skill serp-features -a claude-code`. Or copy the skill folder (skills/seo/on-page/serp-features in kostja94/marketing-skills) into .claude/skills/serp-features in your project. Claude Code loads it when a task matches its description.
How do I install Serp Features in Codex?
Run `npx skills add kostja94/marketing-skills --skill serp-features -a codex`. Or copy the skill folder (skills/seo/on-page/serp-features in kostja94/marketing-skills) into .agents/skills/serp-features in your project. Codex loads it when a task matches its description.
Can I use Serp Features in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kostja94/marketing-skills --skill serp-features -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/serp-features, .gemini/skills/serp-features, .github/skills/serp-features and .opencode/skills/serp-features in your project.
What does Serp Features need to run?
SKILL.md names no scripts, command-line tools or credentials: Serp Features is instructions for the agent only.
Does Serp Features access the network?
SKILL.md names 7 domains. As links in the text: onely.com, seranking.com, searchengineland.com, yandex.com, geneo.app, aiso-hub.com and search.google.com. This is read from the text; nothing was executed.
Is Serp Features safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Serp Features use?
Serp Features is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Serp Features use?
About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Serp Features?
Skills that share tags, products or a category with Serp Features: SEO Geo (ReScienceLab/opc-skills, 1.8k stars), GEO-First SEO Audit Tool (zubair-trabzada/geo-seo-claude, 11k stars), Portaljs Add Dcat (datopian/portaljs, 2.4k stars) and Schema Markup (freekmurze/dotfiles, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Serp Features?
kostja94 (a GitHub user) maintains it in kostja94/marketing-skills, which has 1,019 GitHub stars. The repository holds 102 skills in this directory. The repository was last updated on October 6, 2026.
Source: kostja94/marketing-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.