aiskillstore/marketplace / skills/aaron-he-zhu/keyword-research
keyword-research
VerifiedUse when the user asks to "find keywords", "挖词", or "搜什么词"; prioritizes search volume, keyword difficulty, intent, and topic clusters from provided or connected data. Not for competitor-relative coverage gaps — use content-gap-analysis. 关键词研究/内容选题
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.9 KB |
| references/example-report.md | markdown | 3.6 KB |
| references/instructions-detail.md | markdown | 4.5 KB |
| references/keyword-intent-taxonomy.md | markdown | 4.5 KB |
| references/keyword-prioritization-framework.md | markdown | 1.9 KB |
| references/topic-cluster-templates.md | markdown | 4.2 KB |
| skill-report.json | config | 31.0 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-12T12:38:14.528Z",
"slug": "aaron-he-zhu-keyword-research",
"source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/seo-geo/research/keyword-research",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "3c79d090ffaf9f3d47fceb7d662b0752a8e822597c1ce6918b7cd8accce21fe4",
"tree_hash": "341dabaf872f88b19bb9df9d19f1e2df7e1a4826017554529f13096a1a5a8c82",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "keyword-research",
"description": "Researches and prioritizes SEO keywords using supplied metrics, search intent, opportunity scoring, GEO signals, and topic clusters.",
"summary": "Builds evidence-labeled keyword priorities and content plans from seed topics and available search data.",
"icon": "📦",
"version": "13.0.2",
"author": "aaron-he-zhu",
"license": "Apache-2.0",
"category": "research",
"tags": [
"keyword-research",
"seo",
"search-intent",
"topic-clusters",
"content-planning"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network",
"filesystem"
]
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "Most alerts are false positives caused by Markdown code fences, inline code, documentation links, and repository metadata. Three findings are confirmed because the instructions execute external Python connectors that contact third-party services. No prompt injection or malicious intent was found.",
"remediation": [
{
"issue": "External connector commands run scripts outside the reviewed skill files and send query data to third-party services.",
"suggestion": "Require user confirmation before execution, validate arguments, document each destination, and include reviewed connector scripts with the published package.",
"severity": "medium"
},
{
"issue": "The Google Autocomplete helper uses an unofficial endpoint that may create privacy, reliability, or terms-of-service concerns.",
"suggestion": "Disclose the endpoint before use, avoid sensitive queries, apply rate limits, and provide a supported alternative.",
"severity": "medium"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 22,
"line_end": 24
},
{
"file": "SKILL.md",
"line_start": 24,
"line_end": 26
},
{
"file": "SKILL.md",
"line_start": 26,
"line_end": 28
},
{
"file": "SKILL.md",
"line_start": 28,
"line_end": 32
},
{
"file": "SKILL.md",
"line_start": 32,
"line_end": 36
},
{
"file": "SKILL.md",
"line_start": 36,
"line_end": 36
},
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 48
},
{
"file": "SKILL.md",
"line_start": 50,
"line_end": 50
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 54
},
{
"file": "SKILL.md",
"line_start": 54,
"line_end": 54
},
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 64
},
{
"file": "SKILL.md",
"line_start": 64,
"line_end": 64
},
{
"file": "SKILL.md",
"line_start": 73,
"line_end": 97
},
{
"file": "SKILL.md",
"line_start": 97,
"line_end": 97
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 10,
"line_end": 10
},
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 13
}
]
},
{
"factor": "filesystem",
"evidence": [
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 38
},
{
"file": "SKILL.md",
"line_start": 42,
"line_end": 42
},
{
"file": "SKILL.md",
"line_start": 46,
"line_end": 46
},
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 48
},
{
"file": "SKILL.md",
"line_start": 97,
"line_end": 97
},
{
"file": "SKILL.md",
"line_start": 109,
"line_end": 109
}
]
}
],
"static_findings": [
{
"id": "blocker:references/instructions-detail.md:40:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "references/instructions-detail.md",
"line_start": 40,
"line_end": 41,
"snippet": "- [keyword] for small business"
},
{
"id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 22,
"line_end": 24,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 24,
"line_end": 26,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 26,
"line_end": 28,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 28,
"line_end": 32,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 32,
"line_end": 36,
"snippet": "**Expected output**: a prioritized keyword brief plus the standard handoff summary for `memory/resea"
},
{
"id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 36,
"line_end": 36,
"snippet": "- **Promotes**: durable keyword priorities, competitor facts, and pending strategy decisions to `mem"
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 48,
"line_end": 48,
"snippet": "**Zero-dependency local helper** (no tool needed): `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connector"
},
{
"id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 50,
"line_end": 50,
"snippet": "**Keyless live-SERP sampling**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/firecrawl.py\" sea"
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 52,
"line_end": 54,
"snippet": "**Keyless topic-demand proxy**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/pageviews.py\" \"<T"
},
{
"id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 54,
"line_end": 54,
"snippet": "**Striking-distance shortcut** (when `~~search console` is connected): before broad discovery, mine "
},
{
"id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 58,
"line_end": 64,
"snippet": "When a user requests keyword research, run eight phases and announce each as `[Phase X/8: Name]`:"
},
{
"id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 64,
"line_end": 64,
"snippet": "5. **Score** — assign difficulty (1-100) and compute `Opportunity = (Volume × Intent Value) / Diffic"
},
{
"id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 73,
"line_end": 97,
"snippet": "When you have richer signals than volume/difficulty alone, add a second pass on top of the `Opportun"
},
{
"id": "external_commands:SKILL.md:97:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 97,
"line_end": 97,
"snippet": "Write path: `memory/research/keyword-research/YYYY-MM-DD-<topic>.md`; promote durable keyword priori"
},
{
"id": "network:SKILL.md:10:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 10,
"line_end": 10,
"snippet": "homepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\""
},
{
"id": "network:SKILL.md:13:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 13,
"line_end": 13,
"snippet": "metadata: {\"author\": \"aaron-he-zhu\", \"version\": \"17.0.0\", \"discipline\": \"seo-geo\", \"phase\": \"researc"
},
{
"id": "filesystem:SKILL.md:38:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 38,
"line_end": 38,
"snippet": "- **Primary next skill**: [competitor-analysis](../competitor-analysis/SKILL.md) when the keyword se"
},
{
"id": "filesystem:SKILL.md:42:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 42,
"line_end": 42,
"snippet": "> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill"
},
{
"id": "filesystem:SKILL.md:46:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 46,
"line_end": 46,
"snippet": "Optional integrations: ~~SEO tool, ~~search console. Without tools, ask for seed keywords, audience,"
},
{
"id": "filesystem:SKILL.md:48:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 48,
"line_end": 48,
"snippet": "**Zero-dependency local helper** (no tool needed): `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connector"
},
{
"id": "filesystem:SKILL.md:97:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 97,
"line_end": 97,
"snippet": "Write path: `memory/research/keyword-research/YYYY-MM-DD-<topic>.md`; promote durable keyword priori"
},
{
"id": "filesystem:SKILL.md:109:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 109,
"line_end": 109,
"snippet": "Primary: [competitor-analysis](../competitor-analysis/SKILL.md). Also: [content-gap-analysis](../con"
}
],
"finding_verdicts": [
{
"id": "blocker:references/instructions-detail.md:40:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 39-40 contain generic long-tail keyword templates. They do not instruct network reconnaissance or target any host."
},
{
"id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 22-24 are a fenced example prompt. Markdown backticks do not execute Ruby or shell commands."
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 24-26 only close one Markdown prompt block and open another. No executable command appears."
},
{
"id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 26-28 are a fenced natural-language prompt about competitor keywords. The backticks are Markdown delimiters."
},
{
"id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 28 closes a Markdown code fence before explanatory prose. It does not invoke a shell."
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Lines 32-36 describe expected output and memory paths using inline Markdown code. They contain no command execution."
},
{
"id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 36 lists documented memory destinations in inline code. No Ruby or shell execution is present."
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.96,
"reason": "Line 48 directs execution of a Python connector that queries an unofficial Google Autocomplete endpoint. This creates real external-command and network exposure.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.96,
"reason": "Line 50 directs execution of a Python Firecrawl connector for live search. The command runs code outside the reviewed files and contacts a third party.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.96,
"reason": "Line 52 directs execution of a Python pageviews connector with a topic argument. This is intentional command execution with external network access.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 54 uses inline code to name a search-console integration and API parameter. It does not provide or execute a shell command."
},
{
"id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 58-64 use inline Markdown for phase labels and a scoring formula. No executable shell syntax is present."
},
{
"id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 64 presents a mathematical opportunity formula in inline code. It is documentation, not command execution."
},
{
"id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 73-97 describe scoring, funnel stages, references, and save paths. Inline backticks format prose and do not execute commands."
},
{
"id": "external_commands:SKILL.md:97:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 97 formats an intended output path with Markdown backticks. It contains no shell invocation."
},
{
"id": "network:SKILL.md:10:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 10 is repository homepage metadata pointing to the skill author's GitHub project. It does not initiate a request or transmit data."
},
{
"id": "network:SKILL.md:13:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 13 repeats the public GitHub homepage in package metadata. It is descriptive metadata without network behavior."
},
{
"id": "filesystem:SKILL.md:38:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 38 is a relative Markdown link to a sibling skill. It does not read, write, or traverse the filesystem at runtime."
},
{
"id": "filesystem:SKILL.md:42:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 42 is a documentation link to a repository reference file. The parent-directory segments are static link resolution, not traversal input."
},
{
"id": "filesystem:SKILL.md:46:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 46 links to CONNECTORS.md using a repository-relative path. It performs no dynamic filesystem operation."
},
{
"id": "filesystem:SKILL.md:48:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The parent-directory sequence on line 48 appears only in a static README link. The command uses CLAUDE_PLUGIN_ROOT and contains no traversal segment."
},
{
"id": "filesystem:SKILL.md:97:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "Line 97 specifies a constrained memory output path and links to repository documentation. No user-controlled parent traversal is present."
},
{
"id": "filesystem:SKILL.md:109:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 109 contains relative Markdown links to sibling skills. These links do not perform runtime filesystem traversal."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "**Zero-dependency local helper** (no tool needed): `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connector",
"locations": [
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 48
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.96,
"confidence_reasoning": "Line 48 directs execution of a Python connector that queries an unofficial Google Autocomplete endpoint. This creates real external-command and network exposure."
},
{
"title": "Ruby/shell backtick execution",
"description": "**Keyless live-SERP sampling**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/firecrawl.py\" sea",
"locations": [
{
"file": "SKILL.md",
"line_start": 50,
"line_end": 50
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.96,
"confidence_reasoning": "Line 50 directs execution of a Python Firecrawl connector for live search. The command runs code outside the reviewed files and contacts a third party."
},
{
"title": "Ruby/shell backtick execution",
"description": "**Keyless topic-demand proxy**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/pageviews.py\" \"<T",
"locations": [
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 54
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.96,
"confidence_reasoning": "Line 52 directs execution of a Python pageviews connector with a topic argument. This is intentional command execution with external network access."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 6,
"total_lines": 553,
"audit_model": "codex",
"audited_at": "2026-07-12T12:38:14.528Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Prioritize SEO Keywords and Topic Clusters",
"value_statement": "Keyword lists often lack reliable priorities, intent labels, and content direction. This skill scores available data and organizes opportunities into actionable clusters and calendars.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"keyword research",
"SEO keyword planning",
"search intent",
"topic clusters",
"long-tail keywords",
"GEO content",
"content calendar"
],
"actual_capabilities": [
"Expands seed topics through product, problem, audience, industry, modifier, and long-tail patterns.",
"Classifies keywords by informational, navigational, commercial, or transactional intent.",
"Calculates opportunity scores from supplied volume, difficulty, and intent values.",
"Labels metrics as measured, user-provided, estimated, or unavailable.",
"Flags question, definition, comparison, list, and how-to queries for GEO planning.",
"Groups priorities into pillar pages, cluster content, and a recommended publishing calendar."
],
"limitations": [
"It cannot verify search volume or difficulty without connected tools or supplied data.",
"Model estimates are directional and must not be treated as measured metrics.",
"Competitor-relative coverage analysis belongs in a separate content-gap workflow.",
"Optional live-data helpers depend on external services, availability, and usage policies."
],
"use_cases": [
{
"title": "Plan a New SEO Topic",
"description": "Turn a seed topic into prioritized keywords, intent groups, and an initial content sequence.",
"target_user": "Content strategist"
},
{
"title": "Find Revenue-Focused Opportunities",
"description": "Rank commercial and transactional terms using available demand, difficulty, and business relevance signals.",
"target_user": "Growth marketer"
},
{
"title": "Build a Publishable Topic Cluster",
"description": "Map a pillar page, supporting articles, internal links, and a practical release cadence.",
"target_user": "SEO lead"
}
],
"prompt_templates": [
{
"title": "Expand a Seed Topic",
"prompt": "Research keywords for [topic] in [market and language]. Group ideas by search intent and label every metric by evidence source.",
"scenario": "Beginner keyword discovery from one clear seed."
},
{
"title": "Prioritize Product Keywords",
"prompt": "Research [product or service] for [audience]. Prioritize quick wins, growth terms, and GEO opportunities using my supplied metrics: [metrics].",
"scenario": "Intermediate planning with audience and metric context."
},
{
"title": "Create a Topic Cluster",
"prompt": "Build a topic cluster for [pillar topic]. Include primary and secondary keywords, intent, content format, internal links, and publishing order.",
"scenario": "Structured content architecture for an established topic."
},
{
"title": "Apply Advanced Opportunity Scoring",
"prompt": "Score these keywords using volume, difficulty, intent, CPC, trend, current rank, and authority: [keyword data]. Explain impact and confidence separately.",
"scenario": "Advanced prioritization with richer first-party or tool data."
}
],
"output_examples": [
{
"input": "Research keywords for project management software serving small businesses.",
"output": [
"Quick win: project management for small teams, commercial intent, with supplied volume 1,200 and difficulty 28.",
"Pillar: project management for small business. Clusters cover task tracking, remote teams, templates, and software comparisons.",
"Publish the commercial landing page first, then support it with lower-difficulty instructional articles."
]
},
{
"input": "Prioritize my Search Console queries ranking between positions 5 and 20.",
"output": [
"First priority: terms with measured impressions, strong business relevance, and positions closest to page one.",
"Separate optimization candidates from queries requiring new pages.",
"Mark missing volume or difficulty as unavailable until a trusted source supplies it."
]
},
{
"input": "Build a GEO-focused keyword plan for payroll compliance software.",
"output": [
"Lead with definitions, jurisdiction comparisons, deadlines, checklists, and concise compliance questions.",
"Use authoritative sources and structured answers for factual claims.",
"Connect informational pages to commercial comparison and demo pages through relevant internal links."
]
}
],
"best_practices": [
"Provide audience, market, language, business goal, domain strength, and trusted metrics before scoring.",
"Verify intent against current search results when live data is available.",
"Refresh priorities quarterly and after meaningful ranking, product, or market changes."
],
"anti_patterns": [
"Do not present inferred volume, difficulty, or trends as measured data.",
"Do not prioritize high volume without checking intent, relevance, and ranking feasibility.",
"Do not create thin cluster pages when one stronger page can satisfy the same intent."
],
"faq": [
{
"question": "Does this skill provide live search volume?",
"answer": "Only when a connected source or user-supplied export provides it. Otherwise, volume is unavailable or clearly estimated."
},
{
"question": "How does the skill classify search intent?",
"answer": "It uses query signals and, when available, current search results to assign informational, navigational, commercial, or transactional intent."
},
{
"question": "What is the opportunity score?",
"answer": "It combines volume, intent value, and difficulty to compare keywords. Richer data can add impact and confidence scoring."
},
{
"question": "Can it analyze competitor keyword gaps?",
"answer": "It can use supplied competitor facts, but dedicated competitor-relative coverage gaps require a content-gap analysis workflow."
},
{
"question": "What does GEO opportunity mean?",
"answer": "It identifies queries suited to concise, structured answers, including definitions, comparisons, lists, questions, and how-to content."
},
{
"question": "Can it save the research?",
"answer": "Yes. The workflow defines a dated research path and reusable summaries when the host permits filesystem writes."
}
]
},
"file_structure": [
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "example-report.md",
"type": "file",
"path": "references/example-report.md",
"lines": 97
},
{
"name": "instructions-detail.md",
"type": "file",
"path": "references/instructions-detail.md",
"lines": 132
},
{
"name": "keyword-intent-taxonomy.md",
"type": "file",
"path": "references/keyword-intent-taxonomy.md",
"lines": 68
},
{
"name": "keyword-prioritization-framework.md",
"type": "file",
"path": "references/keyword-prioritization-framework.md",
"lines": 40
},
{
"name": "topic-cluster-templates.md",
"type": "file",
"path": "references/topic-cluster-templates.md",
"lines": 106
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 110
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate 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. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |