aiskillstore/marketplace / skills/aaron-he-zhu/serp-analysis
serp-analysis
VerifiedUse when the user asks to "analyze the SERP" or "SERP分析"; maps SERP features, layout, ranking factors, search intent, AI Overviews, and snippet opportunities for a query. Not for keyword demand discovery — use keyword-research. SERP分析/搜索结果
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.0 KB |
| references/analysis-templates.md | markdown | 3.3 KB |
| references/example-report.md | markdown | 2.6 KB |
| references/serp-feature-taxonomy.md | markdown | 4.9 KB |
| skill-report.json | config | 33.3 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-12T14:02:46.143Z",
"slug": "aaron-he-zhu-serp-analysis",
"source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/seo-geo/research/serp-analysis",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "8be56dbf45baca714e7faf9b0e6a66ecbfded24f7dc38ed6067f5e0227688f17",
"tree_hash": "b5f6a3ce420ed86e0c24ae133d40855276b4f7c4ed75e7bdc6221a0e4bc2524f",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "serp-analysis",
"description": "Analyzes live or supplied search results to map intent, ranking patterns, SERP features, content requirements, and evidence-based difficulty for target queries.",
"summary": "Builds an evidence-based SERP brief with ranking opportunities, difficulty, and content recommendations.",
"icon": "📦",
"version": "13.0.2",
"author": "aaron-he-zhu",
"license": "Apache-2.0",
"category": "research",
"tags": [
"serp analysis",
"seo research",
"search intent",
"content strategy",
"ai visibility"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network",
"filesystem",
"env_access"
]
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "Two command findings are confirmed because the skill directs agents to execute connector scripts outside the audited package, which also initiate network searches. The other 26 alerts are Markdown fences, documentation links, local output paths, or harmless metadata references, and no semantic threat was found.",
"remediation": [
{
"issue": "The live-search instructions execute connector scripts that are outside the audited skill package.",
"suggestion": "Bundle and review the connector scripts, or use a host-approved search tool with explicit user consent before network access.",
"severity": "medium"
},
{
"issue": "The declared WebFetch tool contract does not cover the documented Python commands.",
"suggestion": "Remove the shell commands or declare the required command and network capabilities so users can make an informed installation decision.",
"severity": "medium"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 25
},
{
"file": "SKILL.md",
"line_start": 25,
"line_end": 27
},
{
"file": "SKILL.md",
"line_start": 27,
"line_end": 29
},
{
"file": "SKILL.md",
"line_start": 29,
"line_end": 33
},
{
"file": "SKILL.md",
"line_start": 33,
"line_end": 37
},
{
"file": "SKILL.md",
"line_start": 37,
"line_end": 37
},
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 49
},
{
"file": "SKILL.md",
"line_start": 51,
"line_end": 51
},
{
"file": "SKILL.md",
"line_start": 82,
"line_end": 84
},
{
"file": "SKILL.md",
"line_start": 84,
"line_end": 88
},
{
"file": "SKILL.md",
"line_start": 88,
"line_end": 90
},
{
"file": "SKILL.md",
"line_start": 90,
"line_end": 94
},
{
"file": "SKILL.md",
"line_start": 94,
"line_end": 96
},
{
"file": "SKILL.md",
"line_start": 96,
"line_end": 100
},
{
"file": "SKILL.md",
"line_start": 100,
"line_end": 102
},
{
"file": "SKILL.md",
"line_start": 102,
"line_end": 116
},
{
"file": "SKILL.md",
"line_start": 116,
"line_end": 116
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 10,
"line_end": 10
},
{
"file": "SKILL.md",
"line_start": 14,
"line_end": 14
}
]
},
{
"factor": "filesystem",
"evidence": [
{
"file": "SKILL.md",
"line_start": 39,
"line_end": 39
},
{
"file": "SKILL.md",
"line_start": 43,
"line_end": 43
},
{
"file": "SKILL.md",
"line_start": 47,
"line_end": 47
},
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 49
},
{
"file": "SKILL.md",
"line_start": 112,
"line_end": 112
},
{
"file": "SKILL.md",
"line_start": 116,
"line_end": 116
},
{
"file": "SKILL.md",
"line_start": 123,
"line_end": 123
},
{
"file": "SKILL.md",
"line_start": 127,
"line_end": 127
}
]
},
{
"factor": "env_access",
"evidence": [
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 49
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 23,
"line_end": 25,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 25,
"line_end": 27,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 27,
"line_end": 29,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 29,
"line_end": 33,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 33,
"line_end": 37,
"snippet": "**Expected output**: a prioritized SERP brief plus the standard handoff summary for `memory/research"
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 37,
"line_end": 37,
"snippet": "- **Promotes**: durable keyword priorities, competitor facts, and pending strategy decisions to `mem"
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 49,
"line_end": 49,
"snippet": "**Zero-dependency live SERP (keyless)**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/firecraw"
},
{
"id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 51,
"line_end": 51,
"snippet": "**Second keyless engine for corroboration**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/tavi"
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 82,
"line_end": 84,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 84,
"line_end": 88,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 88,
"line_end": 90,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 90,
"line_end": 94,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 94,
"line_end": 96,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 96,
"line_end": 100,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:100:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 100,
"line_end": 102,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 102,
"line_end": 116,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 116,
"line_end": 116,
"snippet": "Write path: `memory/research/serp-analysis/YYYY-MM-DD-<topic>.md`; promote durable difficulty/intent"
},
{
"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:14:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 14,
"line_end": 14,
"snippet": "metadata: {\"author\": \"aaron-he-zhu\", \"version\": \"17.0.0\", \"discipline\": \"seo-geo\", \"phase\": \"researc"
},
{
"id": "filesystem:SKILL.md:39:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 39,
"line_end": 39,
"snippet": "- **Primary next skill**: [content-writer](../../build/content-writer/SKILL.md) when the user is rea"
},
{
"id": "filesystem:SKILL.md:43:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 43,
"line_end": 43,
"snippet": "> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill"
},
{
"id": "filesystem:SKILL.md:47:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 47,
"line_end": 47,
"snippet": "Optional integrations: ~~SEO tool, ~~search console, ~~AI monitor. Before fetching third-party SERP "
},
{
"id": "filesystem:SKILL.md:49:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 49,
"line_end": 49,
"snippet": "**Zero-dependency live SERP (keyless)**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/firecraw"
},
{
"id": "filesystem:SKILL.md:112:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 112,
"line_end": 112,
"snippet": "See [references/platforms/youtube.md](../../../references/platforms/youtube.md) for YouTube-as-citat"
},
{
"id": "filesystem:SKILL.md:116:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 116,
"line_end": 116,
"snippet": "Write path: `memory/research/serp-analysis/YYYY-MM-DD-<topic>.md`; promote durable difficulty/intent"
},
{
"id": "filesystem:SKILL.md:123:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 123,
"line_end": 123,
"snippet": "- [YouTube as citation surface](../../../references/platforms/youtube.md) — Video SERP / outlier pac"
},
{
"id": "filesystem:SKILL.md:127:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 127,
"line_end": 127,
"snippet": "Primary: [content-writer](../../build/content-writer/SKILL.md)."
},
{
"id": "env_access:SKILL.md:49:generic-api-secret-keys",
"category": "env_access",
"severity": "high",
"pattern": "Generic API/secret keys",
"file": "SKILL.md",
"line_start": 49,
"line_end": 49,
"snippet": "**Zero-dependency live SERP (keyless)**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/firecraw"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 23-25 are a fenced Markdown example containing a natural-language prompt. They do not invoke Ruby, a shell, or any executable."
},
{
"id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 25 closes a Markdown code fence around a prompt example. No shell expression or command execution is present."
},
{
"id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 27-29 are another fenced natural-language prompt example. The backticks are Markdown formatting, not shell execution."
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 29 closes a Markdown code fence and does not execute its contents. No external command is specified."
},
{
"id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format the memory/research path in prose. The line contains no shell syntax or executable invocation."
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks identify three documentation paths for saved research. They are not Ruby backticks or command substitutions."
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.88,
"reason": "Line 49 instructs the agent to run a Python connector outside this audited skill package and perform a live network search. The connector implementation is unavailable here, so its command and data-handling behavior cannot be verified.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.88,
"reason": "Line 51 instructs the agent to execute another external Python connector that performs network searches and optional answer synthesis. The referenced script is outside the audited files.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 82-84 are a fenced natural-language prompt for comparing keywords. They contain no executable command."
},
{
"id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 84 closes a Markdown prompt fence. It does not perform shell or Ruby execution."
},
{
"id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 88-90 contain a natural-language historical analysis prompt inside a Markdown fence. No external command is invoked."
},
{
"id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 90 is only the closing delimiter for a Markdown prompt example. It has no executable semantics."
},
{
"id": "external_commands:SKILL.md:94:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 94-96 are a fenced natural-language location comparison prompt. They do not contain a program or shell command."
},
{
"id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 96 closes a Markdown code fence and does not execute any content."
},
{
"id": "external_commands:SKILL.md:100:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 100-102 present a natural-language mobile and desktop comparison prompt. The fence is formatting only."
},
{
"id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Line 102 closes the Markdown prompt example. It does not invoke an interpreter or external process."
},
{
"id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Backticks format local output paths in documentation. The line requests a file write but contains no external command."
},
{
"id": "network:SKILL.md:10:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL is project homepage metadata pointing to the author's GitHub repository. It does not trigger a request or transmit data."
},
{
"id": "network:SKILL.md:14:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL appears inside package metadata as the project homepage. It is descriptive metadata, not executable network behavior."
},
{
"id": "filesystem:SKILL.md:39:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The parent-directory sequence is a static Markdown link to a related skill. It is not constructed from user input or used in a filesystem operation."
},
{
"id": "filesystem:SKILL.md:43:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The sequence occurs in a Markdown link to shared documentation. No runtime path resolution or file access instruction is present."
},
{
"id": "filesystem:SKILL.md:47:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The parent-directory paths are fixed links to security and connector documentation. They do not accept user-controlled path segments."
},
{
"id": "filesystem:SKILL.md:49:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The command uses a fixed connector path beneath CLAUDE_PLUGIN_ROOT and the line has no parent-directory traversal. External execution is separately confirmed for this line."
},
{
"id": "filesystem:SKILL.md:112:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is a fixed Markdown link to a YouTube reference document. It does not use untrusted input or perform a filesystem operation."
},
{
"id": "filesystem:SKILL.md:116:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.94,
"reason": "The documented write target stays under memory/research, and the topic placeholder names a report rather than authorizing directory traversal. No parent-directory sequence appears in the write path."
},
{
"id": "filesystem:SKILL.md:123:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The sequence is part of a fixed Markdown link to shared reference material. It is not passed to a filesystem API."
},
{
"id": "filesystem:SKILL.md:127:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The parent-directory path is a static Markdown link to the content-writer skill. It is not a user-controlled file access operation."
},
{
"id": "env_access:SKILL.md:49:generic-api-secret-keys",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The command expands CLAUDE_PLUGIN_ROOT only to locate a connector, while FIRECRAWL_API_KEY is mentioned as an optional configuration name. The line does not read, print, or transmit a secret value."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "**Zero-dependency live SERP (keyless)**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/firecraw",
"locations": [
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 49
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.88,
"confidence_reasoning": "Line 49 instructs the agent to run a Python connector outside this audited skill package and perform a live network search. The connector implementation is unavailable here, so its command and data-handling behavior cannot be verified."
},
{
"title": "Ruby/shell backtick execution",
"description": "**Second keyless engine for corroboration**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connectors/tavi",
"locations": [
{
"file": "SKILL.md",
"line_start": 51,
"line_end": 51
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.88,
"confidence_reasoning": "Line 51 instructs the agent to execute another external Python connector that performs network searches and optional answer synthesis. The referenced script is outside the audited files."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 4,
"total_lines": 416,
"audit_model": "codex",
"audited_at": "2026-07-12T14:02:46.143Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Analyze SERPs and Find Ranking Opportunities",
"value_statement": "Search results change by query, location, device, and time. This skill turns live or supplied SERP evidence into prioritized ranking and content recommendations.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"SERP analysis",
"SEO research",
"search intent analysis",
"SERP feature analysis",
"keyword difficulty",
"AI Overview optimization"
],
"actual_capabilities": [
"Maps organic results, AI Overviews, snippets, People Also Ask, media packs, local packs, ads, and related searches.",
"Compares top-ranking pages by format, authority, freshness, links, structure, and likely ranking factors.",
"Identifies dominant search intent using visible SERP features and result types as evidence.",
"Calculates a weighted difficulty score and explains fit for new, growing, and established sites.",
"Recommends content requirements, outlines, snippet formats, AI citation opportunities, and next actions.",
"Compares multiple keywords, locations, devices, or historical SERP observations."
],
"limitations": [
"Feature analysis requires a current screenshot or direct SERP access; organic search APIs may omit visible modules.",
"Authority, backlink, and traffic metrics require supplied exports or connected SEO tools.",
"Historical comparisons require dated screenshots, exports, or another reliable archive.",
"Difficulty scores are estimates unless every weighted input comes from measured data."
],
"use_cases": [
{
"title": "Plan a competitive article",
"description": "Identify the format, depth, evidence, and SERP features a new article must address.",
"target_user": "Content strategist"
},
{
"title": "Prioritize SEO targets",
"description": "Compare candidate queries by intent, ranking barriers, volatility, and site-stage fit.",
"target_user": "SEO manager"
},
{
"title": "Find AI visibility opportunities",
"description": "Review AI Overview citations, answer formats, video results, and structured content opportunities.",
"target_user": "Digital marketing analyst"
}
],
"prompt_templates": [
{
"title": "Analyze one query",
"prompt": "Analyze the current SERP for [keyword] in [location] on [device]. Identify intent, visible features, top-result formats, and three practical opportunities.",
"scenario": "Begin with a focused SERP snapshot."
},
{
"title": "Evaluate supplied evidence",
"prompt": "Using these SERP screenshots or URLs for [keyword], compare the top results. Explain ranking patterns, content requirements, and feature opportunities with evidence.",
"scenario": "Use when direct search access is unavailable."
},
{
"title": "Compare keyword SERPs",
"prompt": "Compare SERPs for [keyword 1], [keyword 2], and [keyword 3] in [location]. Highlight overlap, intent differences, difficulty, and the best target.",
"scenario": "Prioritize several related content opportunities."
},
{
"title": "Run a multi-market audit",
"prompt": "Audit [keyword] across [locations] and [devices], then compare current and historical evidence. Score difficulty, volatility, site-stage fit, and AI visibility opportunities.",
"scenario": "Support advanced market and platform planning."
}
],
"output_examples": [
{
"input": "Analyze the SERP for project management software using the supplied desktop screenshot.",
"output": [
"Intent: Commercial investigation, supported by comparison pages, vendor pages, ads, and review results.",
"Primary opportunity: Publish a transparent comparison with pricing, use cases, limitations, and an updated evaluation method.",
"Evidence status: Screenshot observations are user-provided; backlink requirements remain unavailable."
]
},
{
"input": "Compare local SERPs for emergency plumber in Bristol and Bath.",
"output": [
"Both markets show strong local intent through map packs and service pages.",
"Bristol appears more competitive because established directories and larger providers occupy more visible positions.",
"Recommended focus: Build location-specific service proof, review coverage, and complete business profile information."
]
}
],
"best_practices": [
"Provide the target location, language, device, date, and current SERP evidence.",
"Label every metric as measured, user-provided, estimated, or unavailable.",
"Support intent and difficulty conclusions with specific features and ranking pages."
],
"anti_patterns": [
"Do not treat a generic organic result API as a complete view of SERP features.",
"Do not present estimated authority, links, traffic, or difficulty inputs as measured facts.",
"Do not reuse one market's SERP conclusions for another location, device, or date."
],
"faq": [
{
"question": "Does this skill discover keyword demand?",
"answer": "No. It evaluates results for known queries. Use keyword research tools to discover demand and search volume."
},
{
"question": "What input produces the strongest analysis?",
"answer": "Provide the query, location, language, device, date, and a current screenshot or top-result list."
},
{
"question": "Can it analyze AI Overviews?",
"answer": "Yes, when the supplied or live SERP shows the overview, citations, and answer structure."
},
{
"question": "Can it compare mobile and desktop results?",
"answer": "Yes. Supply evidence for both devices so the analysis can compare features, ordering, and opportunities."
},
{
"question": "How is difficulty calculated?",
"answer": "The score weights top-result authority, page links, content quality, backlink needs, and SERP stability."
},
{
"question": "Does it guarantee rankings?",
"answer": "No. It identifies observed requirements and opportunities, but algorithms, competitors, and results can change."
}
]
},
"file_structure": [
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "analysis-templates.md",
"type": "file",
"path": "references/analysis-templates.md",
"lines": 93
},
{
"name": "example-report.md",
"type": "file",
"path": "references/example-report.md",
"lines": 86
},
{
"name": "serp-feature-taxonomy.md",
"type": "file",
"path": "references/serp-feature-taxonomy.md",
"lines": 109
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 128
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |