serp-analysis

Use 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

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and highly actionable, with executable commands, concrete templates, and clean progressive disclosure into real reference files. The main slack is minor verbosity in the connector explanations and validation logic delegated to external references rather than inlined.

Suggestions

Tighten the Data Sources connector paragraphs: move the Firecrawl/Tavily flag details and credit-tier caveats into scripts/connectors/README.md, keeping one-line summaries inline.

Add an inline validate→fix→retry checkpoint in the main 8-step sequence (e.g., re-run the binding/evidence check if inputs are stale) rather than only referencing the evidence-and-cycle-control profile.

Drop the strikethrough `~~SEO tool, ~~search console, ~~AI monitor` inline notes in favor of a single sentence pointing to CONNECTORS.md for optional integrations.

Dimension	Reasoning	Score
Conciseness	The body is dense and information-rich with almost no concept re-explanation, but the multi-paragraph Firecrawl/Tavily connector explanation and inline strikethrough connector notes could be trimmed, keeping it just below the lean 5 anchor.	4 / 5
Actionability	It provides two copy-paste-ready keyless commands with concrete flags and an 8-step procedure with explicit weighted difficulty inputs (25/20/20/20/15%), giving fully executable guidance for the common cases.	5 / 5
Workflow Clarity	The 8 numbered steps form a clear sequence with a binding step and a calculation step, but the validate→fix→retry checkpoints are referenced out to another file rather than inline, leaving a minor validation gap below the 5 anchor; the destructive/batch cap does not apply since this skill is analysis-only.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references to real bundle files (analysis-templates.md, example-report.md, serp-feature-taxonomy.md) and a dedicated Reference Materials list, with content appropriately split across files.	5 / 5
	Total	18 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: concrete trigger phrases, clear what/when coverage, and explicit disambiguation from the neighboring keyword-research skill. Minor room for improvement only in framing scope areas as discrete actions rather than an enumeration.

Dimension	Reasoning	Score
Specificity	"maps SERP features, layout, ranking factors, search intent, AI Overviews, and snippet opportunities" enumerates several specific scope areas, but it reads more as a domain enumeration than a list of discrete concrete actions, so it sits just below the comprehensive 5 anchor.	4 / 5
Completeness	It explicitly answers both what (maps SERP features, ranking factors, intent, AI Overviews, snippet opportunities) and when (concrete "Use when..." trigger phrases), plus a negative boundary, matching the 5 anchor.	5 / 5
Trigger Term Quality	It gives explicit natural trigger phrases ("Use when the user asks to 'analyze the SERP' or 'SERP分析'") including a non-English synonym, matching the anchor for comprehensive coverage of natural terms including synonyms.	5 / 5
Distinctiveness Conflict Risk	The SERP-analysis niche is distinct and the explicit "Not for keyword demand discovery — use keyword-research" disambiguation minimizes conflict risk, matching the 5 anchor.	5 / 5
	Total	19 / 20 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 11 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: seo-geo/survey/serp-analysis/SKILL.md
Commit: 64562bc

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.