serp-analysis

Use when the user asks to "analyze search results", "SERP analysis", "what ranks for", "SERP features", "why does this page rank", "what is on page one for this query", "who ranks for this keyword", or "what does Google show for". Analyzes search engine results pages (SERPs) to understand ranking factors, SERP features, user intent patterns, and AI overview triggers. Essential for understanding what it takes to rank. For tracking rankings over time, see rank-tracker. For keyword discovery, see keyword-research.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/serp-analysis/SKILL.md

Quality

Content

62%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 highly actionable — structured output templates, a fully worked example, and explicit validation checklists — but it wastes significant tokens on cross-skill promotion, generic tips, and a taxonomy that duplicates its own reference file. Moving the duplicated reference material out and cutting promotional filler would tighten it substantially without losing capability.

Suggestions

Replace the inline "SERP Feature Taxonomy", "AI Overview Analysis Framework", intent-signal, and volatility tables with a pointer to the existing references/serp-feature-taxonomy.md, keeping only a summary table in SKILL.md.

Delete the 20-skill library promotion block and the "Tips for Success" section — both restate what the workflow and Claude's own knowledge already cover.

Make the connector section concrete: specify which tool categories supply which data points and what to do when a connector is absent, instead of the abstract "~~SEO tool" placeholders.

Dimension	Reasoning	Score
Conciseness	Multiple padded sections inflate the body: a ~15-line cross-promotion block listing all 20 library skills, a "Tips for Success" section restating knowledge Claude already has ("Don't assume, verify"), and a condensed SERP-feature taxonomy, intent-signal, and volatility tables that duplicate the 404-line references/serp-feature-taxonomy.md — matching anchor 2 (several unnecessary explanations or padded sections), not 3, because the duplication is systematic rather than incidental.	2 / 5
Actionability	Every analysis step ships a copy-paste-ready markdown output template with exact fields, and the worked "how to start a podcast" example shows complete concrete output; the gap keeping it below 5 is the abstract connector placeholders ("~~SEO tool", "~~AI monitor") that defer rather than resolve how data is actually fetched.	4 / 5
Workflow Clarity	The instructions define a clear 8-step numbered sequence, open with a clarification step ("Clarify if needed"), include a manual-data fallback path, and close with a dedicated Validation Checkpoints section containing both input and output checklists — matching anchor 5 (clear sequence, explicit validation steps, checklists).	5 / 5
Progressive Disclosure	The one reference (references/serp-feature-taxonomy.md) exists, is one level deep, and is clearly signaled under "Reference Materials", but the body simultaneously inlines a ~70-line SERP Feature Taxonomy section, AI Overview framework, and intent/volatility tables covering the same material — content that clearly belongs in the separate file is inline, matching anchor 3.	3 / 5
	Total	14 / 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.

An exemplary description: explicit and natural trigger phrases, a clear third-person capability statement, and explicit disambiguation against adjacent skills. The only weakness is that the capability statement compresses several analysis dimensions under a single "analyzes" verb, leaving specificity a notch below the top anchor.

Suggestions

Recast the capability sentence as distinct actions (e.g., "Maps SERP composition, identifies ranking factors for top-10 pages, and analyzes AI Overview citation patterns") to reach the top specificity anchor.

Trim the vague filler phrase "Essential for understanding what it takes to rank" — it adds no capability or trigger information.

Dimension	Reasoning	Score
Specificity	"Analyzes search engine results pages (SERPs) to understand ranking factors, SERP features, user intent patterns, and AI overview triggers" names several specific capability areas in third person, but they are aspects of a single analyze action rather than multiple distinct operations, matching anchor 4 (several specific actions, minor gaps) rather than 5.	4 / 5
Completeness	It explicitly answers both questions: a concrete "Use when the user asks to..." trigger list, and a clear what-statement ("Analyzes SERPs to understand ranking factors, SERP features, user intent patterns, and AI overview triggers"), matching the anchor-5 good example exactly in structure.	5 / 5
Trigger Term Quality	The trigger list is comprehensive and natural — "analyze search results", "SERP analysis", "what ranks for", "why does this page rank", "what is on page one for this query", "who ranks for this keyword", "what does Google show for" — covering synonyms and phrasings users would actually say, matching the anchor-5 example's breadth.	5 / 5
Distinctiveness Conflict Risk	It carves out a clear SERP-analysis niche and actively reduces conflict with sibling skills via explicit boundary pointers ("For tracking rankings over time, see rank-tracker. For keyword discovery, see keyword-research."), so overlap risk with the library's other skills is minimal.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (637 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 27 suspicious	Warning

	Total	13 / 16 Passed

Repository: teeclaw/phorm-nft
Path: .agents/skills/serp-analysis/SKILL.md
Commit: 02adecb

Reviewed: 6 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.