rank-tracker

Use when the user asks to "track rankings", "check keyword positions", "ranking changes", "monitor SERP positions", "how am I ranking", "where do I rank for this keyword", "did my rankings change", or "keyword position tracking". Tracks and analyzes keyword ranking positions over time for both traditional search results and AI-generated responses. Monitors ranking changes, identifies trends, and alerts on significant movements. For automated alerting, see alert-manager. For comprehensive reports, see performance-reporter.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/rank-tracker/SKILL.md

Quality

Content

56%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 delivers a well-sequenced, template-driven workflow with validation checklists, but it is bloated: domain knowledge tables and duplicated report templates inflate token cost, and reference-worthy material stays inline instead of being split into the bundle. Trimming and splitting would raise conciseness and progressive disclosure substantially.

Suggestions

Move the CTR-by-position benchmarks, SERP volatility/algorithm-impact tables, and rank-change root-cause taxonomy into a new reference file (e.g. references/rank-change-framework.md), linked from a short 'Reference Materials' entry the way tracking-setup-guide.md is.

Cut the ~100-line full report template down to the executive summary plus one detailed section, and remove the 'Ranking Performance Report' template's overlap with the 'Ranking Change Analysis' template — one canonical report format suffices.

Delete the 20-skill library directory block and the 'Tips for Success' section from the body; the former duplicates the skill registry and the latter restates knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	At ~585 lines the body is noticeably padded: a 20-skill library promo block, ~90 lines of CTR/algorithm-volatility tables that restate SEO domain knowledge Claude already has, a ~100-line report template largely duplicating the ranking-change template, plus a generic 'Tips for Success' section.	2 / 5
Actionability	Concrete invocation patterns, seven copy-paste-ready markdown output templates, and a filled worked example make the guidance mostly executable; the abstract '~~SEO tool' connector placeholders leave minor gaps.	4 / 5
Workflow Clarity	A clear numbered 7-step sequence (setup → snapshot → change analysis → SERP features → GEO → competitors → report) with explicit input and output validation checklists; falls short of 5 only because there is no validate-then-fix feedback loop.	4 / 5
Progressive Disclosure	The single reference (references/tracking-setup-guide.md) is real and clearly signaled at one level deep, but ~90 lines of reference-grade material (CTR benchmarks, volatility context, root-cause taxonomy) that should live in a reference file are inlined in SKILL.md.	3 / 5
	Total	13 / 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.

A strong description with an explicit trigger clause, natural user phrasings, and clear third-person capability statements. Its only weakness is slight incompleteness in the 'what' list relative to the skill's full feature set.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "Tracks and analyzes keyword ranking positions over time", "Monitors ranking changes, identifies trends, and alerts on significant movements" — but omits capabilities the skill actually has (competitor comparison, SERP feature tracking), leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both: an explicit "Use when the user asks to..." clause with concrete trigger phrases (when), and a clear multi-clause statement of what it does covering traditional SERP and AI-generated results (what).	5 / 5
Trigger Term Quality	Comprehensive natural phrasings users would actually say, including question forms: "track rankings", "check keyword positions", "monitor SERP positions", "how am I ranking", "where do I rank for this keyword", "did my rankings change", "keyword position tracking".	5 / 5
Distinctiveness Conflict Risk	Clear niche — positional keyword rank tracking over time for both traditional and AI search — and it actively disambiguates adjacent skills ("For automated alerting, see alert-manager. For comprehensive reports, see performance-reporter"), minimizing wrong-skill triggering.	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 (617 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 25 suspicious	Warning

	Total	13 / 16 Passed

Repository: teeclaw/phorm-nft
Path: .agents/skills/rank-tracker/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.