CtrlK
BlogDocsLog inGet started
Tessl Logo

seo-traffic-diagnosis

Diagnose organic traffic changes (drops, stalls, or unexpected wins) using Ahrefs MCP plus Search Console data. Use this skill when traffic suddenly dropped, has been flat despite investment, after an algorithm update, after a migration or deploy, or when a competitor seems to be taking share. Triggers on traffic dropped, traffic decline, traffic stalled, organic decline, lost rankings, why is traffic down, algorithm update, post-migration traffic loss, traffic diagnosis. Also triggers when stakeholders are panicking about an organic traffic number they cannot explain. A panic about tracking, event, or dashboard setup is a measurement problem, not a traffic problem: route those to `analytics-strategy`.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-structured diagnostic skill body: concise, layer-sequenced, with concrete audit prompts, validation checkpoints, and a properly signaled single reference file. Slight room to tighten explanatory prose and make a few layer steps more directly executable.

Suggestions

Tighten explanatory prose in Layer 5 (the Similarweb/Ahrefs competitive-context paragraph) to one crisp sentence to lift conciseness toward 5.

Convert a couple of audit-prompt bullet lists (e.g. Layer 3/4) into a minimal concrete command or MCP-query example to push actionability from 4 to 5.

Add an explicit validate->fix->retry micro-loop around step 5 (technical check) since deploys are flagged as the prime suspect and batch/redirect fixes are destructive-adjacent.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence (checklists, segment dimensions, pattern tables) with minimal over-explanation; a few explanatory sentences (e.g. Layer 5 closing paragraph) could be trimmed but overall efficient.

4 / 5

Actionability

Provides concrete guidance: named data sources per layer, specific segment dimensions, a pattern-to-cause table, and a 10-step workflow. Mostly actionable for an instruction skill, though some layers read as audit prompts rather than fully executable steps.

4 / 5

Workflow Clarity

The 10-step workflow is clearly sequenced with explicit validation checkpoints ('Validate the data' step 2, 'Validate the hypothesis' step 8) and a layer-ordered diagnostic flow; not every step has a full validate-fix-retry loop, keeping it just below a 5.

4 / 5

Progressive Disclosure

SKILL.md is a concise overview with a single one-level-deep reference (references/diagnosis-checklist.md) that exists as a real file and is clearly signaled from both the Workflow step and a dedicated Reference files section.

5 / 5

Total

17

/

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, well-targeted description that clearly states capability, enumerates natural trigger phrases, and actively disambiguates from neighboring skills. The only minor gap is that the headline action ('diagnose') is slightly abstract relative to a fully concrete action list.

DimensionReasoningScore

Specificity

Names the domain (organic traffic) and multiple specific concerns (drops, stalls, unexpected wins, migrations, deploys, competitor share) with named tools (Ahrefs MCP, Search Console), though the core action 'diagnose' is somewhat abstract compared to a fully enumerated action list.

4 / 5

Completeness

Explicitly answers both 'what' ('Diagnose organic traffic changes... using Ahrefs MCP plus Search Console data') and 'when' with a clear 'Use this skill when' clause plus concrete trigger phrases and negative routing.

5 / 5

Trigger Term Quality

Provides a comprehensive list of natural user phrases ('traffic dropped', 'why is traffic down', 'traffic stalled', 'lost rankings', 'algorithm update', 'post-migration traffic loss') plus a behavioral trigger (stakeholders panicking), covering synonyms and scenario variations.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche (organic traffic diagnosis) and explicitly routes adjacent problems (measurement/panics about tracking) to `analytics-strategy`, minimizing overlap with sibling SEO skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
rampstackco/claude-skills
Reviewed

Table of Contents

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.