CtrlK
BlogDocsLog inGet started
Tessl Logo

geo-fundamentals

Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).

36

Quality

34%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/geo-fundamentals/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

32%Scale 1-5

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

This skill reads more like a knowledge base or reference card about GEO concepts than an actionable skill for Claude. It lacks concrete implementation steps, executable examples, and clear workflows. The content is mostly informational tables that explain marketing concepts Claude likely already understands, with fabricated-looking statistics (RAG retrieval factor weights) and a disconnected script reference.

Suggestions

Replace conceptual tables with concrete, executable workflows — e.g., show exactly how to audit a page for GEO readiness with specific commands and expected outputs from the geo_checker.py script.

Remove sections that explain concepts Claude already knows (What is GEO, SEO vs GEO comparison, general content advice) and focus on project-specific implementation steps.

Add a clear sequenced workflow: e.g., 1) Run audit script → 2) Review output → 3) Apply fixes → 4) Re-audit to validate improvements, with example input/output for each step.

Either provide the bundle file for scripts/geo_checker.py with example output, or remove the script reference and replace with inline actionable checks Claude can perform directly.

DimensionReasoningScore

Conciseness

The content is mostly tables which are efficient, but includes several sections that explain general concepts Claude already knows (SEO vs GEO comparison, what RAG retrieval factors are, general content marketing advice). The 'What is GEO?' section and basic definitions are unnecessary padding for Claude. However, the table-heavy format is relatively compact.

3 / 5

Actionability

The skill is almost entirely informational/conceptual with no executable code, no concrete commands (beyond a single script reference at the bottom with no example output), and no specific implementation steps. The checklist in section 5 provides some actionable items but they are high-level guidance rather than concrete executable instructions. The RAG retrieval factor weights appear fabricated with no sourcing.

2 / 5

Workflow Clarity

There is no clear multi-step workflow or sequenced process. The content is organized as a reference/knowledge dump rather than a workflow. The script reference at the bottom hints at a workflow but provides no example output, no validation steps, and no guidance on what to do with results. The checklist is the closest thing to a workflow but lacks sequencing and validation.

2 / 5

Progressive Disclosure

The content is a monolithic file with no references to supporting documents despite covering many topics that could benefit from deeper treatment (entity building, schema implementation, crawler configuration). The script reference at the bottom is disconnected from the rest of the content. No bundle files are provided to support the referenced script path.

2 / 5

Total

9

/

20

Passed

Description

36%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 identifies a specific and emerging domain (GEO for AI search engines) which gives it some distinctiveness, but it fails to describe any concrete actions the skill performs and completely lacks a 'Use when...' clause. It reads more like a topic label than a functional skill description, leaving Claude without enough information to reliably select it.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Analyzes content for AI search engine visibility, optimizes text for citation likelihood, and structures information for AI retrieval.'

Add an explicit 'Use when...' clause with natural trigger phrases, e.g., 'Use when the user asks about optimizing content for AI search, improving AI discoverability, GEO, AI SEO, or getting cited by ChatGPT/Perplexity/Claude.'

Include common synonyms and abbreviations like 'GEO', 'AI SEO', 'AI search ranking', 'AI visibility' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (Generative Engine Optimization) and lists AI search engines as examples, but provides no concrete actions—no mention of what the skill actually does (e.g., optimize content, analyze citations, improve visibility).

2 / 5

Completeness

Provides a vague 'what' (Generative Engine Optimization) but no 'when' clause at all. There is no explicit trigger guidance for when Claude should select this skill, which caps this dimension at 3 per the rubric, and the 'what' itself is too vague to reach 3.

2 / 5

Trigger Term Quality

Includes relevant keywords like 'Generative Engine Optimization', 'AI search engines', 'ChatGPT', 'Claude', 'Perplexity', but misses natural user phrases like 'GEO', 'AI SEO', 'AI search visibility', 'optimize for AI', or 'AI discoverability'.

3 / 5

Distinctiveness Conflict Risk

The domain of 'Generative Engine Optimization' is somewhat niche, but without specifying concrete actions, it could overlap with general SEO skills or content optimization skills. The mention of specific AI search engines helps somewhat but isn't enough to clearly carve out a distinct niche.

3 / 5

Total

10

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.