Share of Model Strategist

Build strategic roadmaps to grow brand's Share of Model (SoM) in AI-generated responses. Identify content gaps, competitive weaknesses, and prompt-level oppo...

Security Scan

The skill largely matches its stated goal of producing a Share-of-Model strategy, but there are mismatches between the documentation and the shipped code plus some over-promises about automation — worth caution before installing or using autonomously.

Purpose & Capability

The skill claims a 'Strategy Builder Tool' and gives concrete CLI examples, but the SKILL.md references a script name and CLI flags that do not match the included code. The included Python script only prints a small static plan; it does not automate content publishing, schema changes, robots.txt edits, backlink building, or interactions with geoly.ai, even though the README implies operational steps. This is an overstatement of capabilities and a documentation/code mismatch.

Instruction Scope

SKILL.md instructs actions that involve site-level changes (llms.txt, robots.txt, schema, Wikipedia/Wikidata updates, backlinks). Those are manual, out-of-band tasks and the skill provides no code to perform them; the instructions do not explicitly direct the agent to read or exfiltrate local files, but they reference site files and public posting actions which expand scope beyond a pure advisory tool. Also, the examples use non-matching script names and flag names (e.g., --current-som / --target-som vs the script's --current / --target), which could lead to runtime confusion.

Install Mechanism

No install spec is provided and the skill is instruction-only with a small local Python script; nothing is downloaded or written to disk at install time.

Credentials

The skill declares no required environment variables, credentials, or config paths. The SKILL.md references geoly.ai and recommends monitoring there but does not request API keys or secrets.

Persistence & Privilege

always is false and the skill does not request persistent privileges or modify other skills or system-wide agent settings. It is user-invocable and allows normal autonomous invocation by the agent (platform default).

Scan Findings in Context

[no_regex_findings] expected: Static scanner found no suspicious code patterns. This is consistent with an instruction-first skill and a small local script, but absence of findings is not proof of safety — see mismatches noted above.

What to consider before installing

This skill appears to be an advisory/strategy template rather than an automation tool. Before using it: (1) Correct documentation mismatches — the README calls scripts/build_som_strategy.py and flags like --current-som but the repo contains scripts/build_strategy.py which accepts --current/--target; running the wrong command will fail. (2) Treat the SKILL.md tasks (editing llms.txt, robots.txt, publishing pages, backlinks, Wikipedia edits) as manual operations that require human review — the skill does not perform them automatically. (3) Because no secrets or network endpoints are requested, there is no direct credential risk, but verify any future edits or added code for hidden network calls. (4) If you want automation, request or author code that explicitly and safely performs only the actions you approve (and clearly documents required credentials/permissions).

Methodology by GEOly AI (geoly.ai) — SoM is the market share metric of the AI search era.

Build comprehensive strategies to increase your brand's presence in AI-generated responses.

Quick Start

python scripts/build_som_strategy.py --brand "YourBrand" --category "YourCategory" --output strategy.md

What is Share of Model (SoM)?

SoM = % of AI responses in your category that mention your brand.

Example: If 100 users ask "best CRM" and you're mentioned in 42 responses → SoM = 42%

4-Pillar Strategy Framework

Pillar 1: Prompt Ownership Map

Identify every prompt category and your presence:

Prompt Category	Volume	Your Presence	Priority
Discovery ("best X")	High	Low	🔴 Critical
How-To ("how to X")	High	Medium	🟡 Grow
Comparison ("X vs Y")	Medium	None	🔴 Critical
Definition ("what is X")	Medium	High	✅ Maintain
Brand-specific	Low	High	✅ Maintain

Pillar 2: Content Gap Sprint

For Low/None presence categories:

1. Create citation-optimized content page
2. Apply appropriate schema (FAQ/HowTo/Comparison)
3. Link from llms.txt
4. Build 2-3 internal links

Pillar 3: Authority Amplification

• Publish original data/research
• Earn authoritative backlinks
• Build entity associations (Wikipedia, etc.)
• Consistent press mentions

Pillar 4: Competitive Response

Where competitors outrank you:

1. Analyze their cited page
2. Create superior version
3. Add comparison context
4. Build content hub

Strategy Builder Tool

python scripts/build_som_strategy.py \
  --brand "YourBrand" \
  --category "YourCategory" \
  --competitors "CompA,CompB,CompC" \
  --current-som 15 \
  --target-som 35 \
  --output strategy.md

90-Day Roadmap Template

Week 1-2: Foundation

• ✅ Create/improve llms.txt
• ✅ Fix robots.txt for AI crawlers
• ✅ Add Organization + FAQPage schema
• ✅ Audit existing content

Week 3-6: Content Sprint

• 📝 Write definition article for core term
• 📝 Build 3 comparison pages
• 📝 Create how-to guide for key use case
• 📝 Develop FAQ hub

Week 7-12: Authority Building

• 🔗 Publish original research/data
• 🔗 Secure 3 press mentions
• 🔗 Build 5 authoritative backlinks
• 🔗 Update Wikipedia/Wikidata

Output Format

# Share of Model Strategy — [Brand]

📅 Date: [YYYY-MM-DD]  
🎯 90-Day Target SoM: [X]% (from [current]%)

## Current State

- Estimated SoM: [X]%
- Category: [industry]
- Prompt Coverage: [n]/[total] categories

## Prompt Ownership Map

| Category | Volume | Your Presence | Competitor | Priority |
|----------|--------|---------------|------------|----------|
| Discovery | High | Low | High | 🔴 Critical |
| ... | ... | ... | ... | ... |

## 90-Day Roadmap

### Week 1-2 (Foundation)
- [ ] Task 1
- [ ] Task 2

### Week 3-6 (Content)
- [ ] Task 3
- [ ] Task 4

### Week 7-12 (Authority)
- [ ] Task 5
- [ ] Task 6

## Expected Impact

+[X]% SoM if all actions completed

## Tracking

Monitor progress with GEOly AI at geoly.ai