Agent skill
competitor-ads-analyst
Extract and analyze competitor advertising from public ad libraries (Facebook Ad Library, Google Ads Transparency Center, TikTok, LinkedIn).
Filed under Positioning and messaging and ABM and paid.
From thatrebeccarae/claude-marketing · 42 skills · 119 · pushed 2026-05-14
What it does when it runs
Extract and analyze competitor advertising from public ad libraries (Facebook Ad Library, Google Ads Transparency Center, TikTok, LinkedIn). Identifies messaging patterns, creative formats, pain points targeted, and positioning gaps. Use for competitive intelligence, campaign planning, and creative inspiration.
Read from the skill and the 3 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It does act, so it runs under whatever permissions your session already grants. - Actions present in the files
- shell
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/thatrebeccarae/claude-marketing.git /tmp/claude-marketing git -C /tmp/claude-marketing sparse-checkout set "skills/competitor-ads-analyst" mkdir -p ~/.claude/skills/competitor-ads-analyst cp -R "/tmp/claude-marketing/skills/competitor-ads-analyst/." ~/.claude/skills/competitor-ads-analyst/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from thatrebeccarae/claude-marketing/blob/a8a63ec1341f05ec9c1e9cb52b4edeb14e3bdcba/skills/competitor-ads-analyst/SKILL.md, which is licensed MIT (skill frontmatter). 448 words, 11 headings.
Competitor Ads Analyst
Analyze competitor advertising from public ad libraries to understand what messaging, creative formats, and positioning strategies are working.
Install
git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/competitor-ads-analyst ~/.claude/skills/
Core Capabilities
- Extract ads from public ad libraries (Facebook, Google, TikTok, LinkedIn)
- Categorize ad creative by format, message type, and funnel stage
- Identify pain points competitors highlight (with frequency scoring)
- Map competitor positioning and find white space
- Extract headline and copy formulas
- Track creative format trends (UGC, before/after, testimonial, etc.)
- Generate competitive intelligence reports and swipe files
Ad Library Access
| Platform | URL | Access |
|---|---|---|
| Meta (Facebook/Instagram) | facebook.com/ads/library | Free, public |
| Google Ads | adstransparency.google.com | Free, public |
| TikTok | library.tiktok.com | Free, public |
| linkedin.com/ad-library | Requires account |
Workflow
1. Define Scope
- Competitors: 3-5 companies to analyze
- Timeframe: Last 30, 60, or 90 days
- Platforms: Which ad libraries to search
- Focus: Messaging, creative format, audience targeting, or all
2. Extract Ads
For each competitor, collect:
- Ad copy (headline, primary text, CTA)
- Creative format (image, video, carousel, UGC)
- Landing page URL
- Active date range (if visible)
- Platform and placement
3. Categorize
Classify each ad by:
Message Type:
- Pain point (problem-aware)
- Solution (product-aware)
- Social proof (testimonial, case study, press)
- Offer (discount, free trial, demo)
- Educational (how-to, tip, guide)
- Brand (awareness, positioning)
Funnel Stage:
- Top (awareness, problem education)
- Middle (consideration, comparison)
- Bottom (conversion, offer, urgency)
Creative Format:
- Static image
- Video (short <15s, medium 15-60s, long >60s)
- Carousel
- UGC-style
- Before/after
- Screenshot/product demo
- Testimonial quote card
- Data/stat visualization
4. Analyze Patterns
- Pain point frequency: Which problems appear most across competitors?
- Message clustering: Are competitors saying the same things?
- Format preferences: Which creative types are most used?
- Positioning map: Where does each competitor sit on key dimensions?
- Gaps: What messages/angles are NO competitors using?
5. Generate Output
Choose from: competitive report, swipe file, messaging matrix, or creative brief.
Key Principles
- Analyze patterns, not individual ads. One ad is an anecdote; 20 ads from 5 competitors is intelligence.
- Look for gaps, not just patterns. The most valuable finding is what competitors are NOT saying.
- Separate observation from recommendation. Report what you see, then separately recommend what to do with it.
- Date everything. Competitive intelligence decays fast.
- Never copy, always adapt. The goal is informed inspiration, not plagiarism.
For analysis frameworks and output templates, see REFERENCE.md.
Files bundled with it
These load only when the skill asks for them, so they cost nothing until it runs.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- ads by coreyhaines31 · 45,947
- competitor-profiling by coreyhaines31 · 45,947
- competitor-analysis by OpenClaudia · 664
- facebook-ads by OpenClaudia · 664
- google-ads by OpenClaudia · 664
- google-ads-report by OpenClaudia · 664
- linkedin-ads by OpenClaudia · 664
- competitor-monitoring by shawnpang · 308
Need help setting it up?
This page tells you what competitor-ads-analyst does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.