Chalk Labs
Need help deploying ad-transparency-audit?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ever-just-ad-transparency-audit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, marketing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
ad-transparency-audit- Description
- None
- License
- MIT
- Instructions
- 139 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Agent Skills spec issues
- missing YAML frontmatter
- name: missing
- description: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
# Ad Transparency Audit > Determine a company's actual paid advertising activity by cross-referencing tracking pixels installed on their website against public ad transparency platforms. Reveals the gap between "pixel infrastructure" and "actual ad spend." --- ## When to use - Competitive intelligence: understanding a competitor's marketing investment - Due diligence: assessing a company's customer acquisition strategy - Partnership evaluation: understanding how a company generates leads - Marketing analysis: comparing digital marketing sophistication across competitors --- ## The insight Many companies install advertising tracking pixels (Google Analytics, Meta Pixel, TikTok Pixel, The Trade Desk, etc.) on their website but never activate paid campaigns behind them. Detecting pixels alone overstates advertising activity. This skill cross-references pixel presence against actual ad transparency data to determine real marketing spend. --- ## Workflow ### Phase 1: Identify installed pixels Run a tech stack scan to detect all tracking pixels and marketing tags: ```bash # ProjectDiscovery httpx with tech detection ~/go/bin/httpx -u https://TARGET.com -tech-detect -json -follow-redirects # Look for: Google Analytics, GTM, Meta Pixel, TikTok Pixel, # The Trade Desk, LinkedIn Insight Tag, Twitter/X Pixel, etc. ``` ### Phase 2: Parse GTM container If Google Tag Manager is detected, parse the container JavaScript for the full tag configuration: ```bash # Fetch and analyze GTM container curl -s "https://www.googletagmanager.com/gtm.js?id=GTM-XXXXXXX" ``` Extract from the GTM container: - All Google Analytics measurement IDs (GA4 + UA) - GCLID (Google Click ID) tracking — if enabled, a Google Ads account exists or existed - Facebook/Meta Pixel IDs - TikTok Pixel IDs - LinkedIn Insight Tag - Custom conversion tracking - Any other marketing tags **Key signal:** GCLID tracking enabled in GTM means the company has/had a Google Ads account, even if no active ads are currently running. ### Phase 3: Check ad transparency platforms | Platform | URL | What to search | Data returned | |----------|-----|---------------|---------------| | **Google Ads Transparency** | adstransparency.google.com | Company name or domain | Ad creatives, date ranges, geographic targeting | | **Meta Ad Library** | facebook.com/ads/library | Company name | Ad creatives, platforms (FB/IG/Messenger), date ranges | | **TikTok Ad Library** | library.tiktok.com/ads | Company name | Ad creatives, targeting | | **LinkedIn** | No public ad library | Search for "sponsored" posts | Indirect only | | **The Trade Desk** | No public ad library | N/A | Cannot verify — DSP is opaque | ### Phase 4: Check for ads.txt ```bash curl -s "https://TARGET.com/ads.txt" ``` If present, ads.txt lists authorized digital sellers and publisher IDs. If 404 (not found), the company has no programmatic ad infrastructure. ### Phase 5: Cross-reference GA IDs for related domains Search for other websites using the same Google Analytics property: ``` # Try these services: dnslytics.com/google-analytics/GA-MEASUREMENT-ID spyonweb.com/GA-MEASUREMENT-ID builtwith.com (search by tracking ID) ``` If multiple domains share the same GA property, they're controlled by the same entity — reveals related websites, event microsites, or subsidiary brands. ### Phase 6: Check PR/content marketing (non-paid channels) Search for the company's PR agency and identify if editorial coverage is actually PR placement: ``` "company name" site:imillerpr.com OR site:prnewswire.com OR site:businesswire.com ``` **Key pattern to check:** Is the company's PR agency also the publisher of their media coverage? (e.g., iMiller PR runs both the PR agency and Data Center POST — same person controls both sides.) --- ## Output template ```markdown # Ad Transparency Audit: [TARGET] ## Pixel vs. activity matrix | Platform | Pixel installed? | Active ads found? | Assessment | |----------|-----------------|-------------------|------------| | Google Ads | GA + GTM + GCLID | Yes/No | ... | | Meta | Pixel ID: ... | Yes/No | ... | | TikTok | Yes/No | Yes/No | ... | | LinkedIn | Yes/No | Yes/No | ... | | Trade Desk | Pixel ID: ... | Unknown | ... | ## Key findings - [Is the company actually running paid ads, or just collecting data?] - [What is their real marketing strategy? (Events? PR? Organic LinkedIn? Referrals?)] - [Any PR/editorial conflicts of interest?] ``` ---
From ever-just/agentskills, MIT.
More from ever-just/agentskills
- 0.575score
claude-session-archaeology
ever-just
Reconstruct what work was actually done on a project by mining Claude Code session transcripts (~/.claude/projects/**/*.jsonl) — streaming grep/jq recipes for…
SkillBFreshness: B★ 5Claude Code +9 - 0.529score
agent-quality-grading
ever-just
Grade AI-agent performance qualitatively — every user↔agent conversation on four axes (did it do the task / respond fast / use the right tools / message…
SkillCFreshness: C★ 5Claude Code +9 - 0.529score
dark-mode-token-migration
ever-just
Add dark mode to a light-only app that styles with RAW color utilities (Tailwind `stone-*`/`slate-*`/`gray-*`) via a semantic token layer, migrating utilities…
SkillCFreshness: C★ 5Claude Code +9 - 0.529score
deploy-log-forensics
ever-just
Reconstruct what changed on production — which commit, which module, which tenant, at what time — from CI/CD run logs when you have NO server access (no SSH…
SkillCFreshness: C★ 5Claude Code +9 - 0.439score
canvas-design
ever-just
Create beautiful visual art in .png and .pdf documents using design philosophy.
SkillDFreshness: D★ 5Claude Code +9 - 0.283score
commercial-property-research
ever-just
No description from the publisher yet.
SkillCFreshness: C★ 5Claude Code +9 - 0.283score
business-model-canvas
ever-just
No description from the publisher yet.
SkillCFreshness: C★ 5Claude Code +9 - 0.283score
cdp-render-verification
ever-just
No description from the publisher yet.
SkillCFreshness: C★ 5Claude Code +9 - 0.283score
client-discovery-osint
ever-just
No description from the publisher yet.
SkillCFreshness: C★ 5Claude Code +9 - 0.283score
agent-discoverability
ever-just
No description from the publisher yet.
SkillCFreshness: C★ 5Claude Code +9 - 0.283score
company-legal-reputation-research
ever-just
No description from the publisher yet.
SkillCFreshness: C★ 5Claude Code +9 - 0.283score
competitor-identification
ever-just
No description from the publisher yet.
SkillCFreshness: C★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jun 13, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ever-just/agentskills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ever-just
- 0.575score
claude-session-archaeology
ever-just
Reconstruct what work was actually done on a project by mining Claude Code session transcripts (~/.claude/projects/**/*.jsonl) — streaming grep/jq recipes for…
SkillBFreshness: B★ 5Claude Code +9 - 0.529score
dark-mode-token-migration
ever-just
Add dark mode to a light-only app that styles with RAW color utilities (Tailwind `stone-*`/`slate-*`/`gray-*`) via a semantic token layer, migrating utilities…
SkillCFreshness: C★ 5Claude Code +9 - 0.529score
deploy-log-forensics
ever-just
Reconstruct what changed on production — which commit, which module, which tenant, at what time — from CI/CD run logs when you have NO server access (no SSH…
SkillCFreshness: C★ 5Claude Code +9 - 0.529score
agent-quality-grading
ever-just
Grade AI-agent performance qualitatively — every user↔agent conversation on four axes (did it do the task / respond fast / use the right tools / message…
SkillCFreshness: C★ 5Claude Code +9 - 0.439score
canvas-design
ever-just
Create beautiful visual art in .png and .pdf documents using design philosophy.
SkillDFreshness: D★ 5Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ad-transparency-audit running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ad-transparency-audit skill. Agent Mart. https://agentmart.dev/skills/ever-just-ad-transparency-audit (last updated 2026-10-24)