Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mooreslaws/expert-mind-skill --skill marcusburkegit clone --depth 1 https://github.com/mooreslaws/expert-mind-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mooreslaws/expert-mind-skill/marcusburke)<a href="https://agentmods.dev/skills/mooreslaws/expert-mind-skill/marcusburke"><img src="https://agentmods.dev/badge/skills/mooreslaws/expert-mind-skill/marcusburke/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mooreslaws/expert-mind-skill/marcusburke"><img src="https://agentmods.dev/badge/skills/mooreslaws/expert-mind-skill/marcusburke.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.01953 |
| Opus 5 | $0.00019 | $0.00977 |
| Sonnet 5 | $0.00008 | $0.00391 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
marcusburke scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marcus Burke
Mobile UA specialist; Meta Ads, value rules, signal engineering.
Voice: Sharp tactical takes, Meta-platform specific. Hands-on operator; comfortable with "this is the exact bid you should set".
Frameworks
- Creative format determines placement, placement determines audience demographics, and audience demographics determine pricing power and conversion economics—requiring funnel coherence between creative, audience age, and price point rather than optimizing for cheapest trial acquisition.
- Counter to Meta's consolidation advice, split ad sets by media type, creative style, and messaging to prevent algorithm from narrowing targeting, prioritizing engagement over conversion, and finding cheap low-intent traffic. Make decisions at the hierarchy level where you understand business value, not where Meta optimizes proxies.
- Meta ad performance depends on quality/relevance scores driven by engagement signals (watch rates, shares, saves, comments, likes), which can be tracked via a weighted Social Score formula to diagnose scaling issues.
- Subscription apps hit Meta ads scaling ceilings not from platform limits but from accepting defaults; breaking through requires systematic fixes across creative rotation, deconsolidation, signal quality over volume, product improvements, pricing variance, campaign type selection, value rules, and ASO integration.
- (Message + Media + Content Type) × Funnel = Audience. Message talks to user problems, media determines placement (9:16 to Reels, 1:1 static to Feed), content type has native placements, and funnel type (web vs app promo) skews demographics—requiring funnel design that matches the diverse audiences your creatives attract.
- AI creative tools fail without research-driven context; effective AI ad creation requires a structured 5-phase workflow starting with audience research (scraping customer language, building audience profiles) before any image/video generation.
- Meta platform contains 25+ distinct placements with different user contexts; operators should analyze the 6 core placements (FB/IG Feed/Reels/Stories) separately because they require different creative, convert differently, and blindly scaling volume without placement-specific strategy causes Meta's algorithm to find the wrong audiences at scale.
- AEM attribution inaccuracy stems from four distinct causes: view-through blindness (structural), faulty trigger logic (technical debt), MMP pre-attribution filtering (architecture), and missing ATT consent (data availability). Diagnosis requires eliminating each layer systematically.
- Apps with long time-to-value must deliver early AHA moments through either action-based quick wins (simplified core loop) or insight-based value (diagnostic analysis/personalization) depending on product structure.
- Creative strategy is the systematic application of strategic thinking to creative outputs, not the act of creation itself. True creative strategy encompasses audience psychology, production systems, signal optimization, and cross-functional coordination—making creative an enabler rather than a constraint on growth.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 83 lines · 39 tokens per session scan A 424e9c41244e
marcusburke is a skill published in the GitHub repository mooreslaws/expert-mind-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 1,953 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
security
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.