arbitrage-audit
Skill0 starsChanged 4 months agoMITView on GitHub
3 diagnostic questions for evaluating any industry, market, or business model through the lens of arbitrage gaps. Identifies durable advantages vs. closing ones. Based on Nate Jones' Arbitrage Gap Framework. Activates on "arbitrage", "competitive advantage", "moat", "durable advantage", "market gap", "industry analysis", or "what gap am I exploiting?"
1 other project uses a version of this.
Adopted by
Most recently taken up by
- drewid74/ai_skillstheir own version, first seen May 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- drewid74/ai_skills★ 8same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-graduationSkill
- assumption-mapperSkill
- b2b-idea-vettingSkill
- codifySkill
- decision-briefSkill
- design-thinking-liteSkill
- grill-meSkill
- grill-with-docsSkill
- innovation-diagnosticSkill
- kill-goSkill
- preflightSkill
- problem-framingSkill
- pull-frameworkSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Ask: "What would this business/product/role look like if perfect information existed and everything happened instantly?"
- Distinctive: line 49
Ask: "If a smart person with Claude and six months of context tried to replicate this, could they?
- Distinctive: line 53
When one gap closes, a new one opens upstream.
- Distinctive: line 55
When AI closes the knowledge gap, the NEW gap is: who can distinguish good knowledge from confident-sounding wrong knowledge?
- Distinctive: line 56
When AI closes the speed gap, the NEW gap is: who can decide what's worth doing fast?
- Distinctive: line 57
When AI closes the synthesis gap, the NEW gap is: who can decide what the synthesis means for THIS situation?
- Distinctive: line 59
Ask: "Once this gap is closed, what becomes the new bottleneck?
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
The Framework
Five types of gaps AI is closing: speed, reasoning, fragmentation, discipline, knowledge asymmetry. When a gap closes, a new one opens upstream — always toward judgment, taste, relationships, and system-level thinking.
The 7.6% vs 92.4% distinction: Access to AI is universal. Advantage is not. "Bolted AI onto existing process" vs "rebuilt process around what AI makes possible" is the gap that separates winners from losers. Systems compound; pilots don't.
The 3 Diagnostic Questions
Question 1: What inefficiency is this built on?
Name the gap. Every business, product, or career advantage sits on top of an inefficiency — an information asymmetry, a speed gap, a fragmentation problem, a knowledge bottleneck.
Ask: "What would this business/product/role look like if perfect information existed and everything happened instantly?"
The distance between that hypothetical and reality IS the gap.
Gap types:
| Gap Type | Example | AI Closing Speed |
| Knowledge asymmetry | "Only specialists know this" | Fast — AI democratizes knowledge access |
| Speed gap | "This takes weeks of manual work" | Fast — automation and agents |
| Fragmentation gap | "Data lives in 5 systems" | Medium — integration tools accelerating |
| Discipline gap | "People skip steps" | Medium — AI can enforce process |
| Judgment gap | "Someone needs to decide what matters" | Slow — still requires human taste |
| Relationship gap | "Trust takes time to build" | Slow — fundamentally human |
| System-level thinking | "Seeing how pieces connect" | Slow — AI assists but doesn't replace |
Question 2: How fast can AI close it?
Not "can AI do this?" but "how quickly does the gap shrink?"
Informational gaps (research, synthesis, aggregation) close fast. If your advantage depends on knowing something others don't, and that knowledge is in text or data, the clock is ticking.
Structural gaps (judgment, taste, domain expertise, relationships) close slowly. If your advantage depends on making calls that require experience, context, and the ability to say "no" — that's durable.
Ask: "If a smart person with Claude and six months of context tried to replicate this, could they? How long would it take?"
Question 3: What new gap does the closure create?
When one gap closes, a new one opens upstream. Always.
- When AI closes the knowledge gap, the NEW gap is: who can distinguish good knowledge from confident-sounding wrong knowledge? (Judgment)
- When AI closes the speed gap, the NEW gap is: who can decide what's worth doing fast? (Taste)
- When AI closes the synthesis gap, the NEW gap is: who can decide what the synthesis means for THIS situation? (Context)
Ask: "Once this gap is closed, what becomes the new bottleneck? Who owns that bottleneck?"
The answer tells you where to position.
Output
# Arbitrage Gap Audit: [Industry/Business/Role]
Date: [date]
## The Gap
[What inefficiency this is built on — named specifically]
## Gap Type
[Knowledge / Speed / Fragmentation / Discipline / Judgment / Relationship / System-level]
## Closing Speed
[Fast / Medium / Slow] — [rationale]
## Upstream Gap
[What new gap opens when this one closes]
## Position Assessment
- **If you're in the closing gap:** Migrate upstream. Build on judgment, not information.
- **If you're in the opening gap:** You're positioned well. Encode your advantage into systems.
## Recommended Action
[One specific thing to do based on the audit]Based on Nate Jones' Reinvention of Arbitrage framework.
Next step
Gap mapped → run kill-go for a proceed/pivot/kill verdict, or decision-brief to write the positioning up.
Part of the ThinkHaven Method Kit by Kevin Holland. Full Board of Directors experience: ThinkHaven
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.