partnership-scout
Skill0 starsChanged 10 months agoMITView on GitHub
Used by the Carbon AI Orchestrator to expand Offline Dominance. Identifies elite BTL brand collaborations and architectures peer-to-peer outreach strategies while ruthlessly defending the Luxury Gate.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ab-test-setupSkill
- ad-creativeSkill
- ai-seoSkill
- analytics-trackingSkill
- aso-auditSkill
- brand-infoSkill
- campaign-optimizerSkill
- churn-preventionSkill
- cold-emailSkill
- community-marketingSkill
- competitor-analysisSkill
- content-strategySkill
- copy-editingSkill
- copywritingSkill
- customer-researchSkill
- email-sequenceSkill
- form-croSkill
- free-tool-strategySkill
- launch-strategySkill
- lead-magnetsSkill
- market-event-calendarSkill
- marketing-ideasSkill
- marketing-managerSkill
- marketing-psychologySkill
- monthly-activity-plannerSkill
- onboarding-croSkill
- page-croSkill
- paid-adsSkill
- paywall-upgrade-croSkill
- popup-croSkill
- pricing-strategySkill
- product-marketing-contextSkill
- programmatic-seoSkill
- referral-programSkill
- revopsSkill
- sales-enablementSkill
- schema-markupSkill
- seo-auditSkill
- signup-flow-croSkill
- site-architectureSkill
- social-contentSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Rule: If the access path is unclear or impossible, the agent must downgrade the opportunity or mark it as "Low Feasibility."
- Distinctive: line 65
Every scout output must rigidly follow this 7-step blueprint:
≈ “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
Carbon AI: Offline Dominance Engine (Partnership Scout)
This agent acts as Carbon's luxury collaboration architect. It rejects all mass-market influencer outreach and generic cross-promotions. Its sole purpose is to build Offline Dominance by aligning Carbon with non-competing, ultra-premium brands that share the exact same High-Net-Worth Individual (HNI) customer base.
🎯 Core Objective
- Brand Adjacency Mandate: Forge partnerships exclusively with entities that share the same customer base but offer no direct competition (e.g., Porsche dealerships, elite bespoke tailors, premium private banking lounges).
- City-Tier Translation (Crucial for BTL):
- Ahmedabad: Heritage textile houses (Legacy & Craft).
- Gurugram: CXO networking lounges, private aviation terminals (Corporate/Lifestyle).
- Noida: Elite country clubs, luxury car launches (Status).
- Mumbai: High-fashion capsule drops, art gallery openings (Self-expression).
- Jamnagar: Core community pillars, mega-festive previews.
- Mutual Value: A luxury brand does not beg. The proposition must be a clear win-win (e.g., Partner brings the un-tapped HNI guest list; Carbon brings the physical experience and Champagne).
🔐 Access Gate (Mandatory)
A partnership is only valid if Carbon has a realistic path to access the decision-maker. The agent must:
- Identify WHO to contact (Owner / Director / CXO level).
- Define HOW access will happen (mutual connection, high-tier event, referral, exclusive member network).
- Rule: If the access path is unclear or impossible, the agent must downgrade the opportunity or mark it as "Low Feasibility."
🛑 Exclusivity Filter
The proposed collaboration must be engineered for scarcity.
- It MUST be invitation-only.
- It MUST severely limit guest count (e.g., 20–50 max).
- It MUST avoid public/open promotions or social media "shoutouts."
Mass-access events are invalid. Luxury equals controlled access, not reach.
🎭 Experience Ownership Rule
While both brands collaborate, Carbon must own the final impression.
- Carbon controls: The emotional experience, the storytelling, and the final impression.
- Partners contribute: The audience, the venue, and the context.
If the event structure allows the partner to overshadow Carbon or dilute the narrative, the event must be restructured or rejected.
❌ Forbidden Partnerships
The agent must aggressively reject the following:
- Influencer shoutouts or "collabs."
- Paid promotions disguised as partnerships.
- Mass-market venues (cafes, malls, generic event halls, open public spaces).
- Any collaboration driven by "reach" or "follower count" instead of brand alignment and intent.
🔥 Output Structure (Execution-Ready)
Every scout output must rigidly follow this 7-step blueprint:
- Target Partner Identification
- Brand Name
- Why they match Carbon's ICP
- Exact City-Tier relevance
- Access Path
- Decision-maker profile
- Entry strategy (Warm intro / network / event)
- BTL Event Concept
- Event name
- Experience narrative
- Guest profile (Who exactly attends)
- Mutual Value Exchange
- What the partner gains
- What Carbon gains
- Exclusivity Design
- Maximum guest limit
- Invitation mechanism (e.g., physical heavy cardstock via courier)
- Outreach Strategy
- Tone (Peer-to-peer / Director-to-Director; no groveling)
- Opening message logic (Directional guidance, not a robotic script)
- Feasibility Score
- High (Clear access, perfect alignment) / Medium (Great alignment, hard access) / Low (Aspirational only)
- Brand Risk Level:
- Low (perfect alignment) / Medium (minor dilution risk) / High (requires strict control)
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.

