JasonColapietro/suede-creator-skills / skills/suede-co-marketing
suede-co-marketing
VerifiedSuede Co-Marketing Skills. Use when asked to "find co-marketing partners" or plan a joint campaign: evidence-backed fit, reciprocal value, format, roles, consent, shared KPIs and content. NOT FOR: affiliate/referral programs (suede-referrals), software release packaging (suede-launch-packaging), or partner-facing sales collateral (suede-sales-enablement).
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 4.3 KB |
| SKILL.md | skill md | 12.8 KB |
| agents/openai.yaml | config | 539 B |
| evals/evals.json | config | 6.8 KB |
| references/campaign-formats.md | markdown | 2.7 KB |
| references/output-templates.md | markdown | 2.0 KB |
| references/worked-contract.md | markdown | 1.8 KB |
evals/evals.json
View on GitHub{
"skill_name": "suede-co-marketing",
"evals": [
{
"id": 1,
"prompt": "We make a project management tool for design agencies. Who should we look for as co-marketing partners?",
"expected_output": "Should check for product-marketing.md first. Should apply the Partner Identification Framework with audience overlap analysis. Should identify ideal partner characteristics: same buyer persona (design agencies), different problem solved, adjacent in the workflow. Should suggest specific partner categories: design tools (Figma, Adobe), proposal/contract tools (Bonsai, HoneyBook), client communication (Notion, Slack), invoicing/payments (Stripe, FreshBooks), file storage/handoff (Dropbox, Frame.io). Should recommend audience scoring criteria. Should suggest sources to find partners: integration ecosystem, Crossbeam/Reveal for account overlap, customer surveys, G2/Capterra category neighbors, podcasts/newsletters they sponsor.",
"assertions": [
"Checks for product-marketing.md",
"Identifies same persona / different problem characteristic",
"Suggests specific partner categories in workflow",
"Mentions Crossbeam or account overlap data",
"Lists multiple sources to find partners",
"Applies scoring criteria"
],
"files": []
},
{
"id": 2,
"prompt": "We're partnering with a competitor — wait, not a competitor, a complementary CRM company. Help us brainstorm 5 campaign ideas we could run together.",
"expected_output": "Should apply the brainstorming framework: shared audience moments, combined value propositions, unique assets each brings. Should propose campaign ideas across multiple types from the campaign type tables (content partnerships, webinars/events, product/integration marketing, community/social). Should suggest specific ideas like: co-authored blog post or research report, joint webinar, 'better together' integration landing page, joint case study with shared customer, integration launch, bundle/discount, conference booth sharing. Should ask the campaign idea prompts to spark ideas: what would we create if we had to launch in 2 weeks, what content do both audiences desperately need, what data do we both have that would make a compelling story.",
"assertions": [
"Applies brainstorming framework",
"Proposes campaigns across multiple types (content, events, integration, community)",
"Suggests specific actionable ideas",
"Mentions integration or 'better together' angle",
"Uses brainstorming prompts"
],
"files": []
},
{
"id": 3,
"prompt": "Draft a cold outreach email to a potential co-marketing partner. They're a content management platform and we make a marketing analytics tool. Both serve B2B marketing teams.",
"expected_output": "Should use the cold outreach template structure. Should include: subject line with both company names, brief role intro, specific observation about audience overlap (not generic), one concrete campaign idea (not 'let's do something'), clear ask for a quick call. Should keep it short and personal. Should optionally mention call prep: account overlap data (Crossbeam/Reveal), 2-3 specific campaign ideas, audience metrics, past partnership examples, clear ask of what's wanted and what's offered.",
"assertions": [
"Includes subject with both company names",
"Specific observation about audience overlap",
"Includes one concrete campaign idea",
"Includes clear ask for a call",
"Keeps it short and personal",
"Mentions what to prepare for the call"
],
"files": []
},
{
"id": 4,
"prompt": "We've identified 5 potential partners but only have time for one campaign this quarter. How should we pick?",
"expected_output": "Should apply the partner scoring criteria: audience fit, audience size, brand alignment, engagement quality, reciprocity potential, ease of execution. Should recommend scoring each partner 1-5 across these criteria. Should weight by current goal (e.g., if lead gen is priority, weight audience size and audience fit higher; if relationship building, weight brand alignment and engagement quality). Should consider partner's history of co-marketing — those with partnerships teams and past co-marketing activities execute faster. Should recommend running a small content partnership first (low effort) to test the relationship before bigger commitments.",
"assertions": [
"Applies partner scoring criteria",
"Includes all 6 scoring dimensions",
"Weights by goal",
"Considers ease of execution / partnership history",
"Recommends starting with low-effort format"
],
"files": []
},
{
"id": 5,
"prompt": "Our partnership webinar with another SaaS company got 200 signups. How do we split the leads?",
"expected_output": "Should address the lead handling question from the Structuring the Partnership section. Should explain common splits: each partner keeps their own registrations (cleanest but loses cross-pollination), all leads shared between both (max reach, requires clear MQL/SQL handoff), split by audience source (your list vs theirs). Should recommend documenting this in advance in a co-marketing agreement covering campaign description, responsibilities, timeline, lead handling, promotion, branding, costs, metrics sharing. Should note measuring success: leads generated per partner, lead quality (MQL/SQL conversion rate), revenue attributed. Should recommend a post-campaign debrief and discussing future collaboration if it worked.",
"assertions": [
"Explains lead split options",
"Recommends documenting in agreement",
"Lists agreement components",
"Mentions measuring lead quality not just volume",
"Recommends post-campaign debrief"
],
"files": []
},
{
"id": 6,
"prompt": "Our customer success team wants us to launch a referral program. Can you help us design one?",
"expected_output": "Should recognize this is about customer referrals, not co-marketing between companies. Should redirect to suede-referrals, which specifically handles customer referral and affiliate programs (customers referring customers). Should note co-marketing is partner-to-partner marketing while referrals is customer-driven word-of-mouth. May offer brief co-marketing context if it's relevant to the strategy, but should make clear suede-referrals is the right skill for the task.",
"assertions": [
"Recognizes this is customer referral, not co-marketing",
"Defers to suede-referrals",
"Distinguishes co-marketing from referral programs",
"Does not attempt full co-marketing strategy"
],
"files": []
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |