hamzabellouch/agent-skills / Business/Marketing_and_Growth/marketing-marketing-ideas
marketing-ideas
VerifiedWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' 'ideas to grow,' 'what else can I try,' 'I don't know how to market this,' 'brainstorm marketing,' or 'what marketing should I do.' Use this as a starting point whenever someone is stuck or looking for inspiration on how to grow. For specific channel execution, see the relevant skill (ads, social, emails, etc.).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.2 KB |
| evals/evals.json | config | 5.8 KB |
| references/ideas-by-category.md | markdown | 14.9 KB |
evals/evals.json
View on GitHub{
"skill_name": "marketing-ideas",
"evals": [
{
"id": 1,
"prompt": "I need marketing ideas for my SaaS product. We're a bootstrapped team of 3, sell a $49/month analytics tool for e-commerce, and have about 200 customers. Budget is tight — maybe $500/month for marketing.",
"expected_output": "Should check for product-marketing.md first. Should filter ideas by low budget and early-stage constraints. Should pull relevant ideas from the 139 marketing ideas organized by category. Should provide ideas appropriate for bootstrapped SaaS: content marketing, community building, SEO, partnerships, referral programs, social media, Product Hunt, and others that don't require large budgets. Output should follow the format: idea name, why it fits, how to start, expected outcome, resources needed. Should prioritize by likely impact given their stage.",
"assertions": [
"Checks for product-marketing.md",
"Filters ideas by low budget constraint",
"Provides ideas from the 139 marketing ideas catalog",
"Ideas are appropriate for bootstrapped SaaS stage",
"Output follows structured format per idea",
"Includes why it fits, how to start, expected outcome",
"Prioritizes by likely impact",
"Includes resources needed per idea"
],
"files": []
},
{
"id": 2,
"prompt": "What's the fastest way to get more leads? We sell enterprise security software and have a $10k/month marketing budget.",
"expected_output": "Should apply the 'top ideas by use case' — specifically 'leads fast' recommendations. Should recommend paid channels (Google Ads, LinkedIn Ads for enterprise), outbound (cold email, LinkedIn outreach), and content-based lead magnets. Should filter for enterprise-appropriate tactics. Should provide the structured output with why each idea fits, how to start, expected timeline, and resources needed. Should note that 'fast leads' typically means paid or outbound channels.",
"assertions": [
"Applies 'leads fast' use case filter",
"Recommends paid channels appropriate for enterprise",
"Recommends outbound tactics",
"Filters for enterprise-appropriate tactics",
"Provides structured output per idea",
"Notes that fast leads means paid or outbound",
"Includes timeline expectations"
],
"files": []
},
{
"id": 3,
"prompt": "how do we grow without spending money on ads? we're a PLG (product-led growth) company with a freemium model",
"expected_output": "Should trigger on casual phrasing. Should apply the 'PLG' use case filter from top ideas. Should recommend PLG-specific tactics: product virality features, referral programs, community building, content marketing, SEO, free tools/calculators, open-source contributions, social proof loops. Should avoid ad-dependent ideas given the constraint. Should provide structured output with implementation guidance.",
"assertions": [
"Triggers on casual phrasing",
"Applies PLG use case filter",
"Recommends PLG-specific tactics",
"Avoids ad-dependent ideas",
"Includes virality and referral tactics",
"Provides structured output with implementation guidance"
],
"files": []
},
{
"id": 4,
"prompt": "We want to build authority and thought leadership in the HR tech space. We're a newer company and nobody knows who we are yet.",
"expected_output": "Should apply the 'authority building' use case filter. Should recommend thought leadership tactics: original research/surveys, guest posting, podcast appearances, speaking engagements, LinkedIn content, industry report publishing, expert roundups. Should note that authority building is a longer-term play. Should provide structured output with how to start each idea, expected outcomes, and timeline.",
"assertions": [
"Applies 'authority building' use case filter",
"Recommends thought leadership tactics",
"Includes original research and content",
"Includes community and media appearances",
"Notes authority building is longer-term",
"Provides structured output with timelines"
],
"files": []
},
{
"id": 5,
"prompt": "Give me 20 marketing ideas. We sell project management software.",
"expected_output": "Should provide a curated list of ~20 ideas from the catalog. Should organize them by category or by effort/impact. Should provide brief implementation context for each. Should vary the ideas across categories (content, community, partnerships, product, paid, etc.) for a well-rounded set. Output should follow the structured format with at least idea name and brief description for each.",
"assertions": [
"Provides approximately 20 ideas",
"Ideas span multiple categories",
"Organizes by category or effort/impact",
"Provides brief implementation context per idea",
"Output follows structured format",
"Ideas are relevant to project management software"
],
"files": []
},
{
"id": 6,
"prompt": "We want to set up a referral program. How should we structure it?",
"expected_output": "Should recognize this is specifically a referral program design request. Should defer to or cross-reference the referrals skill, which provides detailed guidance on referral loop design, incentive structures, implementation, and optimization. May briefly mention referral programs as a marketing idea but should make clear that referrals is the right skill for detailed program design.",
"assertions": [
"Recognizes this as a referral program design request",
"References or defers to referrals skill",
"Does not attempt detailed referral program design",
"May briefly mention as a marketing idea"
],
"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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |