JasonColapietro/suede-creator-skills / skills/suede-marketing-plan
suede-marketing-plan
VerifiedSuede Marketing Planning Skills: a scored tactic shortlist or a full AARRR operating plan with a 90-day plan, 12-month roadmap, and measurement. Use when asked "what should we try next" or for a marketing plan grounded in budget, capacity, and evidence. NOT FOR: channel execution, contested bets (suede-marketing-council), recurring loops (suede-marketing-loops), or positioning alone (suede-product-marketing).
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 4.4 KB |
| SKILL.md | skill md | 13.1 KB |
| agents/openai.yaml | config | 669 B |
| evals/evals.json | config | 11.6 KB |
| references/aarrr-framework.md | markdown | 10.9 KB |
| references/budget-planning.md | markdown | 4.4 KB |
| references/client-types.md | markdown | 11.1 KB |
| references/current-state-rubric.md | markdown | 13.7 KB |
| references/example-quietude.md | markdown | 65.4 KB |
| references/funding-stage-unlocks.md | markdown | 3.6 KB |
| references/growth-patterns.md | markdown | 3.0 KB |
| references/idea-cross-reference.md | markdown | 24.7 KB |
| references/measurement-framework.md | markdown | 10.3 KB |
| references/methodology.md | markdown | 29.4 KB |
| references/ops-stack-mapping.md | markdown | 11.6 KB |
| references/plan-template.md | markdown | 19.7 KB |
| references/tactic-library.md | markdown | 17.0 KB |
| references/tactic-scoring.md | markdown | 3.5 KB |
| references/team-and-agency-model.md | markdown | 3.6 KB |
| references/worked-contract.md | markdown | 2.3 KB |
evals/evals.json
View on GitHub{
"skill_name": "suede-marketing-plan",
"evals": [
{
"id": 1,
"prompt": "I'm starting a fractional CMO engagement with a Series A B2B SaaS doing $2M ARR, 12-person team with 1 marketer, $20K/month marketing budget. They want a marketing plan we can share with the team and the board. Build it.",
"expected_output": "Should check for the canonical product-marketing context first. Should ask for client name or use a slug. Should walk through three-phase workflow (INIT → REVIEW → FINALIZE), starting with intake covering financial constraints, team/owner capacity, budget/authority, channel evidence, what's done, in-flight, and available tooling. Should produce a 13-section AARRR-structured plan: executive summary, strategic frame, current state (scored against the embedded 17-section rubric), Acquisition, Activation, Retention, Referral, Revenue, 90-day roadmap with owner-assigned moves, 12-month outlook with conditional capabilities tied to verified evidence/resources/approval/review/stop rules, marketing operations stack mapping available public Suede skills and authorized tools to AARRR owners and fallbacks, tactical idea bank cross-referencing all 142 tactic-library entries to AARRR + client-specific status, measurement framework with source-backed metrics + RACI + open decisions. Should be comprehensive and Notion-paste-ready. Should be specific to the client's dated evidence and authority, not generic.",
"assertions": [
"Checks for product-marketing.md",
"Asks for client name or uses a slug",
"Walks through INIT phase with structured intake",
"Produces 13-section plan structured by AARRR",
"Section 3 scores against the embedded 17-section rubric",
"Section 9 (90-day roadmap) has owner-assigned moves, not just actions",
"Section 10 names evidence/resource/owner/approval/review/stop conditions for every conditional capability",
"Section 11 maps relevant Suede skills plus currently callable authorized tools or manual fallbacks to each AARRR stage",
"Section 12 cross-references all 142 tactic-library entries with client-specific status",
"Output is Notion-paste-ready markdown",
"Plan is specific to the client (their budget, team, current channels), not generic"
],
"files": []
},
{
"id": 2,
"prompt": "We're pre-seed bootstrapped, $0 paid marketing budget, 4-person team building a D2C consumer app. Founder wants a 90-day plan + 12-month roadmap they can show investors during the upcoming raise. The product is in beta.",
"expected_output": "Should recognize that the stated current paid budget is zero and avoid paid acquisition until a specific test is funded and approved. Should prioritize capacity-feasible organic, lifecycle, and referral hypotheses only when they fit current evidence. Should map conditional unlocks from verified cash, owners, tracking, and decision rules rather than funding-stage defaults. Should respect that the product is in beta and account for activation/throttling gates. Should diagnose the binding AARRR constraint from evidence rather than assume one. Plan must be investor-friendly: exec summary can be lifted into an update.",
"assertions": [
"Uses the verified zero-paid-budget constraint rather than a stage profile",
"Skips paid acquisition execution until an exact test is evidenced, funded, and approved",
"Does not hardcode organic, lifecycle, referral, or any channel from zero paid budget or archetype",
"Names evidence, owner, approval, and stop conditions for future unlocks",
"Accounts for product being in beta",
"Identifies the binding AARRR stage from available evidence",
"Executive summary can be lifted into an investor update",
"Plan is operationally honest: doesn't pretend paid budget exists"
],
"files": []
},
{
"id": 3,
"prompt": "we have an audit already done: can you take that and turn it into a real plan",
"expected_output": "Should ask for the audit output (file path or paste). Should recognize that current-state scoring already exists and ingest it directly into Section 3: don't re-score. Should note scoring date in case material has shifted since. Should proceed with full 13-section plan generation using audit findings to inform 90-day roadmap and AARRR sections (gaps from audit become moves in the plan).",
"assertions": [
"Asks for the audit output",
"Ingests prior audit scoring directly into Section 3",
"Does not re-score what's already been scored",
"Notes the scoring date and flags any shifted material",
"Uses audit gaps to inform 90-day roadmap and AARRR section moves",
"Still produces a full 13-section plan, not just Section 3"
],
"files": []
},
{
"id": 4,
"prompt": "/suede-marketing-plan acme-saas: pick up where we left off",
"expected_output": "Should read .agents/suede-marketing-plans/acme-saas/progress.md to determine state machine phase. Should resume from the exact next unfinished section in REVIEW phase, or transition to FINALIZE only if all 13 checkboxes and approved section artifacts reconcile. Should NOT silently restart. If progress.md is missing, should initialize the complete legacy/interrupted INIT schema and preserve partial research. Only a finalized state should ask: revise as v{N+1}, start fresh, or re-open a section.",
"assertions": [
"Reads .agents/suede-marketing-plans/acme-saas/progress.md",
"Resumes from next unfinished section based on state machine",
"Does not silently restart from scratch",
"Distinguishes missing progress legacy INIT from finalized revise/fresh/re-open choices",
"Atomically persists each confirmed sections/NN.md artifact plus checkbox, approved path, exact next current_section, and timestamp"
],
"files": []
},
{
"id": 5,
"prompt": "I need a plan for a hybrid hardware+software wellness company. They sell a physical product and a subscription app. Series A, $100K/month marketing budget, 8-person team including a marketing lead.",
"expected_output": "Should recognize the hybrid hardware+software business model and consult references/client-types.md for candidate questions, not defaults. Should diagnose each AARRR constraint from dated client evidence. Hardware/software cohort joins, inventory, fulfillment, margin, unboxing/setup, subscription retention, and blended unit economics should be investigated where relevant. The Series A label and stated budget must not choose channels or spend; any paid test needs audience/economics/tracking/creative-capacity evidence plus owner, maximum exposure, approval, review date, and stop conditions. Idea bank should skip ideas that conflict with verified brand, rights, or hardware constraints.",
"assertions": [
"Recognizes hybrid hardware+software archetype",
"Does not prescribe acquisition channels from the hybrid archetype",
"Tests whether unboxing, setup, first session, or paywall is the measured activation constraint",
"Tests lifecycle and community hypotheses against current evidence and capacity",
"Tests gifting and review hypotheses against rights, economics, and customer evidence",
"Uses a finance-approved blended economics definition with source dates and ranges",
"Does not use the Series A label to recommend spend",
"Idea bank skips ideas that conflict with brand fit, with explicit rationale"
],
"files": []
},
{
"id": 6,
"prompt": "Just give me a quick marketing plan. Don't make it long.",
"expected_output": "Should resist defaulting to a short plan. Should explain that suede-marketing-plan is the comprehensive fCMO-deliverable artifact (~10K words) and that for a single-channel quick plan, the channel-specific public Suede skill is the right tool (suede-emails, suede-ads, suede-seo-audit, etc.). Should offer alternatives: (a) full suede-marketing-plan as designed, or (b) point to a specific public Suede skill for the user's actual need. Should NOT silently produce a stripped-down 3K-word plan that misses the ops stack or the idea bank.",
"assertions": [
"Resists short-plan request and explains why",
"Names suede-marketing-plan as the comprehensive fCMO artifact",
"Recommends channel-specific skills for single-channel quick plans",
"Offers alternatives clearly",
"Does not silently produce a stripped-down plan"
],
"files": []
},
{
"id": 7,
"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 142 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",
"Pulls candidates from the 142-idea tactic library and runs Shortlist mode",
"Ideas are appropriate for bootstrapped SaaS stage",
"Output follows structured format per idea",
"Includes why it fits, how to start, metric, review date, and stop condition",
"Surfaces at most 5 and names one Not recommended tactic",
"Includes resources needed per idea"
],
"files": []
},
{
"id": 8,
"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 score PLG-appropriate candidates against the rubric. 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",
"Scores candidates on the six rubric dimensions",
"Recommends PLG-specific tactics",
"Avoids ad-dependent ideas",
"Includes virality and referral tactics",
"Provides structured output with implementation guidance"
],
"files": []
},
{
"id": 9,
"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: 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 |