{"title":"Bundles","description":"\u003cp\u003eThree role-based skill sets, each rewritten to one consistent standard. Buy the loop that matches how you work.\u003c\/p\u003e","products":[{"product_id":"the-solo-dev-set","title":"The Solo Dev Set","description":"\u003cp\u003eAfter this, your AI stops generating plausible-looking code against assumptions you never made — and starts asking the right questions before any code gets written.\u003c\/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eWho this is for\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003eSolo developers and small teams who use Claude Code, Cursor, or Codex daily. You feel the friction: the AI dives in too fast, generates 400 lines against guesses, you spend 30 minutes correcting drift. You want the assistant to behave like the colleague who's been here before — pausing for the right question instead of plowing ahead.\u003c\/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eBefore — default Claude, prompt: \"Add Stripe subscription billing\"\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003eStreams 400 lines of code immediately: Stripe SDK setup, route handlers, billing cycles, three plan tiers. Half of it built against assumptions you never made (monthly vs. annual? self-serve cancellation? proration rules?). You spend the next hour ripping out the 60% you didn't want.\u003c\/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eAfter — same prompt, with Solo Dev Set installed\u003c\/strong\u003e\u003c\/p\u003e\n\u003cpre\u003e\u003ccode\u003eQ: What's the billing model?\n   (a) Subscription [recommended]\n   (b) Usage-based\n   (c) Hybrid\n\u0026gt; a\n\nQ: How many tiers?\n   (a) Two   (b) Three [recommended]   (c) Four+\n\u0026gt; b\n\n[six more questions — annual option, free trial, proration, cancellation flow, dunning, invoicing. Each with a recommended answer. Three minutes.]\n\nNow writes the Stripe integration against the decisions you actually made. No wasted code. No rip-out hour.\u003c\/code\u003e\u003c\/pre\u003e\n\n\u003cp\u003e\u003cstrong\u003eWhat's inside\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003ccode\u003edecisions-grill\u003c\/code\u003e — interrogates the plan one question at a time, with a recommended answer for each, until every load-bearing decision is resolved\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003etests-first\u003c\/code\u003e — forces a failing test before any production code; bugs caught at write-time\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003eroot-cause-debug\u003c\/code\u003e — replaces guess-and-check thrashing with a four-phase root-cause process before any code changes\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003edeepen-modules\u003c\/code\u003e — surfaces only the refactors that earn their keep; small stable interfaces over loud rewrites\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003esend-for-review\u003c\/code\u003e — prepares the changes summary, evidence, and risk notes BEFORE you open the PR\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003eterse-mode\u003c\/code\u003e — cuts AI output roughly 75% with no loss of technical substance\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eThree ways to use this\u003c\/h3\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cstrong\u003ePaste it (any AI, 30 seconds, no install)\u003c\/strong\u003e\u003cbr\u003eOpen the .md file, copy contents, paste into Claude \/ ChatGPT \/ Cursor \/ Perplexity with: \"Read this and apply it whenever the task it describes comes up in our conversation.\" Done.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eInstall it (Claude Code \/ Cursor users)\u003c\/strong\u003e\u003cbr\u003eDrop the unzipped folder into \u003ccode\u003e~\/.claude\/skills\/\u003c\/code\u003e (Claude Code), \u003ccode\u003e.cursor\/skills\/\u003c\/code\u003e (Cursor), or your IDE's equivalent. Auto-loads next session.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNew to AI assistants?\u003c\/strong\u003e Get Claude free at claude.ai, then use Option 1.\u003c\/li\u003e\n\u003c\/ol\u003e\n\n\u003cp\u003e€24 — six skills · sum of parts €42\u003c\/p\u003e","brand":"SkillKeep","offers":[{"title":"Default Title","offer_id":57712232694095,"sku":null,"price":24.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1017\/4621\/3199\/files\/solo-dev-set.png?v=1779017332"},{"product_id":"the-shipping-set","title":"The Shipping Set","description":"\u003cp\u003eAfter this, the AI stops jumping from \"sure, let's build it\" to \"here are 800 lines of code\" — and starts running the actual workflow: PRD, plan, tickets, isolated execution, proof of completion.\u003c\/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eWho this is for\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003eEngineers shipping non-trivial features with an AI assistant. You've been burned by \"finished\" work that broke production, plans that skipped the awkward question, agent runs that started before the design was settled. You want the assistant to behave like the senior engineer who insists on the gates.\u003c\/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eBefore — default Claude, prompt: \"Add a feature flag system\"\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003eStreams 600 lines of code: flag service, admin UI, SDK, four storage backends. Half of it built against assumptions (per-user? per-org? gradual rollout? kill switch?). Three hours later, you've ripped out the SDK and started over.\u003c\/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eAfter — same prompt, with Shipping Set installed\u003c\/strong\u003e\u003c\/p\u003e\n\u003cpre\u003e\u003ccode\u003eStep 1 — PRD from context: 8 questions (granularity, kill-switch latency, auth integration, etc.) → one-page PRD.\nStep 2 — Implementation plan: architecture options A\/B\/C with trade-offs, picks one against your constraints.\nStep 3 — Slice into tickets: 8 tickets, ~4 hours each, dependencies marked.\nStep 4 — Isolate the work: new branch, empty scaffold, ready for tickets.\nStep 5 — Run the plan: picks ticket 1, implements, runs verification, stops at any blocker.\nStep 6 — Claim with proof: \"Ticket 1 done. Tests: 12 pass, 0 fail. Coverage: 89%. Diff: 240 lines.\"\u003c\/code\u003e\u003c\/pre\u003e\n\n\u003cp\u003e\u003cstrong\u003eWhat's inside\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003ccode\u003eprd-from-context\u003c\/code\u003e — turns \"add X\" into a one-page PRD with the awkward questions answered\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003eimplementation-plan\u003c\/code\u003e — designs the architecture with options + trade-offs before any code\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003eslice-into-tickets\u003c\/code\u003e — breaks the plan into 4-hour tickets with dependencies marked\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003eisolate-the-work\u003c\/code\u003e — sets up the branch, scaffolds, prevents work bleeding across features\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003erun-the-plan\u003c\/code\u003e — executes tickets one at a time, stops at the first blocker, doesn't skip ahead\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003eclaim-with-proof\u003c\/code\u003e — runs verification before saying \"done,\" shows the receipts inline\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eThree ways to use this\u003c\/h3\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cstrong\u003ePaste it (any AI, 30 seconds, no install)\u003c\/strong\u003e\u003cbr\u003eOpen the .md file, copy contents, paste into Claude \/ ChatGPT \/ Cursor \/ Perplexity with: \"Read this and apply it whenever the task it describes comes up in our conversation.\" Done.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eInstall it (Claude Code \/ Cursor users)\u003c\/strong\u003e\u003cbr\u003eDrop the unzipped folder into \u003ccode\u003e~\/.claude\/skills\/\u003c\/code\u003e (Claude Code), \u003ccode\u003e.cursor\/skills\/\u003c\/code\u003e (Cursor), or your IDE's equivalent. Auto-loads next session.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNew to AI assistants?\u003c\/strong\u003e Get Claude free at claude.ai, then use Option 1.\u003c\/li\u003e\n\u003c\/ol\u003e\n\n\u003cp\u003e€24 — six skills · sum of parts €42\u003c\/p\u003e","brand":"SkillKeep","offers":[{"title":"Default Title","offer_id":57712233316687,"sku":null,"price":24.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1017\/4621\/3199\/files\/shipping-set.png?v=1779017333"},{"product_id":"the-solo-marketer-set","title":"The Solo Marketer Set","description":"\u003cp\u003eAfter this, the AI stops defaulting to generic SaaS copy and starts writing pages, audits, outreach, and lifecycle emails that match the specifics of your offer and your buyer.\u003c\/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eWho this is for\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003eFounders and solo marketers running growth without a team behind them. You've watched the AI generate \"Boost your productivity!\" headlines for every product you've fed it. You want it to interrogate the offer first, then write copy that says something a real customer would actually nod at.\u003c\/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eBefore — default Claude, prompt: \"Write a landing page for my project management tool\"\u003c\/strong\u003e\u003c\/p\u003e\n\u003cpre\u003e\u003ccode\u003eStreams a generic SaaS page:\n  \"Supercharge Your Team's Productivity!\"\n  \"Streamline workflows. Boost collaboration. Ship faster.\"\n  [Feature bullets. Three pricing tiers. Stock testimonial placeholders.]\n\nPolished. Says nothing specific. Doesn't sound like you.\u003c\/code\u003e\u003c\/pre\u003e\n\n\u003cp\u003e\u003cstrong\u003eAfter — same prompt, with Solo Marketer Set installed\u003c\/strong\u003e\u003c\/p\u003e\n\u003cpre\u003e\u003ccode\u003eQ: Who is the page for? (PMs \/ engineers \/ both)\nQ: What's the one job they hire your product for?\nQ: What's the alternative they're using now?\nQ: What do they hate about it?\nQ: Why are they on THIS page (researching, comparing, ready to buy)?\n[three more questions, then writes:]\n\n\"For PMs who run sprint planning in a tab next to Slack.\"\n\"The replacement for the workflow you've patched together from Notion, Linear, and a Google Doc.\"\n[Hero with 3 headline alternatives. Body with concrete customer language. CTA with 2 alternatives.]\u003c\/code\u003e\u003c\/pre\u003e\n\n\u003cp\u003e\u003cstrong\u003eWhat's inside\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003ccode\u003epage-copy\u003c\/code\u003e — interrogates the offer first, then writes headlines + body + CTAs that say something specific\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003econversion-audit\u003c\/code\u003e — returns prioritised fixes across seven dimensions (not \"try a different button color\")\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003ecold-outreach\u003c\/code\u003e — writes outreach that opens conversations: specific subject lines, plain body, one clear ask\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003elifecycle-emails\u003c\/code\u003e — writes the welcome → activation → re-engage flow against actual user behavior, not generic templates\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eThree ways to use this\u003c\/h3\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cstrong\u003ePaste it (any AI, 30 seconds, no install)\u003c\/strong\u003e\u003cbr\u003eOpen the .md file, copy contents, paste into Claude \/ ChatGPT \/ Cursor \/ Perplexity with: \"Read this and apply it whenever the task it describes comes up in our conversation.\" Done.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eInstall it (Claude Code \/ Cursor users)\u003c\/strong\u003e\u003cbr\u003eDrop the unzipped folder into \u003ccode\u003e~\/.claude\/skills\/\u003c\/code\u003e (Claude Code), \u003ccode\u003e.cursor\/skills\/\u003c\/code\u003e (Cursor), or your IDE's equivalent. Auto-loads next session.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNew to AI assistants?\u003c\/strong\u003e Get Claude free at claude.ai, then use Option 1.\u003c\/li\u003e\n\u003c\/ol\u003e\n\n\u003cp\u003e€24 — four skills · sum of parts €28\u003c\/p\u003e","brand":"SkillKeep","offers":[{"title":"Default Title","offer_id":57712233546063,"sku":null,"price":24.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1017\/4621\/3199\/files\/solo-marketer-set.png?v=1779017333"},{"product_id":"the-founder-set","title":"The Founder Set","description":"\u003cp\u003eAfter this, the AI stops generating generic founder advice (\"focus on PMF!\") and starts running the actual decisions: offer design, price-setting, pitch shaping, deliberate go\/no-go calls.\u003c\/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eWho this is for\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003eSolo founders and early teams making the inside-the-head calls — what to charge, what to build next, what to say to investors, what to ignore. You've gotten generic YC-flavored advice from every AI you've asked. You want it to interrogate your situation specifically and give you a real answer.\u003c\/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eBefore — default Claude, prompt: \"What should I price my SaaS at?\"\u003c\/strong\u003e\u003c\/p\u003e\n\u003cpre\u003e\u003ccode\u003e\"Most early-stage SaaS prices in three tiers: $9 (starter), $29 (pro), $99 (business). You can also try usage-based pricing. Make sure to A\/B test! Look at competitors. Don't forget to talk to customers.\"\n\nGeneric. Cites no specifics about YOUR offer. Three tiers as default because every SaaS does three tiers.\u003c\/code\u003e\u003c\/pre\u003e\n\n\u003cp\u003e\u003cstrong\u003eAfter — same prompt, with Founder Set installed (price-the-offer)\u003c\/strong\u003e\u003c\/p\u003e\n\u003cpre\u003e\u003ccode\u003eQ: What's the offer? (one-sentence description)\nQ: Who's the target customer?\nQ: What's their alternative? (free DIY \/ competitor \/ status quo)\nQ: What's the unit economics? (CAC, gross margin per unit)\nQ: What gate do they pass through first — free trial, demo, direct?\n[three more questions about willingness-to-pay signals]\n\n\"Price at €39\/month. Single tier. Here's why:\n- Mid-tier marketing agencies (your target) currently pay €120\/month for the closest alternative.\n- Gross margin at €39 is 78% — comfortable.\n- Free trial is the right gate. Low commitment; you have time to show value before they decide.\n- Three tiers would hurt you here. The buyer doesn't know enough about your product to self-select, and tier-comparison friction kills conversion at your stage.\n- Reconsider in 3 months once you have 50 paying customers and real data.\"\u003c\/code\u003e\u003c\/pre\u003e\n\n\u003cp\u003e\u003cstrong\u003eWhat's inside\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003ccode\u003eirresistible-offer\u003c\/code\u003e — designs the offer: what they get, how, the guarantee, what's stacked in\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003eunit-economics\u003c\/code\u003e — runs the math: CAC, LTV, payback period, gross margin per unit\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003eprice-the-offer\u003c\/code\u003e — sets the actual price against alternatives + willingness-to-pay signals\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003einvestor-deck\u003c\/code\u003e — structures the deck around the question the round is really being raised to answer\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003edecide-deliberately\u003c\/code\u003e — names the decision, the options, the trade-offs, the call — before slack-asking five advisors\u003c\/li\u003e\n\u003cli\u003e\n\u003ccode\u003efounder-focus\u003c\/code\u003e — drops the things that aren't on the path, names what is\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eThree ways to use this\u003c\/h3\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cstrong\u003ePaste it (any AI, 30 seconds, no install)\u003c\/strong\u003e\u003cbr\u003eOpen the .md file, copy contents, paste into Claude \/ ChatGPT \/ Cursor \/ Perplexity with: \"Read this and apply it whenever the task it describes comes up in our conversation.\" Done.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eInstall it (Claude Code \/ Cursor users)\u003c\/strong\u003e\u003cbr\u003eDrop the unzipped folder into \u003ccode\u003e~\/.claude\/skills\/\u003c\/code\u003e (Claude Code), \u003ccode\u003e.cursor\/skills\/\u003c\/code\u003e (Cursor), or your IDE's equivalent. Auto-loads next session.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNew to AI assistants?\u003c\/strong\u003e Get Claude free at claude.ai, then use Option 1.\u003c\/li\u003e\n\u003c\/ol\u003e\n\n\u003cp\u003e€24 — six skills · sum of parts €42\u003c\/p\u003e","brand":"SkillKeep","offers":[{"title":"Default Title","offer_id":57712469934415,"sku":null,"price":24.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1017\/4621\/3199\/files\/founder-set.png?v=1779017332"}],"url":"https:\/\/www.skillkeep.io\/collections\/bundles.oembed","provider":"SkillKeep","version":"1.0","type":"link"}