[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FB23TF1ZG1HCW5KDBAXTK6":3,"skill-same:01M7FB23TF1ZG1HCW5KDBAXTK6":64},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7FB23TF1ZG1HCW5KDBAXTK6","founder-consumer",null,"The consumer panel. Spins up a swarm of buyer sub-agents (default 100, --quick for 20) trained on the user's target customer, each with a different income, age, buying behaviour and objection, shows every one the same pitch, and runs the business through 100 buyer scenarios to see who buys, who doesn't, and why. Tallies the answers into buy rates by segment, the reasons people pass in their own words, what would flip a no, and price answers for founder-pricing. Use when the user says \"would people buy this\", \"test it on customers\", \"run the consumer panel\", \"simulate buyers\", \"who is my customer\", or \"validate demand\".","siddu1004\u002FSFP","siddu1004","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F260113491?v=4","01M7F8W1SAJAR49097VRTE1TW5","Siddhardh Vanguri","01M7F8W1SYGY7JE15AHAECCT9R",5,"MIT","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fbusiness-ops\u002Fskills\u002Ffounder-consumer\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: founder-consumer\ndescription: >-\n  The consumer panel. Spins up a swarm of buyer sub-agents (default 100, --quick\n  for 20) trained on the user's target customer, each with a different income,\n  age, buying behaviour and objection, shows every one the same pitch, and runs\n  the business through 100 buyer scenarios to see who buys, who doesn't, and why.\n  Tallies the answers into buy rates by segment, the reasons people pass in their\n  own words, what would flip a no, and price answers for founder-pricing. Use when\n  the user says \"would people buy this\", \"test it on customers\", \"run the\n  consumer panel\", \"simulate buyers\", \"who is my customer\", or \"validate demand\".\nargument-hint: \"[--n 100 | --quick] [--seed S]\"\n---\n\n# founder-consumer\n\nThe craziest part of the pack. Instead of guessing whether people will buy, you\nask a hundred of them, each one a sub-agent playing a specific buyer drawn from\nyour target customer. You are the moderator. You never answer for a buyer.\n\nWhat the user typed after `\u002Ffounder-consumer`: `$ARGUMENTS`\n\n## The tool\n\nAll bookkeeping goes through `panel.py` in this skill's folder:\n\n```bash\npython3 \"${CLAUDE_SKILL_DIR}\u002Fpanel.py\" \u003Ccommand>\n```\n\nBelow, `PANEL` means exactly that. If the path is not expanded, use the base\ndirectory Claude Code printed for this skill. State lives in `founder\u002Fpanel\u002F`.\n\n## Step 1: the target customer\n\nWrite `founder\u002Fcustomer.json` (shape: `customer.example.json` in this folder):\n\n- `business`, and `target`: who the customer is, in one specific line.\n- `segments`: 2 to 4 groups with a `share` and an `income` range [low, high].\n- `behaviours`: 4 to 8 buying behaviours with a `share` and a `how` line\n  (daily regular, deal hunter, reads every review, loyal to a competitor...).\n- `objections`: the 4 to 8 doubts this kind of buyer really has.\n- `habits` (optional): everyday context lines that make a buyer concrete.\n\nGround it in something real. Use what the user knows about their customers, and\nif `\u002Ffounder-competitors` ran, the complaints in `founder\u002Fcompetitors.md`. If the\nuser has real customer data (interviews, reviews, survey answers), prefer it to\nyour guesses and say which parts are guesses. Show the user the profile in a few\nlines and let them correct it before you deal: a wrong customer makes the whole\npanel wrong.\n\n## Step 2: the pitch\n\nWrite `founder\u002Fpitch.md`: what a buyer would actually see. The product, the price,\nwhere and how to get it, any opening offer. Three to six plain lines, no\nsuperlatives, nothing the business cannot deliver. Every buyer sees exactly this.\n\n## Step 3: deal and run\n\n```bash\nPANEL init --customer founder\u002Fcustomer.json --pitch founder\u002Fpitch.md --n 100\nPANEL prompts\n```\n\n`init` deals the persona cards (same seed, same cards; the seed is recorded).\n`prompts` writes one brief per buyer and lists them in waves of 10. For each wave,\nsend ONE message with one Agent tool call per buyer in that wave (the Agent tool\nis called Task in older Claude Code versions):\n\n- `subagent_type`: `general-purpose`\n- `description`: `panel \u003Cid>`\n- `prompt`: `Read \u003Cbrief path> and follow it exactly. It is your whole brief.`\n\nWait for the whole wave before the next one. Claude Code runs about 10 tool calls\nat once by default, so 100 buyers is 10 waves. After the last wave:\n\n```bash\nPANEL check      # lists missing or broken answers\nPANEL prompts    # rewrites briefs for those only; run them once more\nPANEL tally\n```\n\nIf a buyer printed its JSON in its reply instead of writing the file (it happens),\nfile its own reply with `PANEL save \u003Cid>` and the reply on stdin; `save` refuses\nanything that is not a valid answer. A buyer that fails twice is left out and\ncounted in the results. Never write an answer for a buyer yourself.\n\nBefore a 100-buyer run, tell the user it is 100 sub-agent calls and suggest\n`--quick` (20 buyers) for a first look. Sub-agents write one file each into\n`founder\u002Fpanel\u002Fanswers\u002F`; in the default permission mode that is one approval per\nfile, so suggest accept-edits mode (Shift+Tab) for the run.\n\n## Step 4: read it to the user\n\n`PANEL tally` writes `founder\u002Fpanel\u002Fresults.md` and `results.json`. Give the user:\n\n1. The headline: \"40 buy · 60 pass\" and the buy rate.\n2. Who buys and who doesn't: the segment and behaviour rows that differ most.\n3. Why they pass: the top three reasons with one quote each, as written.\n4. What would flip a no: the most repeated answers.\n5. One sentence on what to change before spending money, and which skill does it\n   (pricing, offer, marketing).\n\n## Honest limits, say them once\n\nThese are simulated buyers. They are good at surfacing objections, segments and\nwording you had not thought of, and bad at predicting real conversion: language\nmodels lean agreeable, so treat the buy rate as an upper bound. Confirm the big\ncalls with real people (a waitlist, a pre-sale, a landing page with a price)\nbefore signing anything. Do not present panel quotes as customer testimonials.\n\n## The brief every buyer gets\n\n`panel.py` fills the card into a fixed template (see `BRIEF` in the script): who\nthe buyer is (name, age, segment, income, buying behaviour, a habit, the doubt\nthat comes to mind), the pitch word for word, an instruction not to be agreeable\nand not to invent facts, and the exact JSON to write: buys, purchases in the first\nmonth, a reason code, the reason in their own voice, their main objection, what\nwould change their mind, and four price answers (too cheap, a bargain, getting\nexpensive, too expensive). Never edit a brief for one buyer.\n\n## Output\n\n`founder\u002Fcustomer.json`, `founder\u002Fpitch.md`, `founder\u002Fpanel\u002F` (cards, briefs,\nanswers, results). Next: `\u002Ffounder-pricing` reads the price answers,\n`\u002Ffounder-offer` and `\u002Ffounder-marketing` read the objections.\n","# founder-consumer\n\nThe craziest part of the pack. Instead of guessing whether people will buy, you\nask a hundred of them, each one a sub-agent playing a specific buyer drawn from\nyour target customer. You are the moderator. You never answer for a buyer.\n\nWhat the user typed after `\u002Ffounder-consumer`: `$ARGUMENTS`\n\n## The tool\n\nAll bookkeeping goes through `panel.py` in this skill's folder:\n\n```bash\npython3 \"${CLAUDE_SKILL_DIR}\u002Fpanel.py\" \u003Ccommand>\n```\n\nBelow, `PANEL` means exactly that. If the path is not expanded, use the base\ndirectory Claude Code printed for this skill. State lives in `founder\u002Fpanel\u002F`.\n\n## Step 1: the target customer\n\nWrite `founder\u002Fcustomer.json` (shape: `customer.example.json` in this folder):\n\n- `business`, and `target`: who the customer is, in one specific line.\n- `segments`: 2 to 4 groups with a `share` and an `income` range [low, high].\n- `behaviours`: 4 to 8 buying behaviours with a `share` and a `how` line\n  (daily regular, deal hunter, reads every review, loyal to a competitor...).\n- `objections`: the 4 to 8 doubts this kind of buyer really has.\n- `habits` (optional): everyday context lines that make a buyer concrete.\n\nGround it in something real. Use what the user knows about their customers, and\nif `\u002Ffounder-competitors` ran, the complaints in `founder\u002Fcompetitors.md`. If the\nuser has real customer data (interviews, reviews, survey answers), prefer it to\nyour guesses and say which parts are guesses. Show the user the profile in a few\nlines and let them correct it before you deal: a wrong customer makes the whole\npanel wrong.\n\n## Step 2: the pitch\n\nWrite `founder\u002Fpitch.md`: what a buyer would actually see. The product, the price,\nwhere and how to get it, any opening offer. Three to six plain lines, no\nsuperlatives, nothing the business cannot deliver. Every buyer sees exactly this.\n\n## Step 3: deal and run\n\n```bash\nPANEL init --customer founder\u002Fcustomer.json --pitch founder\u002Fpitch.md --n 100\nPANEL prompts\n```\n\n`init` deals the persona cards (same seed, same cards; the seed is recorded).\n`prompts` writes one brief per buyer and lists them in waves of 10. For each wave,\nsend ONE message with one Agent tool call per buyer in that wave (the Agent tool\nis called Task in older Claude Code versions):\n\n- `subagent_type`: `general-purpose`\n- `description`: `panel \u003Cid>`\n- `prompt`: `Read \u003Cbrief path> and follow it exactly. It is your whole brief.`\n\nWait for the whole wave before the next one. Claude Code runs about 10 tool calls\nat once by default, so 100 buyers is 10 waves. After the last wave:\n\n```bash\nPANEL check      # lists missing or broken answers\nPANEL prompts    # rewrites briefs for those only; run them once more\nPANEL tally\n```\n\nIf a buyer printed its JSON in its reply instead of writing the file (it happens),\nfile its own reply with `PANEL save \u003Cid>` and the reply on stdin; `save` refuses\nanything that is not a valid answer. A buyer that fails twice is left out and\ncounted in the results. Never write an answer for a buyer yourself.\n\nBefore a 100-buyer run, tell the user it is 100 sub-agent calls and suggest\n`--quick` (20 buyers) for a first look. Sub-agents write one file each into\n`founder\u002Fpanel\u002Fanswers\u002F`; in the default permission mode that is one approval per\nfile, so suggest accept-edits mode (Shift+Tab) for the run.\n\n## Step 4: read it to the user\n\n`PANEL tally` writes `founder\u002Fpanel\u002Fresults.md` and `results.json`. Give the user:\n\n1. The headline: \"40 buy · 60 pass\" and the buy rate.\n2. Who buys and who doesn't: the segment and behaviour rows that differ most.\n3. Why they pass: the top three reasons with one quote each, as written.\n4. What would flip a no: the most repeated answers.\n5. One sentence on what to change before spending money, and which skill does it\n   (pricing, offer, marketing).\n\n## Honest limits, say them once\n\nThese are simulated buyers. They are good at surfacing objections, segments and\nwording you had not thought of, and bad at predicting real conversion: language\nmodels lean agreeable, so treat the buy rate as an upper bound. Confirm the big\ncalls with real people (a waitlist, a pre-sale, a landing page with a price)\nbefore signing anything. Do not present panel quotes as customer testimonials.\n\n## The brief every buyer gets\n\n`panel.py` fills the card into a fixed template (see `BRIEF` in the script): who\nthe buyer is (name, age, segment, income, buying behaviour, a habit, the doubt\nthat comes to mind), the pitch word for word, an instruction not to be agreeable\nand not to invent facts, and the exact JSON to write: buys, purchases in the first\nmonth, a reason code, the reason in their own voice, their main objection, what\nwould change their mind, and four price answers (too cheap, a bargain, getting\nexpensive, too expensive). Never edit a brief for one buyer.\n\n## Output\n\n`founder\u002Fcustomer.json`, `founder\u002Fpitch.md`, `founder\u002Fpanel\u002F` (cards, briefs,\nanswers, results). Next: `\u002Ffounder-pricing` reads the price answers,\n`\u002Ffounder-offer` and `\u002Ffounder-marketing` read the objections.\n",{"name":5,"description":7,"argument-hint":24},"[--n 100 | --quick] [--seed S]","main","15fa5201935d2b1d172b4e61c2360c908d876d20","plugins\u002Fbusiness-ops\u002Fskills\u002Ffounder-consumer",0,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP","https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fsfp-hive","https:\u002F\u002Fgithub.com\u002Fsiddu1004","I am a student at Amrita Vishwa Vidyapeetham pursuing my BTECH degree in Electronics and Electrical Engineering (2024-2028).","2026-11-09 16:04:40",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add siddu1004\u002FSFP --skill founder-consumer",{"tool":40,"command":41},"bunx","bunx skills add siddu1004\u002FSFP --skill founder-consumer",{"tool":43,"command":44},"pnpm","pnpm dlx skills add siddu1004\u002FSFP --skill founder-consumer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fbusiness-ops\u002Fskills\u002Ffounder-consumer\u002FSKILL.md",true,[48,54,60],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"customer.example.json","REFERENCE","参考文档",1702,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fbusiness-ops\u002Fskills\u002Ffounder-consumer\u002Fcustomer.example.json",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"panel.py","SCRIPT","脚本",19194,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fbusiness-ops\u002Fskills\u002Ffounder-consumer\u002Fpanel.py",{"path":61,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":62,"sourceHtmlUrl":63},"pitch.example.md",238,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fbusiness-ops\u002Fskills\u002Ffounder-consumer\u002Fpitch.example.md",[65,72,79,86,93,100],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7FEEDADZBNBVY19H3XZKCBQ","scientific-schematics","Generates scientific diagram drafts using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.7 Flash for quality review. Refines when the review requests improvement, with at most two generations. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fscientific-schematics\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FEE0JS04FE58MST48D0MMC","polyhaven-texture-apply","Apply realistic PBR textures from PolyHaven to any Blender object. Supports metals, wood, concrete, fabric, and more. Trigger when asked to texture an object, apply a material from PolyHaven, make something look like metal\u002Fwood\u002Fmarble, or change object surface.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-texture-apply\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FEDJRWV194TY411WVRS84W","polyhaven-studio-setup","Set up a professional product photography studio in Blender using PolyHaven HDRIs and PBR ground materials. Trigger when asked to create a studio setup, add HDRI lighting, set up product photography, or create a showroom scene.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-studio-setup\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FED5H2FGS50XGETMGSM0RV","polyhaven-scene-builder","Build complete product scenes using PolyHaven assets — HDRI environment, textured ground\u002Fpedestal, and optional props from the 3D model library. Trigger when asked to build a product scene, create a showcase setup, add a pedestal, or compose a product shot.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-scene-builder\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7FECSNZ2CJA7Z8TPE5R844R","polyhaven-material-swap","Cycle through multiple PolyHaven materials on a product and render each variant. Great for showing color\u002Ffinish options. Trigger when asked to show material variants, swap textures, create color options, show finish comparisons, or render product in different materials.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-material-swap\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7FECBPQ6YWH48PYAMS0C5CE","polyhaven-hdri-showcase","Render the same product across multiple HDRI environments and output a comparison grid. Trigger when asked to compare lighting setups, test different environments, show product in multiple settings, or create an HDRI comparison.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-hdri-showcase\u002FSKILL.md",[],[]]