[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DM3XBER2WNQC5NSR80R9J7":3,"skill-same:01M7DM3XBER2WNQC5NSR80R9J7":62},{"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":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M7DM3XBER2WNQC5NSR80R9J7","idea-autopsy",null,"Autopsy a business idea before you build it: kill-list check, five hard filters, a free-AI one-prompt test, live ad-market verification, and a verdict with a named kill-pattern.","Hazek-dc\u002FPresensiGuru_FaceNet_EMAR","Hazek-dc","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F75208960?v=4","01M7DEQV5B4YGS86A81DYH81DR","Hazek","01M7DEQV5XP4TM0C6NTHXCXCHR",1,"MIT","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fidea-autopsy\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: idea-autopsy\ndescription: \"Autopsy a business idea before you build it: kill-list check, five hard filters, a free-AI one-prompt test, live ad-market verification, and a verdict with a named kill-pattern.\"\ncategory: product\nrisk: critical\nsource: community\nsource_repo: hafiz-actyte\u002Fidea-autopsy\nsource_type: community\ndate_added: \"2026-07-10\"\nauthor: hafiz-actyte\ntags: [business-ideas, idea-validation, market-research, startup, founders]\ntools: [claude, cursor, gemini]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fhafiz-actyte\u002Fidea-autopsy\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# Idea Autopsy\n\n## Overview\n\nTurns the agent into a ruthless business-idea pathologist: instead of encouraging\nthe user, it hunts for the one sentence that kills an idea — before any money or\nweeks are spent building it. Built from a real founder kill-list of 42 dead ideas\n(including a 9\u002F10-scored idea and one that turned out to be federally illegal to\ncharge for). Every autopsy ends in a hard verdict: DEAD with a named kill-pattern,\nor SURVIVED with the one cheapest test that could still kill it.\n\n## When to Use This Skill\n\n- Use when the user proposes a new business, product, or side-project idea\n- Use when the user asks \"should I build X?\" or \"validate this idea\"\n- Use when the user says \"autopsy my idea\"\n- Use before any market-research or build-planning task for a new venture\n\n## How It Works\n\n### Step 1: Kill-list check\n\nIf the project contains a `REJECTION.md` (the user's personal kill-list), read it\nfirst. A NICHE match (same niche as a killed row) = verdict DEAD, cite the row,\nstop. A KILL-PATTERN match alone (new niche, previously-seen pattern) is a strong\nprior, NOT a verdict: name the matching pattern, then run the specific check for\nthat pattern (the relevant filter or test below) to confirm it actually applies\nbefore declaring death. If no kill-list exists, ask the user for permission to create one\nwith exactly this schema — this autopsy writes its first row:\n\n```markdown\n# REJECTION.md — my kill-list\n\n## Killed ideas\n\n| # | Idea\u002FNiche | Killed (date) | Hard reason (one line) | Pattern |\n|---|-----------|---------------|------------------------|---------|\n\n## Survivors under test\n\n| Idea | Passed filters (date) | Pending test | Deadline |\n|------|----------------------|--------------|----------|\n```\n\n### Step 2: The five filters\n\nDemand evidence, not optimism. One hard NO = dead.\n\n1. **Real pain?** 2am-problem, or a nice-to-have \"vitamin\"?\n2. **Buyer has money?** Right now — not after the product helps them.\n3. **Proven demand?** Can the user name a single live competitor ad?\n4. **Legal to charge for?** Regulated, licensed, or illegal in the target market? Name the law if suspicion exists.\n5. **A moat?** What stops the 50th copycat next month?\n\n### Step 3: The free-AI test\n\nTry to produce the idea's core deliverable with one prompt to a frontier model.\nIf one prompt produces the whole deliverable free, the verdict is DEAD with\nkill-pattern `free-AI`: the user doesn't have a product, they have a prompt.\n\n### Step 4: Live-market verification (own eyes)\n\nDesk research lies. Walk the user through the Meta Ad Library (or equivalent) with\nan explicit checklist: number of ACTIVE advertisers, age of the oldest running ad\n(90+ days = someone is paying because it works), and the three traps — zero ads\n(`wrong-channel`), a few giants (`incumbent-owned`), or hundreds of ads\n(`crowded` commodity knife-fight: demand ≠ room for you).\n\n### Step 5: Verdict\n\n```\nVERDICT: DEAD | SURVIVED\nKILL-PATTERN: \u003Cname>            (if dead)\nTHE ONE SENTENCE: \u003Cthe single finding that decided it>\nEVIDENCE: \u003C2-4 hard facts with sources\u002Fnumbers>\nNEXT: \u003Cif survived: the ONE cheapest test that could still kill it>\n```\n\nThen record the result — gated on consent: if `REJECTION.md` exists, or the user\napproved creating it in Step 1, append a one-line row (dead) or note the survivor\nwith the date and pending test. If the user declined the kill-list, do NOT create\nor write the file — print the proposed row as text so they can save it wherever\nthey prefer. The kill-list is the compounding asset — every autopsy makes the\nnext one faster, but only with the user's consent.\n\n## Examples\n\n### Example 1: Idea that dies on the free-AI test\n\n```\nUser: Should I build a chargeback-response kit for Shopify sellers? Ready-to-send\n      evidence packets, $29 one-time.\nAgent: Running the autopsy... Step 3 kills it: one prompt to a frontier model\n      produces a complete, usable evidence packet for free.\n      VERDICT: DEAD. KILL-PATTERN: free-AI.\n      THE ONE SENTENCE: If AI ships your whole deliverable in one prompt, you\n      don't have a product — you have a prompt.\n```\n\n### Example 2: Proven demand that still dies\n\n```\nUser: An app that identifies plants from a photo — there are over a thousand\n      active ads for these, demand is proven!\nAgent: Step 4 confirms ~1,100 active advertisers — and that's the trap. The AI is\n      free, the datasets are public, everyone could build it, so everyone did.\n      VERDICT: DEAD. KILL-PATTERN: no-moat.\n      THE ONE SENTENCE: Demand tells you a market exists; it doesn't tell you\n      there's room for you.\n```\n\n## Best Practices\n\n- ✅ Demand a number, a law, a live ad, or a quote for every claim\n- ✅ Treat a fast honest kill as a WIN — it saves weeks and dollars\n- ✅ Make the user verify ad-library findings with their own eyes\n- ❌ Don't soften verdicts to be encouraging — \"it depends\" is a failed autopsy\n- ❌ Don't let buildability excitement skip the buyer questions; building was never the problem\n\n## Limitations\n\n- This skill does not replace legal advice, financial advice, or professional market research.\n- Kill-patterns are priors, not verdicts — a new niche matching an old pattern still deserves a fresh check that the pattern applies.\n- Ad-library checks reflect one acquisition channel; some categories legitimately sell through search or app stores.\n- Stop and ask for clarification if the idea's target market, buyer, or deliverable is unclear.\n\n## Security & Safety Notes\n\n- This skill performs no shell commands, network calls, or credential handling.\n- It modifies project state in exactly one place: creating or appending rows to the project's own `REJECTION.md` (hence `risk: critical`). It never edits other files; ask permission before creating the file on first run.\n- Web checks (ad libraries) are performed by the USER in their own browser; the skill only provides the checklist.\n","# Idea Autopsy\n\n## Overview\n\nTurns the agent into a ruthless business-idea pathologist: instead of encouraging\nthe user, it hunts for the one sentence that kills an idea — before any money or\nweeks are spent building it. Built from a real founder kill-list of 42 dead ideas\n(including a 9\u002F10-scored idea and one that turned out to be federally illegal to\ncharge for). Every autopsy ends in a hard verdict: DEAD with a named kill-pattern,\nor SURVIVED with the one cheapest test that could still kill it.\n\n## When to Use This Skill\n\n- Use when the user proposes a new business, product, or side-project idea\n- Use when the user asks \"should I build X?\" or \"validate this idea\"\n- Use when the user says \"autopsy my idea\"\n- Use before any market-research or build-planning task for a new venture\n\n## How It Works\n\n### Step 1: Kill-list check\n\nIf the project contains a `REJECTION.md` (the user's personal kill-list), read it\nfirst. A NICHE match (same niche as a killed row) = verdict DEAD, cite the row,\nstop. A KILL-PATTERN match alone (new niche, previously-seen pattern) is a strong\nprior, NOT a verdict: name the matching pattern, then run the specific check for\nthat pattern (the relevant filter or test below) to confirm it actually applies\nbefore declaring death. If no kill-list exists, ask the user for permission to create one\nwith exactly this schema — this autopsy writes its first row:\n\n```markdown\n# REJECTION.md — my kill-list\n\n## Killed ideas\n\n| # | Idea\u002FNiche | Killed (date) | Hard reason (one line) | Pattern |\n|---|-----------|---------------|------------------------|---------|\n\n## Survivors under test\n\n| Idea | Passed filters (date) | Pending test | Deadline |\n|------|----------------------|--------------|----------|\n```\n\n### Step 2: The five filters\n\nDemand evidence, not optimism. One hard NO = dead.\n\n1. **Real pain?** 2am-problem, or a nice-to-have \"vitamin\"?\n2. **Buyer has money?** Right now — not after the product helps them.\n3. **Proven demand?** Can the user name a single live competitor ad?\n4. **Legal to charge for?** Regulated, licensed, or illegal in the target market? Name the law if suspicion exists.\n5. **A moat?** What stops the 50th copycat next month?\n\n### Step 3: The free-AI test\n\nTry to produce the idea's core deliverable with one prompt to a frontier model.\nIf one prompt produces the whole deliverable free, the verdict is DEAD with\nkill-pattern `free-AI`: the user doesn't have a product, they have a prompt.\n\n### Step 4: Live-market verification (own eyes)\n\nDesk research lies. Walk the user through the Meta Ad Library (or equivalent) with\nan explicit checklist: number of ACTIVE advertisers, age of the oldest running ad\n(90+ days = someone is paying because it works), and the three traps — zero ads\n(`wrong-channel`), a few giants (`incumbent-owned`), or hundreds of ads\n(`crowded` commodity knife-fight: demand ≠ room for you).\n\n### Step 5: Verdict\n\n```\nVERDICT: DEAD | SURVIVED\nKILL-PATTERN: \u003Cname>            (if dead)\nTHE ONE SENTENCE: \u003Cthe single finding that decided it>\nEVIDENCE: \u003C2-4 hard facts with sources\u002Fnumbers>\nNEXT: \u003Cif survived: the ONE cheapest test that could still kill it>\n```\n\nThen record the result — gated on consent: if `REJECTION.md` exists, or the user\napproved creating it in Step 1, append a one-line row (dead) or note the survivor\nwith the date and pending test. If the user declined the kill-list, do NOT create\nor write the file — print the proposed row as text so they can save it wherever\nthey prefer. The kill-list is the compounding asset — every autopsy makes the\nnext one faster, but only with the user's consent.\n\n## Examples\n\n### Example 1: Idea that dies on the free-AI test\n\n```\nUser: Should I build a chargeback-response kit for Shopify sellers? Ready-to-send\n      evidence packets, $29 one-time.\nAgent: Running the autopsy... Step 3 kills it: one prompt to a frontier model\n      produces a complete, usable evidence packet for free.\n      VERDICT: DEAD. KILL-PATTERN: free-AI.\n      THE ONE SENTENCE: If AI ships your whole deliverable in one prompt, you\n      don't have a product — you have a prompt.\n```\n\n### Example 2: Proven demand that still dies\n\n```\nUser: An app that identifies plants from a photo — there are over a thousand\n      active ads for these, demand is proven!\nAgent: Step 4 confirms ~1,100 active advertisers — and that's the trap. The AI is\n      free, the datasets are public, everyone could build it, so everyone did.\n      VERDICT: DEAD. KILL-PATTERN: no-moat.\n      THE ONE SENTENCE: Demand tells you a market exists; it doesn't tell you\n      there's room for you.\n```\n\n## Best Practices\n\n- ✅ Demand a number, a law, a live ad, or a quote for every claim\n- ✅ Treat a fast honest kill as a WIN — it saves weeks and dollars\n- ✅ Make the user verify ad-library findings with their own eyes\n- ❌ Don't soften verdicts to be encouraging — \"it depends\" is a failed autopsy\n- ❌ Don't let buildability excitement skip the buyer questions; building was never the problem\n\n## Limitations\n\n- This skill does not replace legal advice, financial advice, or professional market research.\n- Kill-patterns are priors, not verdicts — a new niche matching an old pattern still deserves a fresh check that the pattern applies.\n- Ad-library checks reflect one acquisition channel; some categories legitimately sell through search or app stores.\n- Stop and ask for clarification if the idea's target market, buyer, or deliverable is unclear.\n\n## Security & Safety Notes\n\n- This skill performs no shell commands, network calls, or credential handling.\n- It modifies project state in exactly one place: creating or appending rows to the project's own `REJECTION.md` (hence `risk: critical`). It never edits other files; ask permission before creating the file on first run.\n- Web checks (ad libraries) are performed by the USER in their own browser; the skill only provides the checklist.\n",{"name":5,"risk":24,"tags":25,"tools":31,"author":35,"source":36,"license":15,"category":37,"date_added":38,"description":7,"source_repo":39,"source_type":36,"license_source":40},"critical",[26,27,28,29,30],"business-ideas","idea-validation","market-research","startup","founders",[32,33,34],"claude","cursor","gemini","hafiz-actyte","community","product","2026-07-10","hafiz-actyte\u002Fidea-autopsy","https:\u002F\u002Fgithub.com\u002Fhafiz-actyte\u002Fidea-autopsy\u002Fblob\u002Fmain\u002FLICENSE","main","b1e4ffadb4f933bbbcaa03a83f8b9929171ac28b",".agents\u002Fskills\u002Fidea-autopsy",0,"https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR","https:\u002F\u002Fgithub.com\u002FHazek-dc","2026-10-22 08:36:44",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add Hazek-dc\u002FPresensiGuru_FaceNet_EMAR --skill idea-autopsy",{"tool":54,"command":55},"bunx","bunx skills add Hazek-dc\u002FPresensiGuru_FaceNet_EMAR --skill idea-autopsy",{"tool":57,"command":58},"pnpm","pnpm dlx skills add Hazek-dc\u002FPresensiGuru_FaceNet_EMAR --skill idea-autopsy","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fidea-autopsy\u002FSKILL.md",true,[],[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7DS6GGYRZAYD33PFPS8Z2T3","testing-best-practices","Laravel test design and review. Use when selecting coverage, naming or structuring tests, choosing assertions or test data, isolating dependencies, testing HTTP or security boundaries, improving suite performance, or reviewing test value. Use framework guidance or search-docs for Pest and PHPUnit syntax.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Ftesting-best-practices\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7DS6BC3AW7HTPRHE2TTVKWM","tailwindcss-development","Always invoke when the user's message includes 'tailwind' in any form. Also invoke for: building responsive grid layouts (multi-column card grids, product grids), flex\u002Fgrid page structures (dashboards with sidebars, fixed topbars, mobile-toggle navs), styling UI components (cards, tables, navbars, pricing sections, forms, inputs, badges), adding dark mode variants, fixing spacing or typography, and Tailwind v3\u002Fv4 work. The core use case: writing or fixing Tailwind utility classes in HTML templates (Blade, JSX, Vue). Skip for backend PHP logic, database queries, API routes, JavaScript with no HTML\u002FCSS component, CSS file audits, build tool configuration, and vanilla CSS.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Ftailwindcss-development\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7DS66GE6B11MYJDVC74HXM4","laravel-best-practices","Apply this skill whenever writing, reviewing, or refactoring Laravel PHP code. This includes creating or modifying controllers, models, migrations, form requests, policies, jobs, scheduled commands, service classes, and Eloquent queries. Triggers for N+1 and query performance issues, caching strategies, authorization and security patterns, validation, error handling, queue and job configuration, route definitions, and architectural decisions. Also use for Laravel code reviews and refactoring existing Laravel code to follow best practices. Covers any task involving Laravel backend PHP code patterns.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Flaravel-best-practices\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7DS5ZW717DMS6P1E90AQCKV","infer-conventions","Use this skill to analyze how a Laravel application is actually written and record its conventions as shared rules. Trigger when the user wants to detect, infer, document, or standardize project conventions or coding style, set up or grow `.ai\u002Frules`, resolve mixed or conflicting patterns (e.g. \"are we using Form Requests or inline validation?\"), or onboard agents and teammates to \"how we do things here\". Covers: a systematic sweep of ~49 Laravel convention dimensions (validation, models, architecture, testing, frontend, database, console), open-ended house-pattern discovery, conflict reporting, and recording rules scoped to the right paths via the Boost `record-rule` MCP tool. Only run this skill when the user explicitly asks for it; never start a sweep as part of another task. Do not use for one-off code review, enforcing formatting a linter already handles, or editing `.ai\u002Frules` files by hand.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Finfer-conventions\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7DS5W12RGCVJTFQJ1N0GB8E","inertia-react-development","Develops Inertia.js v2 React client-side applications. Activates when creating React pages, forms, or navigation; using \u003CLink>, \u003CForm>, useForm, or router; working with deferred props, prefetching, or polling; or when user mentions React with Inertia, React pages, React forms, or React navigation.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Finertia-react-development\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7DS5PVDPMPCWSK2RXPDC9BB","deploying-to-cloud","Deploys and manages Laravel applications on Laravel Cloud using the `cloud` CLI. Use when the user wants to deploy an app, ship to Cloud, create or manage applications, environments, databases, caches, object storage, queues, domains, instances, background processes, secrets, compute, scheduled tasks, or Laravel Cloud infrastructure; or check billing, usage, or spend. Triggers on deployment, shipping, Cloud management, environment setup, database provisioning, billing or usage queries, the `cloud` CLI, and Laravel Cloud deployment troubleshooting.","https:\u002F\u002Fgithub.com\u002FHazek-dc\u002FPresensiGuru_FaceNet_EMAR\u002Fblob\u002Fmain\u002Fattendance-web\u002F.claude\u002Fskills\u002Fdeploying-to-cloud\u002FSKILL.md",[],[]]