[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F5FDNAMJWVF9AH74VDB63S":3,"skill-same:01M7F5FDNAMJWVF9AH74VDB63S":45},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7F5FDNAMJWVF9AH74VDB63S","web-research",null,"General web research method for current external questions. Focuses on framing, evidence quality, source selection, contradiction handling, and confidence grading rather than any one domain. Use when a question needs current external evidence or source verification.","cwik-tech\u002Foctopus","cwik-tech","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54542292?v=4","01M7F42E123GEHVK6RWC5MSWJ9","Tomasz Cwik","01M7F42E1PD4P54MTG8PG32VCV",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fcwik-tech\u002Foctopus\u002Fblob\u002Fmain\u002Fagents\u002Fweb-researcher\u002Fskills\u002Fweb-research\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: web-research\ndescription: General web research method for current external questions. Focuses on framing, evidence quality, source selection, contradiction handling, and confidence grading rather than any one domain. Use when a question needs current external evidence or source verification.\n---\n\n# Web Research Skill\n\nThis skill is for answering external questions with enough evidence to support the next decision. It is not tied to company research only. Use it for any current-question task that depends on material outside the brief.\n\n## Core Principle\n\nDo not start with websites. Start with the question.\n\nA good research result answers four things clearly:\n\n1. What exactly are we trying to know?\n2. What evidence would actually answer that?\n3. How reliable is the evidence?\n4. What still remains uncertain?\n\n## Step 1: Frame The Question\n\nConvert the request into a precise research question before searching.\n\nGood framing usually includes:\n\n- target subject\n- claim or uncertainty to resolve\n- time horizon\n- required confidence level\n- decision the answer will support\n\nExamples:\n\n- weak: \"research this market\"\n- better: \"what has changed in this market in the last 12 months that would affect entry timing?\"\n\n- weak: \"check this company\"\n- better: \"does this company currently sell to enterprise buyers, and what direct evidence supports that?\"\n\n## Step 2: Decompose Into Sub-Questions\n\nIf the question is broad, split it into smaller checks.\n\nUseful decomposition patterns:\n\n- fact check: is claim X true?\n- state check: what is true now?\n- comparison: how does A differ from B?\n- trend check: what changed over time?\n- causality check: what explains the observed change?\n- risk check: what could make this conclusion wrong?\n\nDo not search a broad question all at once if it actually contains several distinct claims.\n\n## Step 3: Choose Source Types By Claim Type\n\nPick sources based on what kind of claim you are testing.\n\n| Claim Type | Stronger Sources | Weaker Sources |\n|------------|------------------|----------------|\n| Current facts | official site, official docs, regulator, raw data | blogs, summaries, reposts |\n| Historical events | dated primary reporting, filings, archived pages | memory-based commentary |\n| Pricing \u002F packaging | live pricing page, terms, checkout flow | listicles, old screenshots |\n| Product capability | official docs, demos, code, release notes | marketing copy alone |\n| Legal \u002F regulatory | statute, regulator guidance, enforcement records | commentary without citations |\n| Market behavior | raw datasets, earnings calls, primary reporting | opinion pieces |\n| Reputation \u002F sentiment | broad cross-source pattern, direct quotes, reviews with context | isolated anecdotes |\n| YouTube \u002F video claims | externally supplied transcript plus independent verification; otherwise escalate acquisition to the YouTube extraction workflow | paraphrases of the video alone |\n\nRule: match the source to the claim. A source can be strong for one kind of claim and weak for another.\n\n## Step 4: Gather Evidence Narrowly\n\nSearch only for evidence that resolves the framed question.\n\nGuidelines:\n\n1. Prefer primary sources first.\n2. Use secondary sources to discover leads, not to end the search.\n3. Capture dates whenever recency matters.\n4. Follow citations upstream to the original source.\n5. Search for disconfirming evidence, not just confirming evidence.\n6. Treat absence of evidence as a finding when the claim should be easy to verify.\n\n## Step 5: Evaluate Evidence Quality\n\nJudge each source on the dimensions that matter for the current question:\n\n- relevance: does it answer this exact question?\n- recency: is it current enough?\n- proximity: is it close to the underlying event or data?\n- independence: is it repeating someone else?\n- incentives: who benefits if this is believed?\n- specificity: does it provide details, or only vague claims?\n\n### Typical Failure Modes\n\nWatch for:\n\n- stale pages presented as current\n- vendor self-description treated as independent proof\n- multiple articles repeating one uncited claim\n- selective screenshots without surrounding context\n- strong conclusion drawn from one weak source\n- source mismatch, such as using commentary to prove legal status\n\n## Step 6: Separate Fact, Inference, And Open Question\n\nEvery material point should fall into one of these buckets:\n\n- **Fact**: directly supported by inspected evidence\n- **Inference**: reasonable interpretation of several facts\n- **Open question**: still unresolved or weakly evidenced\n\nDo not let inference masquerade as fact.\n\n## Step 7: Handle Contradictions Explicitly\n\nWhen sources conflict, do not average them into a blurry summary.\n\nInstead:\n\n1. state the conflict directly\n2. check dates and definitions\n3. check whether one source is secondary and the other primary\n4. note whether the disagreement is resolvable or still open\n\nContradiction is often the most important output of the research.\n\n## Step 8: Grade Confidence\n\nUse confidence tags on the conclusion and on major findings.\n\n- **High** — recent, direct, relevant, and independently corroborated\n- **Medium** — credible but partial, indirect, or not fully corroborated\n- **Low** — weak, stale, promotional, conflicting, or single-source\n\nConfidence is about evidence quality, not writing tone.\n\n## Decision Rule: Stop Or Go Deeper\n\nStop when:\n\n- the question is answered clearly enough for the next decision\n- remaining uncertainty is non-critical\n- additional searching is unlikely to change the answer materially\n\nGo deeper when:\n\n- core claims still conflict\n- the source base is weak or highly biased\n- the question actually requires a full domain model\n- the decision risk is high and the current evidence is thin\n\n## Output Standard\n\nThis skill decides what you know and how well you know it. The persona decides\nwhat you return. Do not choose a report shape here.\n\nWhatever the shape, every material finding carries its date, its confidence, and\na clickable Markdown link to the exact observed page URL. Contradictions and\nunresolved questions stay visible; they are findings, not untidiness.\n\n## Lightweight Domain Examples\n\nExamples of questions this method should handle well:\n\n- company facts\n- competitor positioning\n- pricing checks\n- product capability verification\n- market or category shifts\n- policy or regulatory checks\n- public narrative and sentiment scans\n- event timelines\n- source verification for claims found in videos, articles, or decks\n\nThese are examples only. The method comes first.\n","# Web Research Skill\n\nThis skill is for answering external questions with enough evidence to support the next decision. It is not tied to company research only. Use it for any current-question task that depends on material outside the brief.\n\n## Core Principle\n\nDo not start with websites. Start with the question.\n\nA good research result answers four things clearly:\n\n1. What exactly are we trying to know?\n2. What evidence would actually answer that?\n3. How reliable is the evidence?\n4. What still remains uncertain?\n\n## Step 1: Frame The Question\n\nConvert the request into a precise research question before searching.\n\nGood framing usually includes:\n\n- target subject\n- claim or uncertainty to resolve\n- time horizon\n- required confidence level\n- decision the answer will support\n\nExamples:\n\n- weak: \"research this market\"\n- better: \"what has changed in this market in the last 12 months that would affect entry timing?\"\n\n- weak: \"check this company\"\n- better: \"does this company currently sell to enterprise buyers, and what direct evidence supports that?\"\n\n## Step 2: Decompose Into Sub-Questions\n\nIf the question is broad, split it into smaller checks.\n\nUseful decomposition patterns:\n\n- fact check: is claim X true?\n- state check: what is true now?\n- comparison: how does A differ from B?\n- trend check: what changed over time?\n- causality check: what explains the observed change?\n- risk check: what could make this conclusion wrong?\n\nDo not search a broad question all at once if it actually contains several distinct claims.\n\n## Step 3: Choose Source Types By Claim Type\n\nPick sources based on what kind of claim you are testing.\n\n| Claim Type | Stronger Sources | Weaker Sources |\n|------------|------------------|----------------|\n| Current facts | official site, official docs, regulator, raw data | blogs, summaries, reposts |\n| Historical events | dated primary reporting, filings, archived pages | memory-based commentary |\n| Pricing \u002F packaging | live pricing page, terms, checkout flow | listicles, old screenshots |\n| Product capability | official docs, demos, code, release notes | marketing copy alone |\n| Legal \u002F regulatory | statute, regulator guidance, enforcement records | commentary without citations |\n| Market behavior | raw datasets, earnings calls, primary reporting | opinion pieces |\n| Reputation \u002F sentiment | broad cross-source pattern, direct quotes, reviews with context | isolated anecdotes |\n| YouTube \u002F video claims | externally supplied transcript plus independent verification; otherwise escalate acquisition to the YouTube extraction workflow | paraphrases of the video alone |\n\nRule: match the source to the claim. A source can be strong for one kind of claim and weak for another.\n\n## Step 4: Gather Evidence Narrowly\n\nSearch only for evidence that resolves the framed question.\n\nGuidelines:\n\n1. Prefer primary sources first.\n2. Use secondary sources to discover leads, not to end the search.\n3. Capture dates whenever recency matters.\n4. Follow citations upstream to the original source.\n5. Search for disconfirming evidence, not just confirming evidence.\n6. Treat absence of evidence as a finding when the claim should be easy to verify.\n\n## Step 5: Evaluate Evidence Quality\n\nJudge each source on the dimensions that matter for the current question:\n\n- relevance: does it answer this exact question?\n- recency: is it current enough?\n- proximity: is it close to the underlying event or data?\n- independence: is it repeating someone else?\n- incentives: who benefits if this is believed?\n- specificity: does it provide details, or only vague claims?\n\n### Typical Failure Modes\n\nWatch for:\n\n- stale pages presented as current\n- vendor self-description treated as independent proof\n- multiple articles repeating one uncited claim\n- selective screenshots without surrounding context\n- strong conclusion drawn from one weak source\n- source mismatch, such as using commentary to prove legal status\n\n## Step 6: Separate Fact, Inference, And Open Question\n\nEvery material point should fall into one of these buckets:\n\n- **Fact**: directly supported by inspected evidence\n- **Inference**: reasonable interpretation of several facts\n- **Open question**: still unresolved or weakly evidenced\n\nDo not let inference masquerade as fact.\n\n## Step 7: Handle Contradictions Explicitly\n\nWhen sources conflict, do not average them into a blurry summary.\n\nInstead:\n\n1. state the conflict directly\n2. check dates and definitions\n3. check whether one source is secondary and the other primary\n4. note whether the disagreement is resolvable or still open\n\nContradiction is often the most important output of the research.\n\n## Step 8: Grade Confidence\n\nUse confidence tags on the conclusion and on major findings.\n\n- **High** — recent, direct, relevant, and independently corroborated\n- **Medium** — credible but partial, indirect, or not fully corroborated\n- **Low** — weak, stale, promotional, conflicting, or single-source\n\nConfidence is about evidence quality, not writing tone.\n\n## Decision Rule: Stop Or Go Deeper\n\nStop when:\n\n- the question is answered clearly enough for the next decision\n- remaining uncertainty is non-critical\n- additional searching is unlikely to change the answer materially\n\nGo deeper when:\n\n- core claims still conflict\n- the source base is weak or highly biased\n- the question actually requires a full domain model\n- the decision risk is high and the current evidence is thin\n\n## Output Standard\n\nThis skill decides what you know and how well you know it. The persona decides\nwhat you return. Do not choose a report shape here.\n\nWhatever the shape, every material finding carries its date, its confidence, and\na clickable Markdown link to the exact observed page URL. Contradictions and\nunresolved questions stay visible; they are findings, not untidiness.\n\n## Lightweight Domain Examples\n\nExamples of questions this method should handle well:\n\n- company facts\n- competitor positioning\n- pricing checks\n- product capability verification\n- market or category shifts\n- policy or regulatory checks\n- public narrative and sentiment scans\n- event timelines\n- source verification for claims found in videos, articles, or decks\n\nThese are examples only. The method comes first.\n",{"name":5,"description":7},"main","f0f0efe1d4c64b51a51f44427ad147750d29154e","agents\u002Fweb-researcher\u002Fskills\u002Fweb-research","https:\u002F\u002Fgithub.com\u002Fcwik-tech\u002Foctopus","www.cuteoctopus.site","https:\u002F\u002Fgithub.com\u002Fcwik-tech","2026-10-27 06:12:19",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add cwik-tech\u002Foctopus --skill web-research",{"tool":37,"command":38},"bunx","bunx skills add cwik-tech\u002Foctopus --skill web-research",{"tool":40,"command":41},"pnpm","pnpm dlx skills add cwik-tech\u002Foctopus --skill web-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcwik-tech\u002Foctopus\u002Fblob\u002Fmain\u002Fagents\u002Fweb-researcher\u002Fskills\u002Fweb-research\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7F5MQVQ3CHGM77Q51M4B1AC","twenty-year-land-plan","Apply the Bren discipline of evaluating every land and development decision on a twenty-year horizon, with a comprehensive plan for how the land, the community, and the surrounding public infrastructure evolve together. Deals optimized for a five-year exit are structurally different from deals that compound across generations; insist on knowing which kind you are making. Use when evaluating land, entitlements, master-planned development, or phasing decisions, and when separating five-year exit deals from generational holds.","https:\u002F\u002Fgithub.com\u002Fcwik-tech\u002Foctopus\u002Fblob\u002Fmain\u002Fskills\u002Ftwenty-year-land-plan\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7F5MGQ8JSV27SFDQVVGFQE3","thematic-gut-check","Apply the Gray discipline of identifying the structural theme behind every real estate deal, testing where that theme sits in its capital-flow lifecycle, and insisting that deals without a named theme — or deals late in a crowded theme — clear a higher bar. A mediocre deal in a strong theme usually beats a clever deal in a weak one. Use when naming the structural thesis behind a deal, judging whether that theme is early or crowded, and setting the bar the deal must clear.","https:\u002F\u002Fgithub.com\u002Fcwik-tech\u002Foctopus\u002Fblob\u002Fmain\u002Fskills\u002Fthematic-gut-check\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7F5M8V64Y0ZD8PTPWEJQXJ9","supply-pipeline-gut-check","Apply the Zell discipline of grounding every real estate thesis in the local supply pipeline. Demand counts over adjectives — units under construction, units permitted, units proposed — and convert them into a forward absorption schedule. A deal that ignores the pipeline is a bet on a market you have not actually studied. Use when validating a market thesis, forecasting absorption and rent growth, or counting units under construction, permitted, and proposed.","https:\u002F\u002Fgithub.com\u002Fcwik-tech\u002Foctopus\u002Fblob\u002Fmain\u002Fskills\u002Fsupply-pipeline-gut-check\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7F5M3J2Q146BJC13TD3YCXF","ruin-scenario-mapping","Apply the Taleb discipline of identifying, for every real estate deal, the specific chain of events that produces ruin — permanent, unrecoverable capital loss — and verifying that no single such chain has non-trivial probability. Deals with any plausible ruin path must be restructured or abandoned. Use when sizing leverage, testing refinancing, covenant, and liquidity risk, or checking whether any single failure chain can permanently wipe out the position.","https:\u002F\u002Fgithub.com\u002Fcwik-tech\u002Foctopus\u002Fblob\u002Fmain\u002Fskills\u002Fruin-scenario-mapping\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7F5KZDS0DYD172P6HS0WXEM","revenue-cost-architecture","Design a venture's revenue streams, pricing logic, cost structure, and unit economics so the business model has a coherent theory of value capture, not just value creation. Use after the value proposition and customer segment are set and before financial projections, when choosing a pricing model, calculating contribution margin or CAC payback, or checking whether the unit economics hold at scale.","https:\u002F\u002Fgithub.com\u002Fcwik-tech\u002Foctopus\u002Fblob\u002Fmain\u002Fskills\u002Frevenue-cost-architecture\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7F5KP1CNQMYAVCDTV4EEW3J","replacement-cost-stress-test","Apply the Buffett discipline of pricing every real estate asset against the cost to rebuild it from scratch. The ratio of purchase price to replacement cost sets a ceiling on long-run downside: below replacement cost, new supply cannot profitably undercut you; at or above it, you are buying a liability disguised as an asset. Use when setting a purchase price, judging downside protection, or testing how exposed an asset is to newly built competing supply.","https:\u002F\u002Fgithub.com\u002Fcwik-tech\u002Foctopus\u002Fblob\u002Fmain\u002Fskills\u002Freplacement-cost-stress-test\u002FSKILL.md",[],[]]