[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AMM97AWPQX9APF3DZ0G8KC":3,"skill-same:01M7AMM97AWPQX9APF3DZ0G8KC":48},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7AMM97AWPQX9APF3DZ0G8KC","research-search-and-source-quality",null,"Use when researching whether a factual claim is still current — constructing web searches, judging source quality, dating a claim, distinguishing primary from secondary sources, and recording provenance. Triggers on web search research, fact-checking a claim, \"find a source for\", verifying a statistic, source tiers, primary sources, and any task where an answer must be grounded in something citable rather than recalled. Covers the fabrication failure mode and what to do when the search comes back empty.","the-vibey-project\u002Fvibey","the-vibey-project","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F329298758?v=4","01M7AJHGZ9722CTJ4JNQZVRH0Q","the vibey project","01M7AJHGZVMG2K7TGXQ6XFHVG3",5,"MIT","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fcurrency-research\u002Fskills\u002Fresearch-search-and-source-quality\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: research-search-and-source-quality\ndescription: Use when researching whether a factual claim is still current — constructing web searches, judging source quality, dating a claim, distinguishing primary from secondary sources, and recording provenance. Triggers on web search research, fact-checking a claim, \"find a source for\", verifying a statistic, source tiers, primary sources, and any task where an answer must be grounded in something citable rather than recalled. Covers the fabrication failure mode and what to do when the search comes back empty.\n---\n\n# Search and Source Quality\n\nHow to find out what is actually true right now, and how to know whether what you found is\nworth writing down.\n\n---\n\n## The one rule that matters most\n\n⚠️ **Never present recalled knowledge as a search result.** The single worst outcome of a\nresearch task is a confident, specific, well-formatted claim that was reconstructed from\ntraining data and labelled \"verified\". It is worse than no answer, because it is\nindistinguishable from a real one until someone tries to use it.\n\nConcretely:\n\n- If a search returns nothing useful, **say the search returned nothing useful.**\n- If you can only find secondary coverage, **say it is secondary.**\n- If a figure is approximate or disputed, **carry the approximation or the dispute into the text.**\n- If your recollection disagrees with the sources you found, **the sources win** — or the\n  question goes in the pull request as unresolved.\n\nThe tell for this failure mode is plausible scaffolding around invented specifics: real\norganisation names, a real-sounding report title, a precise number, and no retrievable\nsource. If your draft has that shape, delete the specifics.\n\n---\n\n## Constructing the search\n\n**Start from the claim, not the topic.** \"Is X still 12%?\" searches better than \"X overview\".\nThe claim gives you the entity, the quantity and the implicit date.\n\nUseful moves, roughly in order:\n\n- **Name the authority.** Standards bodies, regulators and vendors publish the thing itself;\n  search for the specification, the register, the changelog, the docs — not commentary on them.\n- **Date-bound the query.** Add the current or previous year when a claim is time-sensitive.\n  Be aware that this biases toward recently *published* pages, which is not the same as\n  recently *true*.\n- **Search for the change, not the state.** \"deprecated\", \"sunset\", \"withdrawn\", \"superseded\",\n  \"end of life\", \"replaced by\", \"revision\" find transitions that a state-of-the-world query misses.\n- **Search for the contradiction.** If the reference says X, search for \"not X\" as well. A\n  source that disagrees is more informative than the tenth that agrees.\n- **Go to the primary document** whenever a secondary source cites one. Press coverage of a\n  standard routinely garbles version numbers, dates and scope.\n\n⚠️ **One search is not research.** A single query that appears to confirm the existing text is\nthe weakest possible evidence, because you have only sampled the part of the web that agrees.\nTwo or three angles, including one adversarial, before concluding \"unchanged\".\n\n---\n\n## Source tiers\n\nJudge a source by what it is, not by how confident it sounds.\n\n| Tier | Examples | Use for |\n|---|---|---|\n| **Primary \u002F authoritative** | The standard, the statute, the regulator's register, the vendor's own docs and pricing, the filed report, the dataset | Anything you state as fact. Prefer always. |\n| **Peer-reviewed \u002F systematic** | Journal articles, systematic reviews, meta-analyses, official statistics | Scientific and quantitative claims. Check retraction status for older work. |\n| **Reputable secondary** | Established trade and technical press, industry analysts, standards-body summaries | Orientation, and finding the primary source. Cite the primary. |\n| **Weak** | Vendor marketing, press releases about intentions, blog posts without sources, forum consensus, LLM output, undated pages | Leads only. **Never the sole basis for an edit.** |\n\nSpecific traps:\n\n- **A press release announcing a plan is not evidence the plan happened.** Check for the follow-through.\n- **Analyst market-share figures vary wildly by methodology.** If you cite one, name the source and\n  the method, and prefer reporting a range across sources over a single false-precise number.\n- **Wikipedia is a finding aid, not a citation.** Follow its references.\n- **A vendor's own docs are authoritative about that vendor's product** and about nothing else,\n  least of all competitors.\n- **Beware circular sourcing** — three outlets repeating one unsourced claim is still one\n  unsourced claim.\n\n---\n\n## Dating a claim\n\nCurrency work lives and dies on dates, and pages are bad at them.\n\n- Distinguish **publication date**, **last-revised date** and **the date the content is about**.\n  A page revised this month may describe last year's state.\n- Undated pages are close to useless for currency work. Look for a version number, a changelog\n  entry, or an archived copy that pins the date.\n- **A superseded document is still evidence** — of what was true then. Use it to establish the\n  before-state when you are describing a change.\n- When you cannot establish a date, **say the date is unestablished** rather than assuming\n  the page is current.\n\n---\n\n## Recording provenance\n\nEvery proposed edit must carry enough provenance for a reviewer to check it without repeating\nyour research. Record, in the pull request:\n\n- **who** published it (the organisation, not just the site);\n- **what** it is (specification, report, register entry, article);\n- **when** it is dated;\n- **what it actually said** — the specific figure or statement, in your own words;\n- **how well it supports the edit** — direct statement, inference, or single-source.\n\nMatch the confidence of the wording to the strength of the source. The references in this\nmarketplace already hedge carefully — \"reported\", \"estimates place\", \"sources disagree\",\n\"n=753\" — and an edit that drops the hedging to sound cleaner has made the document worse\neven if the number is right.\n\n---\n\n## When the evidence is thin\n\nThin evidence is a normal outcome, not a failure. Options, in order of preference:\n\n1. **Leave the text alone** and note in the pull request what you looked for and did not find.\n2. **Weaken the claim to match the evidence** — turn a flat assertion into a hedged one, or\n   add the disagreement between sources. This is often the most honest edit available.\n3. **Mark the uncertainty in the text** where the reference already uses that device\n   (a confidence marker, a \"sources disagree\" note).\n4. **Raise it as a question** in the pull request for a human to resolve.\n\n⚠️ **Never resolve thin evidence by picking the most quotable number.** If two credible\nsources disagree, the disagreement *is* the finding, and the reference should say so.\n","# Search and Source Quality\n\nHow to find out what is actually true right now, and how to know whether what you found is\nworth writing down.\n\n---\n\n## The one rule that matters most\n\n⚠️ **Never present recalled knowledge as a search result.** The single worst outcome of a\nresearch task is a confident, specific, well-formatted claim that was reconstructed from\ntraining data and labelled \"verified\". It is worse than no answer, because it is\nindistinguishable from a real one until someone tries to use it.\n\nConcretely:\n\n- If a search returns nothing useful, **say the search returned nothing useful.**\n- If you can only find secondary coverage, **say it is secondary.**\n- If a figure is approximate or disputed, **carry the approximation or the dispute into the text.**\n- If your recollection disagrees with the sources you found, **the sources win** — or the\n  question goes in the pull request as unresolved.\n\nThe tell for this failure mode is plausible scaffolding around invented specifics: real\norganisation names, a real-sounding report title, a precise number, and no retrievable\nsource. If your draft has that shape, delete the specifics.\n\n---\n\n## Constructing the search\n\n**Start from the claim, not the topic.** \"Is X still 12%?\" searches better than \"X overview\".\nThe claim gives you the entity, the quantity and the implicit date.\n\nUseful moves, roughly in order:\n\n- **Name the authority.** Standards bodies, regulators and vendors publish the thing itself;\n  search for the specification, the register, the changelog, the docs — not commentary on them.\n- **Date-bound the query.** Add the current or previous year when a claim is time-sensitive.\n  Be aware that this biases toward recently *published* pages, which is not the same as\n  recently *true*.\n- **Search for the change, not the state.** \"deprecated\", \"sunset\", \"withdrawn\", \"superseded\",\n  \"end of life\", \"replaced by\", \"revision\" find transitions that a state-of-the-world query misses.\n- **Search for the contradiction.** If the reference says X, search for \"not X\" as well. A\n  source that disagrees is more informative than the tenth that agrees.\n- **Go to the primary document** whenever a secondary source cites one. Press coverage of a\n  standard routinely garbles version numbers, dates and scope.\n\n⚠️ **One search is not research.** A single query that appears to confirm the existing text is\nthe weakest possible evidence, because you have only sampled the part of the web that agrees.\nTwo or three angles, including one adversarial, before concluding \"unchanged\".\n\n---\n\n## Source tiers\n\nJudge a source by what it is, not by how confident it sounds.\n\n| Tier | Examples | Use for |\n|---|---|---|\n| **Primary \u002F authoritative** | The standard, the statute, the regulator's register, the vendor's own docs and pricing, the filed report, the dataset | Anything you state as fact. Prefer always. |\n| **Peer-reviewed \u002F systematic** | Journal articles, systematic reviews, meta-analyses, official statistics | Scientific and quantitative claims. Check retraction status for older work. |\n| **Reputable secondary** | Established trade and technical press, industry analysts, standards-body summaries | Orientation, and finding the primary source. Cite the primary. |\n| **Weak** | Vendor marketing, press releases about intentions, blog posts without sources, forum consensus, LLM output, undated pages | Leads only. **Never the sole basis for an edit.** |\n\nSpecific traps:\n\n- **A press release announcing a plan is not evidence the plan happened.** Check for the follow-through.\n- **Analyst market-share figures vary wildly by methodology.** If you cite one, name the source and\n  the method, and prefer reporting a range across sources over a single false-precise number.\n- **Wikipedia is a finding aid, not a citation.** Follow its references.\n- **A vendor's own docs are authoritative about that vendor's product** and about nothing else,\n  least of all competitors.\n- **Beware circular sourcing** — three outlets repeating one unsourced claim is still one\n  unsourced claim.\n\n---\n\n## Dating a claim\n\nCurrency work lives and dies on dates, and pages are bad at them.\n\n- Distinguish **publication date**, **last-revised date** and **the date the content is about**.\n  A page revised this month may describe last year's state.\n- Undated pages are close to useless for currency work. Look for a version number, a changelog\n  entry, or an archived copy that pins the date.\n- **A superseded document is still evidence** — of what was true then. Use it to establish the\n  before-state when you are describing a change.\n- When you cannot establish a date, **say the date is unestablished** rather than assuming\n  the page is current.\n\n---\n\n## Recording provenance\n\nEvery proposed edit must carry enough provenance for a reviewer to check it without repeating\nyour research. Record, in the pull request:\n\n- **who** published it (the organisation, not just the site);\n- **what** it is (specification, report, register entry, article);\n- **when** it is dated;\n- **what it actually said** — the specific figure or statement, in your own words;\n- **how well it supports the edit** — direct statement, inference, or single-source.\n\nMatch the confidence of the wording to the strength of the source. The references in this\nmarketplace already hedge carefully — \"reported\", \"estimates place\", \"sources disagree\",\n\"n=753\" — and an edit that drops the hedging to sound cleaner has made the document worse\neven if the number is right.\n\n---\n\n## When the evidence is thin\n\nThin evidence is a normal outcome, not a failure. Options, in order of preference:\n\n1. **Leave the text alone** and note in the pull request what you looked for and did not find.\n2. **Weaken the claim to match the evidence** — turn a flat assertion into a hedged one, or\n   add the disagreement between sources. This is often the most honest edit available.\n3. **Mark the uncertainty in the text** where the reference already uses that device\n   (a confidence marker, a \"sources disagree\" note).\n4. **Raise it as a question** in the pull request for a human to resolve.\n\n⚠️ **Never resolve thin evidence by picking the most quotable number.** If two credible\nsources disagree, the disagreement *is* the finding, and the reference should say so.\n",{"name":5,"description":7},"develop","ae32736a1aabddabca5d2c96d665aa0ebc7d8700","src\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fcurrency-research\u002Fskills\u002Fresearch-search-and-source-quality",3,"https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey","https:\u002F\u002Fthe-vibey-project.github.io\u002Fvibey\u002F","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project","https:\u002F\u002Fvibewithadam.matthewsteinberger.com","freedom for software engineers","2026-11-15 05:47:42",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add the-vibey-project\u002Fvibey --skill research-search-and-source-quality",{"tool":40,"command":41},"bunx","bunx skills add the-vibey-project\u002Fvibey --skill research-search-and-source-quality",{"tool":43,"command":44},"pnpm","pnpm dlx skills add the-vibey-project\u002Fvibey --skill research-search-and-source-quality","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fcurrency-research\u002Fskills\u002Fresearch-search-and-source-quality\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7AT1FQJAE1FQYAMDTF490Y4","white-paper-writing","Use when writing white papers, technical reports, policy documents, thought leadership pieces, or any long-form authoritative document. Triggers on requests to write, structure, outline, or review white papers, technical reports, position papers, policy briefs, or evidence-driven arguments. Also use for B2B content marketing strategy, technical documentation requiring authority, academic-style reports, or any document that must educate while persuading. Use when someone asks \"how should I structure this\" for a long-form document.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fwhite-paper-writing\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7AT16BJRJJKK2MASXRZS76G","prose-technical-mechanics","Use when editing or writing prose at a technical\u002Fmechanical level: choosing between Anglo-Saxon and Latinate diction, placing information in topic vs stress positions, writing periodic vs cumulative sentences, handling sentence rhythm, punctuation as logic, transitions, paragraph structure, or phonesthetics. Use when someone wants to understand WHY prose works or doesn't, not just surface-level style advice. Triggers on word choice, sentence structure, emphasis, rhythm, diction, or any deep writing mechanics question.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fprose-technical-mechanics\u002FSKILL.md",[],[],{"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},"01M7AT0W9HT0ZZ9Y287NW99MR3","prose-mechanics","Use when writing, editing, or analyzing prose style; when trying to avoid generic AI-sounding writing; when applying specific prose styles such as journalistic, academic, narrative, KJV biblical, Hemingway plain, Latinate\u002FJamesian, Orwellian, Augustan, Victorian, Early Modern (Bacon, Browne, Milton), or free indirect discourse; or when coaching someone on writing voice and mechanics. Triggers on any request to improve, analyze, or write in a specific prose style, to fix \"AI-sounding\" writing, to make prose more vivid or concrete, to vary sentence rhythm, or to understand how a particular writer achieves their effects.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fprose-mechanics\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},"01M7AT0KR635JX66X2X6F3E2CP","narrative-structure","Use when structuring stories, pitches, presentations, white papers, or any persuasive narrative; analyzing the hero's journey in fiction or non-fiction; applying StoryBrand for business communication; designing narrative arcs for thought leadership; or understanding Vogler, Snyder, Propp, or Campbell frameworks. Triggers on any narrative structure, storytelling, pitch structure, StoryBrand, hero's journey, three-act structure, Freytag, Save the Cat, narrative arc, or \"how should I structure this story\u002Fpitch\u002Fpresentation\" request.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fnarrative-structure\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},"01M7AT0AKGW09NKKZDYBT8VRDE","legal-brief-writing","Use when writing legal briefs, motions, or any court filing; when analyzing judicial cognition and persuasion; when applying elite brief-writing techniques from Roberts, Clement, Kagan, Garner; or when structuring legal arguments for maximum persuasion. Also use for autistic\u002Fneurodivergent advocates who need to understand how their natural communication style maps to elite legal advocacy. Triggers on any legal writing, brief drafting, motion preparation, or legal argument structuring request.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Flegal-brief-writing\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},"01M7AT00VWPS4Q8B5VEMXX9NQT","journal-publishability-criteria","Use whenever a research paper, article or preprint is being written, revised, reviewed or published, and specifically before every publication of docs\u002Fpaper.md. Covers what legitimate journals actually gate on, in order of gating — the editor's desk screen (scope, novelty, package problems), what reviewers judge (methodological soundness, claims the evidence can carry, statistical and qualitative reporting), EQUATOR reporting guidelines, the ICMJE authorship criteria, COPE's view of text recycling, the near-universal generative-AI policy (no AI author, disclosure, author responsibility), TOP 2025 transparency standards, how to verify a journal is legitimate, submitting without an institution, and a pre-submission checklist. Triggers on requests to evaluate, review, prepare or submit a paper, to judge publishability, to write a declarations or data-availability section, to disclose AI use, or to check a journal.","https:\u002F\u002Fgithub.com\u002Fthe-vibey-project\u002Fvibey\u002Fblob\u002Fdevelop\u002Fsrc\u002Fvibey_tools\u002Fskills\u002Fplugins\u002Fwriting-craft\u002Fskills\u002Fjournal-publishability-criteria\u002FSKILL.md",[],[]]