[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MR2XPMMMYVJ8G3ZVP2GH8":3,"skill-same:01M74MR2XPMMMYVJ8G3ZVP2GH8":57},{"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":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M74MR2XPMMMYVJ8G3ZVP2GH8","sell-research-honestly",null,"Audit, position, and communicate research value without outrunning the evidence. Use when users need audience-specific buy-in from advisors, collaborators, reviewers, talk audiences, or the research community; want to pitch or promote an idea, paper, result, codebase, or demo; plan research PR; or need to detect and repair overclaiming. Do not use for generic proofreading, summarization, or formatting.","pengqianhan\u002FAI-Human-Research-OS","pengqianhan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4286531?v=4","01M74M3DT9HNZ6HPAK8TX69EX9","PengqianHan","01M74M3DTVSN2GXW0JH2W396FK",3,"MIT","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fsell-research-honestly\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: sell-research-honestly\ndescription: Audit, position, and communicate research value without outrunning the evidence. Use when users need audience-specific buy-in from advisors, collaborators, reviewers, talk audiences, or the research community; want to pitch or promote an idea, paper, result, codebase, or demo; plan research PR; or need to detect and repair overclaiming. Do not use for generic proofreading, summarization, or formatting.\n---\n\n# Sell Research Honestly\n\nTurn one research object into the strongest defensible case for one audience\nand one desired action. Keep facts invariant while changing emphasis.\n\n## Inputs\n\nEstablish three inputs:\n\n1. **Research object** — an idea, experiment, paper, codebase, talk, demo, or\n   the files that contain it.\n2. **Audience** — one advisor, collaborator, reviewer, talk audience, or\n   research community.\n3. **Desired action** — what that audience should understand, approve, discuss,\n   accept, use, cite, or do next.\n\nInspect supplied materials and repository evidence before requesting facts. If\nan input remains missing, ask one blocking question per turn while completing\nthe audit work that is already possible.\n\n## 1. Frame the case\n\nClassify the research object as `idea`, `preliminary`, or `evidenced`. Read the\nmatching audience section in\n[`references\u002Faudience-playbooks.md`](references\u002Faudience-playbooks.md), then\nwrite a four-part **audience model**:\n\n- outcome the audience values;\n- cost or decision risk they bear;\n- objection they are most likely to raise;\n- evidence that would make the desired action reasonable.\n\nRead the reference's feedback section only when the user brings back real\nreactions or outcomes.\n\n**Complete when:** the research object, maturity, single audience, desired\naction, and all four audience-model fields are explicit.\n\n## 2. Build the value case\n\nCreate a six-field **value case**. Mark every field `supported`, `plausible`,\n`missing`, or `contradicted`.\n\n| Field | Question |\n| --- | --- |\n| Problem | What concrete problem exists? |\n| Audience stake | Why does this audience care? |\n| Gap | Where do current approaches fail or cost too much? |\n| Insight \u002F solution | What new information or intervention does the work add? |\n| Evidence | What makes each material claim credible? |\n| Boundary \u002F cost | Where does it fail, stop applying, or impose a cost? |\n\nBuild a **claim ledger** beside the value case. Give every material claim one\nstate and an exact evidence pointer:\n\n- `observed` — directly supported by the materials;\n- `inferred` — a reasoned interpretation of observed evidence;\n- `hypothesized` — a proposition awaiting a test;\n- `unsupported` — no supplied support;\n- `contradicted` — conflicts with supplied evidence.\n\nPrefer evidence in this order: raw results, data, code output, figures, and\nverified citations; locatable project or manuscript material; user-provided\nbut unverified information; agent inference. Label the last two categories.\nTreat novelty, priority, state-of-the-art, and comparisons with current work as\nexternal facts: verify them against external literature. Until verified, keep\ntheir claim state `unsupported`, add `verification: unverified`, and exclude\nthem from public copy.\n\nMake the evidence burden proportional to the claim:\n\n- Attach evidence to strong terms such as *first*, *general*, *robust*,\n  *low-cost*, and *state of the art*; otherwise use a supported term.\n- Inspect critical subgroup and failure behavior rather than relying on an\n  average alone.\n- Account for added compute, data, labor, latency, memory, and deployment cost.\n- Match causal language to a design that excludes the main alternative\n  explanations.\n- Match scope to the tested models, datasets, conditions, and cases.\n- Require fair baselines for comparative effectiveness.\n\nWhen evidence is narrower, narrow the claim.\n\n**Complete when:** all six fields have a status, every material claim has one\nstate and a source pointer, and every comparative external claim is verified\nor held `unsupported` with `verification: unverified`.\n\n## 3. Apply the value gate\n\nChoose exactly one verdict:\n\n- `ready-to-sell` — the value proposition and material claims are supported;\n- `narrow-and-sell` — a useful case survives after narrowing or qualification;\n- `validate-first` — the value is plausible but a load-bearing claim lacks\n  evidence;\n- `do-not-claim` — the core claim is unsupported, contradicted, or relies on a\n  research-integrity breach.\n\nFor `validate-first`, produce a minimum discriminating validation plan: claim,\ncheapest informative test, success and failure criteria, and how each outcome\nchanges the message. Treat the result as an internal validation brief rather\nthan public-ready copy.\n\nFor `do-not-claim`, run one **salvage pass** for a narrower phenomenon, negative\nresult, failure mode, engineering benefit, cost advantage, or worthwhile\nresearch question. Use the recovered case only if its own claim ledger passes\nthe gate. If nothing survives, make the Primary Deliverable a concise no-case\nfinding that names the evidence required to reopen the claim.\n\nThe verdict measures readiness for honest communication, not the probability\nof acceptance, collaboration, publication, or attention.\n\n**Complete when:** the verdict follows from the value case and fixes which\ndeliverable is allowed next.\n\n## 4. Compose the strongest defensible message\n\nFor `ready-to-sell` or `narrow-and-sell`, use this narrative spine:\n\n> audience-relevant problem → concrete gap → insight or solution → value →\n> strongest evidence → boundary and cost → explicit next action\n\nWrite `observed` claims as facts. Mark `inferred` claims with calibrated\nlanguage. Present `hypothesized` claims only as research questions or future\ntests. Replace `unsupported` and `contradicted` claims with the narrowest\nsupported alternative.\n\nVary emphasis, length, and vocabulary for the audience; keep evidence, costs,\nand scope unchanged. Produce one primary deliverable unless the user requests\nadditional formats. Name the concrete contribution before any larger vision.\n\n**Complete when:** the deliverable serves the audience model, contains one\nclear takeaway and next action, and every factual sentence maps to the claim\nledger.\n\n## 5. Run the integrity pass and deliver\n\nRe-run the Step 2 evidence rules against every sentence in the draft. Repair\neach mismatch by adding evidence, qualifying the sentence, or replacing it\nwith the narrowest supported claim.\n\nReturn four sections:\n\n1. **Verdict** — status and decisive reason.\n2. **Value Case** — the six audited fields and audience model.\n3. **Primary Deliverable** — one ready-to-use artifact allowed by the gate.\n4. **Integrity Notes** — claim ledger, required qualifiers, evidence gaps, and\n   next action.\n\nDefault to chat output. Edit only files the user explicitly names. Draft PR\nplans, outreach, and posts locally; publish, send, or contact people only after\nthe user authorizes that external action. Match the user's language unless the\ntarget artifact establishes another language.\n\n**Complete when:** the audience and action are explicit; the verdict matches\nthe research maturity; every material claim is traceable; the deliverable\npreserves boundaries and costs; and the next action is concrete.\n","# Sell Research Honestly\n\nTurn one research object into the strongest defensible case for one audience\nand one desired action. Keep facts invariant while changing emphasis.\n\n## Inputs\n\nEstablish three inputs:\n\n1. **Research object** — an idea, experiment, paper, codebase, talk, demo, or\n   the files that contain it.\n2. **Audience** — one advisor, collaborator, reviewer, talk audience, or\n   research community.\n3. **Desired action** — what that audience should understand, approve, discuss,\n   accept, use, cite, or do next.\n\nInspect supplied materials and repository evidence before requesting facts. If\nan input remains missing, ask one blocking question per turn while completing\nthe audit work that is already possible.\n\n## 1. Frame the case\n\nClassify the research object as `idea`, `preliminary`, or `evidenced`. Read the\nmatching audience section in\n[`references\u002Faudience-playbooks.md`](references\u002Faudience-playbooks.md), then\nwrite a four-part **audience model**:\n\n- outcome the audience values;\n- cost or decision risk they bear;\n- objection they are most likely to raise;\n- evidence that would make the desired action reasonable.\n\nRead the reference's feedback section only when the user brings back real\nreactions or outcomes.\n\n**Complete when:** the research object, maturity, single audience, desired\naction, and all four audience-model fields are explicit.\n\n## 2. Build the value case\n\nCreate a six-field **value case**. Mark every field `supported`, `plausible`,\n`missing`, or `contradicted`.\n\n| Field | Question |\n| --- | --- |\n| Problem | What concrete problem exists? |\n| Audience stake | Why does this audience care? |\n| Gap | Where do current approaches fail or cost too much? |\n| Insight \u002F solution | What new information or intervention does the work add? |\n| Evidence | What makes each material claim credible? |\n| Boundary \u002F cost | Where does it fail, stop applying, or impose a cost? |\n\nBuild a **claim ledger** beside the value case. Give every material claim one\nstate and an exact evidence pointer:\n\n- `observed` — directly supported by the materials;\n- `inferred` — a reasoned interpretation of observed evidence;\n- `hypothesized` — a proposition awaiting a test;\n- `unsupported` — no supplied support;\n- `contradicted` — conflicts with supplied evidence.\n\nPrefer evidence in this order: raw results, data, code output, figures, and\nverified citations; locatable project or manuscript material; user-provided\nbut unverified information; agent inference. Label the last two categories.\nTreat novelty, priority, state-of-the-art, and comparisons with current work as\nexternal facts: verify them against external literature. Until verified, keep\ntheir claim state `unsupported`, add `verification: unverified`, and exclude\nthem from public copy.\n\nMake the evidence burden proportional to the claim:\n\n- Attach evidence to strong terms such as *first*, *general*, *robust*,\n  *low-cost*, and *state of the art*; otherwise use a supported term.\n- Inspect critical subgroup and failure behavior rather than relying on an\n  average alone.\n- Account for added compute, data, labor, latency, memory, and deployment cost.\n- Match causal language to a design that excludes the main alternative\n  explanations.\n- Match scope to the tested models, datasets, conditions, and cases.\n- Require fair baselines for comparative effectiveness.\n\nWhen evidence is narrower, narrow the claim.\n\n**Complete when:** all six fields have a status, every material claim has one\nstate and a source pointer, and every comparative external claim is verified\nor held `unsupported` with `verification: unverified`.\n\n## 3. Apply the value gate\n\nChoose exactly one verdict:\n\n- `ready-to-sell` — the value proposition and material claims are supported;\n- `narrow-and-sell` — a useful case survives after narrowing or qualification;\n- `validate-first` — the value is plausible but a load-bearing claim lacks\n  evidence;\n- `do-not-claim` — the core claim is unsupported, contradicted, or relies on a\n  research-integrity breach.\n\nFor `validate-first`, produce a minimum discriminating validation plan: claim,\ncheapest informative test, success and failure criteria, and how each outcome\nchanges the message. Treat the result as an internal validation brief rather\nthan public-ready copy.\n\nFor `do-not-claim`, run one **salvage pass** for a narrower phenomenon, negative\nresult, failure mode, engineering benefit, cost advantage, or worthwhile\nresearch question. Use the recovered case only if its own claim ledger passes\nthe gate. If nothing survives, make the Primary Deliverable a concise no-case\nfinding that names the evidence required to reopen the claim.\n\nThe verdict measures readiness for honest communication, not the probability\nof acceptance, collaboration, publication, or attention.\n\n**Complete when:** the verdict follows from the value case and fixes which\ndeliverable is allowed next.\n\n## 4. Compose the strongest defensible message\n\nFor `ready-to-sell` or `narrow-and-sell`, use this narrative spine:\n\n> audience-relevant problem → concrete gap → insight or solution → value →\n> strongest evidence → boundary and cost → explicit next action\n\nWrite `observed` claims as facts. Mark `inferred` claims with calibrated\nlanguage. Present `hypothesized` claims only as research questions or future\ntests. Replace `unsupported` and `contradicted` claims with the narrowest\nsupported alternative.\n\nVary emphasis, length, and vocabulary for the audience; keep evidence, costs,\nand scope unchanged. Produce one primary deliverable unless the user requests\nadditional formats. Name the concrete contribution before any larger vision.\n\n**Complete when:** the deliverable serves the audience model, contains one\nclear takeaway and next action, and every factual sentence maps to the claim\nledger.\n\n## 5. Run the integrity pass and deliver\n\nRe-run the Step 2 evidence rules against every sentence in the draft. Repair\neach mismatch by adding evidence, qualifying the sentence, or replacing it\nwith the narrowest supported claim.\n\nReturn four sections:\n\n1. **Verdict** — status and decisive reason.\n2. **Value Case** — the six audited fields and audience model.\n3. **Primary Deliverable** — one ready-to-use artifact allowed by the gate.\n4. **Integrity Notes** — claim ledger, required qualifiers, evidence gaps, and\n   next action.\n\nDefault to chat output. Edit only files the user explicitly names. Draft PR\nplans, outreach, and posts locally; publish, send, or contact people only after\nthe user authorizes that external action. Match the user's language unless the\ntarget artifact establishes another language.\n\n**Complete when:** the audience and action are explicit; the verdict matches\nthe research maturity; every material claim is traceable; the deliverable\npreserves boundaries and costs; and the next action is concrete.\n",{"name":5,"description":7},"main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fopen-paper-skills\u002Fsell-research-honestly",0,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS","https:\u002F\u002Fpengqianhan.github.io\u002FAI-Human-Research-OS\u002F","https:\u002F\u002Fgithub.com\u002Fpengqianhan","Ph.D. candidate of The University of Auckland, New Zealand","2026-11-14 18:08:16",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill sell-research-honestly",{"tool":39,"command":40},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill sell-research-honestly",{"tool":42,"command":43},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill sell-research-honestly","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fsell-research-honestly\u002FSKILL.md",true,[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",336,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fsell-research-honestly\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Faudience-playbooks.md",7791,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fopen-paper-skills\u002Fsell-research-honestly\u002Freferences\u002Faudience-playbooks.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M74MWYTHT498SVMN823896T7","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"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},"01M74MWWVCFZ8HQS8840F1V1FT","uv","Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fuv\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},"01M74MWRH5BTSWZ2C5PCTD5FV9","uniprot-database","Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funiprot_database\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},"01M74MWN1D3ER9F1FZPWH8HQC1","unibind-database","Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED\u002FFASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funibind_database\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},"01M74MWHHB5QZY3NR2FYA1EK4N","ucsc-conservation-and-tfbs","Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fucsc_conservation_and_tfbs\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},"01M74MWERYHSY87P21FDMVE6BA","string-database","Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fstring_database\u002FSKILL.md",[],[]]