[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73B3CX5BST76G0KXJ710G9R":3,"skill-same:01M73B3CX5BST76G0KXJ710G9R":68},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M73B3CX5BST76G0KXJ710G9R","academic-humanizer",null,"Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and funding proposals (NSF Project Summary\u002FDescription, NIH Specific Aims): preserve scholarly conventions, match claims to evidence (and, for proposals, claims to feasibility), and match the author's own voice. It never changes a number, result, or citation, and it is not for evading AI-use disclosure. Use when editing AI-assisted academic prose or grant proposals.","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Facademic-humanizer\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Facademic-humanizer\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: academic-humanizer\nversion: 0.3.3\ndescription: \"Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and\n  funding proposals (NSF Project Summary\u002FDescription, NIH Specific Aims): preserve scholarly\n  conventions, match claims to evidence (and, for proposals, claims to feasibility), and match the\n  author's own voice. It never changes a number, result, or citation, and it is not for evading\n  AI-use disclosure. Use when editing AI-assisted academic prose or grant proposals.\"\nlicense: MIT\ncompatibility: claude-code codex morphmind opencode\nallowed-tools: [Read, Write, Edit, Grep, Glob, AskUserQuestion]\n---\n\n# Academic Humanizer\n\nImprove the clarity and voice of AI-assisted *academic* writing while keeping the precise,\nevidence-bound voice that scholarship requires and matching the author's own style. It preserves every\nnumber, result, and citation, and it is not a tool for evading AI-use disclosure.\n\n## When to use\nEditing or reviewing academic prose: paper sections, abstracts, rebuttals, related work, and **funding\nproposals** (NSF Project Summary\u002FDescription, NIH Specific Aims, fellowship and foundation proposals;\nsee Layer 6). **Not** for blogs, marketing, or personal essays, and **never** inject opinion, humor, or\nfirst-person \"personality\" into a manuscript. For technical writing, neutral and precise *is* the human\nvoice. One caveat for proposals: their register is different from a paper's, since they are sold on\nvision and feasibility, so the ambition language a paper would trim is appropriate there; apply Layer 6,\nnot the paper layers' stricter trimming, to vision statements.\n\n## Core principle\nAcademic writing already has a correct human voice: neutral, precise, third-person plural (\"we\"), every\nclaim tied to its evidence. The job is to (1) strip the AI *tells* without casualizing, and (2) enforce\nthe discipline a general humanizer misses: **every claim earns its number, figure, or citation, and no\nverb is stronger than its evidence.**\n\n## Process\n1. **Read** the manuscript and any author writing sample; note the document type (paper vs. funding\n   proposal) and the target venue or funding agency. For proposals, also apply Layer 6 and preserve\n   appropriate vision.\n2. **Audit** (do not edit yet): list each detected pattern with its location and proposed fix, and each\n   empirical claim's evidence status.\n3. **Rewrite**: same structure and content, all claims and citations preserved, tells removed, over-claims\n   matched to evidence, legitimate hedging kept.\n4. **Report**: cleaned text plus a short change log (patterns removed, claims softened or given evidence\n   pointers, voice notes). Cover everything the original covered: if it had five paragraphs, so does the\n   rewrite.\n\n---\n\n## Layer 1: General AI-tell catalog\nScan for and fix the general patterns, subject to the academic exceptions in Layer 3:\ninflated significance (\"marking a pivotal moment\"); superficial \"-ing\" tails that fake depth\n(\"..., highlighting...\"); promotional\u002Ffigurative language (\"rich\", \"vibrant\", \"groundbreaking\");\nvague attributions (\"experts argue\" with no cite); AI vocabulary (*delve, underscore, intricate,\ntapestry, testament, landscape (abstract), pivotal, showcase, foster, leverage (filler), realm,\nseamless*); copula avoidance (\"serves as\" -> \"is\"); negative parallelisms (\"not just X, but Y\");\nrule-of-three padding; elegant variation (cycling synonyms for one referent); filler\n(\"it is worth noting that\", \"in order to\"); **overlong, clause-stacked sentences (split them; see 2.11)**;\nand **em-dashes (remove entirely; recast with commas, colons, parentheses, or separate sentences)**.\n\n**Before:** *Additionally, an enduring testament to the method's value is its ability to delve into\nintricate dependencies, showcasing a seamless integration that underscores its pivotal role.*\n**After:** *The method also captures higher-order dependencies, which the baselines miss (Table 2).*\n\n---\n\n## Layer 2: Academic AI tells (remove or fix)\n\n### 2.1 Over-claiming verbs\nEmpirical work *shows* and *provides evidence*; it does not *prove* or *demonstrate* universal truths.\n**Watch:** demonstrate, prove, establish, confirm, guarantee; \"significantly\" with no test\u002Fnumber.\n**Before:** *We prove that our method significantly outperforms all prior approaches.*\n**After:** *Our method improves held-out accuracy by 4--7 points over the strongest prior approach\n(Table 3); the gain is significant at p \u003C 0.01 by a paired test.*\n\n### 2.2 Significance hype\n**Watch:** paves the way for, a crucial\u002Fpivotal step toward, has the potential to revolutionize, opens\nnew avenues, sheds light on, of paramount importance, bridges the gap.\n**Before:** *This work paves the way for a new paradigm and sheds light on a problem of paramount\nimportance.*\n**After:** *This work addresses one failure mode of prior methods: error accumulation under long-horizon\nrollout (Section 4).*\n\n### 2.3 Empty intensifiers\n**Watch:** extensive\u002Fcomprehensive\u002Fthorough experiments, a wide range of, numerous, various.\n**Before:** *We conduct extensive experiments on a wide range of datasets.*\n**After:** *We evaluate on three datasets (ImageNet, CIFAR-100, and iNaturalist).*\n\n### 2.4 Novelty padding\n**Watch:** \"novel\" used more than once per section; \"to the best of our knowledge\"; \"for the first time\".\n**Before:** *We propose a novel framework and, to the best of our knowledge, are the first to study this.*\n**After:** *We study online calibration under delayed labels, which prior calibration work (offline) does\nnot address.*\n\n### 2.5 Formulaic openers\n**Watch:** \"In recent years, X has attracted increasing attention\"; \"With the rapid development of...\";\n\"Despite recent advances,...\".\n**Before:** *In recent years, tabular deep learning has attracted increasing attention.*\n**After:** *Tabular deep learning has a structural limitation: most models discard feature-type metadata\nand must relearn it from data.*\n\n### 2.6 Connective overuse\nDo not start consecutive sentences with Moreover\u002FFurthermore\u002FAdditionally\u002FIn particular; let logic carry.\n**Before:** *Moreover, the method is fast. Furthermore, it is simple. Additionally, it scales.*\n**After:** *The method is fast and simple, and it scales to one million rows (Section 5).*\n\n### 2.7 Contribution-list cliches\nEach contribution names a *specific* result, not a restatement of the abstract.\n**Before:** *Our contributions are: (1) a novel method; (2) extensive experiments; (3) strong results.*\n**After:** *We (1) introduce a metadata-aware encoder that reaches 0.91 AUROC vs 0.86 for the strongest\nbaseline; (2) show it stays within 2 points under 20% label noise where the baseline drops 9; (3) release\nthe benchmark.*\n\n### 2.8 Citation dumping\nCite the one or two works that matter and say why, not a bracketed list.\n**Before:** *Many methods exist [3, 7, 9, 12, 15].*\n**After:** *The closest prior method is TabNet [7], which encodes all features jointly; we instead\ncondition on feature-type metadata.*\n\n### 2.9 Hedging-by-vagueness\n**Watch:** somewhat, relatively, fairly, to some extent, quite. Quantify or cut.\n**Before:** *Performance is somewhat better and relatively robust.*\n**After:** *Accuracy is 3 points higher and varies by less than 1 point across five seeds.*\n\n### 2.10 Boilerplate emphasis\n**Watch:** \"It is worth noting that\", \"It should be emphasized that\", \"Notably,\", \"Importantly,\".\nIf it matters, the sentence shows it.\n**Before:** *It is worth noting that, importantly, the gain holds across scenarios.*\n**After:** *The gain holds across all three scenarios (Table 4).*\n\n### 2.11 Overlong, clause-stacked sentences\nAI favors long sentences that chain three or four clauses with commas and \"which\", \"that\", \"while\", \"with\".\nSplit them: one idea per sentence, and cut subordinate clauses that carry no weight. **Watch:** sentences\npast ~30 words, or with 3+ subordinate clauses.\n**Before:** *Existing methods, though promising, are largely empirical, with unclear principles\nunderpinning their behavior, which limits their reliability and further progress.*\n**After:** *Existing methods stay empirical. Their principles are unclear, which limits reliability and\nprogress.*\n\n---\n\n## Layer 3: Preserve these (do NOT over-correct)\nA general humanizer flattens legitimate scholarly constructs. Keep them.\n\n- **Evidence-tied hedging is correct and required.** Keep \"suggests\", \"is consistent with\", \"we\n  hypothesize that\", \"may indicate\", \"appears to\" when the claim is genuinely uncertain.\n  *Wrong fix:* turning *\"the results suggest X\"* into *\"the results prove X\"*: this manufactures\n  over-claiming. Keep the calibrated verb.\n- **Passive voice** is fine when the actor is irrelevant: *\"Samples were normalized to total protein.\"*\n- **First-person plural \"we\"** is standard; do not rewrite to avoid it.\n- **Semicolons and an occasional triple** are fine in moderation. Em-dashes are the exception: remove\n  them entirely (Layer 1), recasting with commas, colons, parentheses, or separate sentences.\n- **Formal definitions, named methods\u002Fmetrics, technical terms, equations, and symbols** stay verbatim.\n- **Never invent, drop, or alter a number, equation, or citation.** Same content; preserve every cite key.\n\n---\n\n## Layer 4: Claim-evidence discipline\nFor every empirical claim, check (a) is it backed by a number, figure, table, or citation in the text,\nand (b) does the verb match the strength of that evidence?\n\n- **Unbacked claim -> add the evidence pointer or soften.**\n  *Before:* *Our method is more robust.*  *After:* *Our method's accuracy drops by 2 points under\n  distribution shift, versus 11 points for the baseline (Figure 3).*\n- **Verb stronger than evidence -> downgrade.**\n  *Before:* *This demonstrates that our method is universally superior.*\n  *After:* *On these three datasets, our method matches or exceeds the strongest baseline (Table 2).*\n- **Vague magnitude -> a number or RANGE, attributed.**\n  *Before:* *a large improvement.*  *After:* *a 2--6% improvement in balanced accuracy over the strongest\n  baseline.*\n  Prefer ranges (e.g., \"2--6%\") over single averaged values unless the averaging method is stated, and\n  attribute each number to its method, metric, and baseline. When comparing, lead with the comparison\n  against the strongest competitor, not the trivial baseline.\n\n---\n\n## Layer 5: Voice and venue matching\nIf the author supplies prior papers, read a sample first and note sentence rhythm, connective habits,\nlevel and placement of hedging, how they open sections, notation, and recurring phrasings, then match\nthem. Match the venue's register too (e.g., ICLR\u002FNeurIPS: terse, direct, results-forward; Nature\u002FPNAS:\nmore expository). Absent a sample, default to clean, precise, venue-appropriate prose, not the casual,\nopinionated voice of a general-purpose humanizer.\n\n## Layer 6: Funding-proposal mode (NSF, NIH)\nA proposal is not a paper. It is sold on **vision plus feasibility**, not on finished results, and\nreviewers score it. The register shift matters: ambition language that the paper layers would trim\n(\"long-term goal\", \"pioneer\", \"transformative\", \"establish a foundation\") is *appropriate and expected*\nhere, provided a credible plan and evidence back it. So in proposal mode, **do not flatten the vision**;\nenforce a different discipline instead: **claim \u003C-> feasibility**.\n\n### 6.1 Know the structure; the score lives in the first pages\nReviewers form a score from the opening, then skim the rest to confirm it. Put most editing effort there.\n- **NSF.** A one-page **Project Summary** with the three review-criteria heads spelled out:\n  **Overview**, **Intellectual Merit**, **Broader Impacts**, each self-contained. The Project\n  Description then opens with **long-term vision -> this proposal's goal -> the gap -> the specific\n  thrusts\u002Faims -> the payoff**, ideally within the first 1--2 pages, with one overview figure. Broader\n  Impacts must be substantive and integrated, never an afterthought.\n- **NIH (R01).** The **Specific Aims page is the whole proposal in one page**, and is the most-read,\n  most-decisive page. Standard arc: (1) opening: the problem, what is known, the **gap \u002F critical need**;\n  (2) the **long-term goal** and the **central hypothesis** with its rationale; (3) \"**The objective of\n  this application is...**\" plus how the hypothesis was formed; (4) **2--3 Aims**, each a one-line goal +\n  a phrase on approach + the expected outcome; (5) a **payoff** paragraph: what changes if it succeeds.\n  Then **Significance, Innovation, Approach** as separately scored sections.\n\n### 6.2 First-3-pages primacy (edit these hardest)\nBy the end of page 1 (NIH Aims) or pages ~2--3 (NSF), the reader must already hold: the **hook** (why it\nmatters, concretely), the **gap** (what is missing and the cost of the gap), the **central idea** (your\napproach in one sentence), the **aims\u002Fthrusts** (crisp and parallel), and the **payoff**. If any is\nmissing or buried, fix that before touching later sections. A reviewer unconvinced by page 3 does not\nrecover on page 10.\n\n### 6.3 Proposal-specific weak moves to fix\n- **Vague importance.** *Watch:* \"this is an important\u002Ftimely problem\", \"X has many applications\".\n  **Before:** *Understanding this problem is critically important.*\n  **After:** *Without bounds on how measurement noise propagates to diagnosis, clinical models are tuned by\n  trial and error, the inefficiency this proposal removes.*\n- **Method-as-aim** (an aim naming a technique instead of a question or outcome).\n  **Before:** *Aim 2: Apply transfer learning to the dataset.*\n  **After:** *Aim 2: Determine whether fusing wearable and lab signals improves early detection, and for\n  which patient subgroups it helps or hurts.*\n- **Dominoed aims** (Aim 2\u002F3 collapse if Aim 1 fails; reviewers flag this as fragile). *Fix:* phrase\n  aims as **parallel and independently valuable**; where one depends on another, state the fallback.\n- **Ambition without feasibility.** Every bold claim needs a footing: preliminary data, a prior\n  result\u002Fpublication, a classical theorem you build on, or a collaborator\u002Fletter. *Fix:* attach the\n  evidence beside the claim (\"our preliminary result in Fig. X shows...\", \"building on a classical minimax\n  lower bound...\").\n- **Boilerplate Broader Impacts \u002F training plan.** *Watch:* \"we will mentor students and disseminate via\n  talks and papers.\" *Fix:* make it concrete, enumerated, and tied to the research: specific programs,\n  named courses or tools, measurable outreach.\n- **Hedged central hypothesis.** The Aims-page hypothesis is a falsifiable commitment, not \"we will\n  explore whether possibly...\". Calibrated hedging belongs in the Approach's interpretation, not the\n  central claim.\n\n### 6.4 Preserve and deploy (funded-proposal craft)\nThese read as strength; keep or add them rather than editing them out.\n- **Vision\u002Fambition framing**: a bold long-term goal up front, with this proposal as one principled step\n  toward it.\n- **Run-in lead-ins for scannability**: bold\u002Fitalic **Goal:**, **Motivation:**, **Innovation:**,\n  *Thrust\u002FAim N (one-line mission):*. Reviewers skim; visible structure earns time.\n- **A concrete running example or protagonist** to make an abstract method vivid and consistent across aims.\n- **Sharp challenge\u002Faim statements posed as questions**: a crisp open question reads as a well-posed\n  problem (a boxed or set-off question per aim works well).\n- **Anchoring novel work in deep, named classical results** to signal rigor and lineage: a known\n  inequality, capacity notion, or test that the new method generalizes.\n- **Foreground the team's standing as feasibility evidence**: prior funded work, preliminary results,\n  publications, collaborators, and demonstration partners belong *early*, as proof the plan is executable.\n  A real track record is evidence, not boasting; place it where it de-risks the aims. *(Use only the PI's\n  own real, supplied record; never invent funding, results, partners, or letters.)*\n\n### 6.5 Claim \u003C-> feasibility (the proposal analog of Layer 4)\nFor every aim and promised outcome, check: is the ambition matched by a credible means, such as\npreliminary data, a prior method, a classical foundation, a collaborator, or staged de-risking? If yes,\nkeep the ambitious verb. If no, attach the missing evidence or scale the claim to what the plan supports.\nNever invent preliminary results, prior funding, partners, or letters; if the support does not exist, flag\nthe gap for the author rather than papering over it.\n\n---\n\n## Output\nReturn the cleaned text plus a short change report: patterns removed (by type), claims softened or given\nevidence pointers, and any voice\u002Fvenue notes. Confirm that no number, equation, or citation was altered.\n","# Academic Humanizer\n\nImprove the clarity and voice of AI-assisted *academic* writing while keeping the precise,\nevidence-bound voice that scholarship requires and matching the author's own style. It preserves every\nnumber, result, and citation, and it is not a tool for evading AI-use disclosure.\n\n## When to use\nEditing or reviewing academic prose: paper sections, abstracts, rebuttals, related work, and **funding\nproposals** (NSF Project Summary\u002FDescription, NIH Specific Aims, fellowship and foundation proposals;\nsee Layer 6). **Not** for blogs, marketing, or personal essays, and **never** inject opinion, humor, or\nfirst-person \"personality\" into a manuscript. For technical writing, neutral and precise *is* the human\nvoice. One caveat for proposals: their register is different from a paper's, since they are sold on\nvision and feasibility, so the ambition language a paper would trim is appropriate there; apply Layer 6,\nnot the paper layers' stricter trimming, to vision statements.\n\n## Core principle\nAcademic writing already has a correct human voice: neutral, precise, third-person plural (\"we\"), every\nclaim tied to its evidence. The job is to (1) strip the AI *tells* without casualizing, and (2) enforce\nthe discipline a general humanizer misses: **every claim earns its number, figure, or citation, and no\nverb is stronger than its evidence.**\n\n## Process\n1. **Read** the manuscript and any author writing sample; note the document type (paper vs. funding\n   proposal) and the target venue or funding agency. For proposals, also apply Layer 6 and preserve\n   appropriate vision.\n2. **Audit** (do not edit yet): list each detected pattern with its location and proposed fix, and each\n   empirical claim's evidence status.\n3. **Rewrite**: same structure and content, all claims and citations preserved, tells removed, over-claims\n   matched to evidence, legitimate hedging kept.\n4. **Report**: cleaned text plus a short change log (patterns removed, claims softened or given evidence\n   pointers, voice notes). Cover everything the original covered: if it had five paragraphs, so does the\n   rewrite.\n\n---\n\n## Layer 1: General AI-tell catalog\nScan for and fix the general patterns, subject to the academic exceptions in Layer 3:\ninflated significance (\"marking a pivotal moment\"); superficial \"-ing\" tails that fake depth\n(\"..., highlighting...\"); promotional\u002Ffigurative language (\"rich\", \"vibrant\", \"groundbreaking\");\nvague attributions (\"experts argue\" with no cite); AI vocabulary (*delve, underscore, intricate,\ntapestry, testament, landscape (abstract), pivotal, showcase, foster, leverage (filler), realm,\nseamless*); copula avoidance (\"serves as\" -> \"is\"); negative parallelisms (\"not just X, but Y\");\nrule-of-three padding; elegant variation (cycling synonyms for one referent); filler\n(\"it is worth noting that\", \"in order to\"); **overlong, clause-stacked sentences (split them; see 2.11)**;\nand **em-dashes (remove entirely; recast with commas, colons, parentheses, or separate sentences)**.\n\n**Before:** *Additionally, an enduring testament to the method's value is its ability to delve into\nintricate dependencies, showcasing a seamless integration that underscores its pivotal role.*\n**After:** *The method also captures higher-order dependencies, which the baselines miss (Table 2).*\n\n---\n\n## Layer 2: Academic AI tells (remove or fix)\n\n### 2.1 Over-claiming verbs\nEmpirical work *shows* and *provides evidence*; it does not *prove* or *demonstrate* universal truths.\n**Watch:** demonstrate, prove, establish, confirm, guarantee; \"significantly\" with no test\u002Fnumber.\n**Before:** *We prove that our method significantly outperforms all prior approaches.*\n**After:** *Our method improves held-out accuracy by 4--7 points over the strongest prior approach\n(Table 3); the gain is significant at p \u003C 0.01 by a paired test.*\n\n### 2.2 Significance hype\n**Watch:** paves the way for, a crucial\u002Fpivotal step toward, has the potential to revolutionize, opens\nnew avenues, sheds light on, of paramount importance, bridges the gap.\n**Before:** *This work paves the way for a new paradigm and sheds light on a problem of paramount\nimportance.*\n**After:** *This work addresses one failure mode of prior methods: error accumulation under long-horizon\nrollout (Section 4).*\n\n### 2.3 Empty intensifiers\n**Watch:** extensive\u002Fcomprehensive\u002Fthorough experiments, a wide range of, numerous, various.\n**Before:** *We conduct extensive experiments on a wide range of datasets.*\n**After:** *We evaluate on three datasets (ImageNet, CIFAR-100, and iNaturalist).*\n\n### 2.4 Novelty padding\n**Watch:** \"novel\" used more than once per section; \"to the best of our knowledge\"; \"for the first time\".\n**Before:** *We propose a novel framework and, to the best of our knowledge, are the first to study this.*\n**After:** *We study online calibration under delayed labels, which prior calibration work (offline) does\nnot address.*\n\n### 2.5 Formulaic openers\n**Watch:** \"In recent years, X has attracted increasing attention\"; \"With the rapid development of...\";\n\"Despite recent advances,...\".\n**Before:** *In recent years, tabular deep learning has attracted increasing attention.*\n**After:** *Tabular deep learning has a structural limitation: most models discard feature-type metadata\nand must relearn it from data.*\n\n### 2.6 Connective overuse\nDo not start consecutive sentences with Moreover\u002FFurthermore\u002FAdditionally\u002FIn particular; let logic carry.\n**Before:** *Moreover, the method is fast. Furthermore, it is simple. Additionally, it scales.*\n**After:** *The method is fast and simple, and it scales to one million rows (Section 5).*\n\n### 2.7 Contribution-list cliches\nEach contribution names a *specific* result, not a restatement of the abstract.\n**Before:** *Our contributions are: (1) a novel method; (2) extensive experiments; (3) strong results.*\n**After:** *We (1) introduce a metadata-aware encoder that reaches 0.91 AUROC vs 0.86 for the strongest\nbaseline; (2) show it stays within 2 points under 20% label noise where the baseline drops 9; (3) release\nthe benchmark.*\n\n### 2.8 Citation dumping\nCite the one or two works that matter and say why, not a bracketed list.\n**Before:** *Many methods exist [3, 7, 9, 12, 15].*\n**After:** *The closest prior method is TabNet [7], which encodes all features jointly; we instead\ncondition on feature-type metadata.*\n\n### 2.9 Hedging-by-vagueness\n**Watch:** somewhat, relatively, fairly, to some extent, quite. Quantify or cut.\n**Before:** *Performance is somewhat better and relatively robust.*\n**After:** *Accuracy is 3 points higher and varies by less than 1 point across five seeds.*\n\n### 2.10 Boilerplate emphasis\n**Watch:** \"It is worth noting that\", \"It should be emphasized that\", \"Notably,\", \"Importantly,\".\nIf it matters, the sentence shows it.\n**Before:** *It is worth noting that, importantly, the gain holds across scenarios.*\n**After:** *The gain holds across all three scenarios (Table 4).*\n\n### 2.11 Overlong, clause-stacked sentences\nAI favors long sentences that chain three or four clauses with commas and \"which\", \"that\", \"while\", \"with\".\nSplit them: one idea per sentence, and cut subordinate clauses that carry no weight. **Watch:** sentences\npast ~30 words, or with 3+ subordinate clauses.\n**Before:** *Existing methods, though promising, are largely empirical, with unclear principles\nunderpinning their behavior, which limits their reliability and further progress.*\n**After:** *Existing methods stay empirical. Their principles are unclear, which limits reliability and\nprogress.*\n\n---\n\n## Layer 3: Preserve these (do NOT over-correct)\nA general humanizer flattens legitimate scholarly constructs. Keep them.\n\n- **Evidence-tied hedging is correct and required.** Keep \"suggests\", \"is consistent with\", \"we\n  hypothesize that\", \"may indicate\", \"appears to\" when the claim is genuinely uncertain.\n  *Wrong fix:* turning *\"the results suggest X\"* into *\"the results prove X\"*: this manufactures\n  over-claiming. Keep the calibrated verb.\n- **Passive voice** is fine when the actor is irrelevant: *\"Samples were normalized to total protein.\"*\n- **First-person plural \"we\"** is standard; do not rewrite to avoid it.\n- **Semicolons and an occasional triple** are fine in moderation. Em-dashes are the exception: remove\n  them entirely (Layer 1), recasting with commas, colons, parentheses, or separate sentences.\n- **Formal definitions, named methods\u002Fmetrics, technical terms, equations, and symbols** stay verbatim.\n- **Never invent, drop, or alter a number, equation, or citation.** Same content; preserve every cite key.\n\n---\n\n## Layer 4: Claim-evidence discipline\nFor every empirical claim, check (a) is it backed by a number, figure, table, or citation in the text,\nand (b) does the verb match the strength of that evidence?\n\n- **Unbacked claim -> add the evidence pointer or soften.**\n  *Before:* *Our method is more robust.*  *After:* *Our method's accuracy drops by 2 points under\n  distribution shift, versus 11 points for the baseline (Figure 3).*\n- **Verb stronger than evidence -> downgrade.**\n  *Before:* *This demonstrates that our method is universally superior.*\n  *After:* *On these three datasets, our method matches or exceeds the strongest baseline (Table 2).*\n- **Vague magnitude -> a number or RANGE, attributed.**\n  *Before:* *a large improvement.*  *After:* *a 2--6% improvement in balanced accuracy over the strongest\n  baseline.*\n  Prefer ranges (e.g., \"2--6%\") over single averaged values unless the averaging method is stated, and\n  attribute each number to its method, metric, and baseline. When comparing, lead with the comparison\n  against the strongest competitor, not the trivial baseline.\n\n---\n\n## Layer 5: Voice and venue matching\nIf the author supplies prior papers, read a sample first and note sentence rhythm, connective habits,\nlevel and placement of hedging, how they open sections, notation, and recurring phrasings, then match\nthem. Match the venue's register too (e.g., ICLR\u002FNeurIPS: terse, direct, results-forward; Nature\u002FPNAS:\nmore expository). Absent a sample, default to clean, precise, venue-appropriate prose, not the casual,\nopinionated voice of a general-purpose humanizer.\n\n## Layer 6: Funding-proposal mode (NSF, NIH)\nA proposal is not a paper. It is sold on **vision plus feasibility**, not on finished results, and\nreviewers score it. The register shift matters: ambition language that the paper layers would trim\n(\"long-term goal\", \"pioneer\", \"transformative\", \"establish a foundation\") is *appropriate and expected*\nhere, provided a credible plan and evidence back it. So in proposal mode, **do not flatten the vision**;\nenforce a different discipline instead: **claim \u003C-> feasibility**.\n\n### 6.1 Know the structure; the score lives in the first pages\nReviewers form a score from the opening, then skim the rest to confirm it. Put most editing effort there.\n- **NSF.** A one-page **Project Summary** with the three review-criteria heads spelled out:\n  **Overview**, **Intellectual Merit**, **Broader Impacts**, each self-contained. The Project\n  Description then opens with **long-term vision -> this proposal's goal -> the gap -> the specific\n  thrusts\u002Faims -> the payoff**, ideally within the first 1--2 pages, with one overview figure. Broader\n  Impacts must be substantive and integrated, never an afterthought.\n- **NIH (R01).** The **Specific Aims page is the whole proposal in one page**, and is the most-read,\n  most-decisive page. Standard arc: (1) opening: the problem, what is known, the **gap \u002F critical need**;\n  (2) the **long-term goal** and the **central hypothesis** with its rationale; (3) \"**The objective of\n  this application is...**\" plus how the hypothesis was formed; (4) **2--3 Aims**, each a one-line goal +\n  a phrase on approach + the expected outcome; (5) a **payoff** paragraph: what changes if it succeeds.\n  Then **Significance, Innovation, Approach** as separately scored sections.\n\n### 6.2 First-3-pages primacy (edit these hardest)\nBy the end of page 1 (NIH Aims) or pages ~2--3 (NSF), the reader must already hold: the **hook** (why it\nmatters, concretely), the **gap** (what is missing and the cost of the gap), the **central idea** (your\napproach in one sentence), the **aims\u002Fthrusts** (crisp and parallel), and the **payoff**. If any is\nmissing or buried, fix that before touching later sections. A reviewer unconvinced by page 3 does not\nrecover on page 10.\n\n### 6.3 Proposal-specific weak moves to fix\n- **Vague importance.** *Watch:* \"this is an important\u002Ftimely problem\", \"X has many applications\".\n  **Before:** *Understanding this problem is critically important.*\n  **After:** *Without bounds on how measurement noise propagates to diagnosis, clinical models are tuned by\n  trial and error, the inefficiency this proposal removes.*\n- **Method-as-aim** (an aim naming a technique instead of a question or outcome).\n  **Before:** *Aim 2: Apply transfer learning to the dataset.*\n  **After:** *Aim 2: Determine whether fusing wearable and lab signals improves early detection, and for\n  which patient subgroups it helps or hurts.*\n- **Dominoed aims** (Aim 2\u002F3 collapse if Aim 1 fails; reviewers flag this as fragile). *Fix:* phrase\n  aims as **parallel and independently valuable**; where one depends on another, state the fallback.\n- **Ambition without feasibility.** Every bold claim needs a footing: preliminary data, a prior\n  result\u002Fpublication, a classical theorem you build on, or a collaborator\u002Fletter. *Fix:* attach the\n  evidence beside the claim (\"our preliminary result in Fig. X shows...\", \"building on a classical minimax\n  lower bound...\").\n- **Boilerplate Broader Impacts \u002F training plan.** *Watch:* \"we will mentor students and disseminate via\n  talks and papers.\" *Fix:* make it concrete, enumerated, and tied to the research: specific programs,\n  named courses or tools, measurable outreach.\n- **Hedged central hypothesis.** The Aims-page hypothesis is a falsifiable commitment, not \"we will\n  explore whether possibly...\". Calibrated hedging belongs in the Approach's interpretation, not the\n  central claim.\n\n### 6.4 Preserve and deploy (funded-proposal craft)\nThese read as strength; keep or add them rather than editing them out.\n- **Vision\u002Fambition framing**: a bold long-term goal up front, with this proposal as one principled step\n  toward it.\n- **Run-in lead-ins for scannability**: bold\u002Fitalic **Goal:**, **Motivation:**, **Innovation:**,\n  *Thrust\u002FAim N (one-line mission):*. Reviewers skim; visible structure earns time.\n- **A concrete running example or protagonist** to make an abstract method vivid and consistent across aims.\n- **Sharp challenge\u002Faim statements posed as questions**: a crisp open question reads as a well-posed\n  problem (a boxed or set-off question per aim works well).\n- **Anchoring novel work in deep, named classical results** to signal rigor and lineage: a known\n  inequality, capacity notion, or test that the new method generalizes.\n- **Foreground the team's standing as feasibility evidence**: prior funded work, preliminary results,\n  publications, collaborators, and demonstration partners belong *early*, as proof the plan is executable.\n  A real track record is evidence, not boasting; place it where it de-risks the aims. *(Use only the PI's\n  own real, supplied record; never invent funding, results, partners, or letters.)*\n\n### 6.5 Claim \u003C-> feasibility (the proposal analog of Layer 4)\nFor every aim and promised outcome, check: is the ambition matched by a credible means, such as\npreliminary data, a prior method, a classical foundation, a collaborator, or staged de-risking? If yes,\nkeep the ambitious verb. If no, attach the missing evidence or scale the claim to what the plan supports.\nNever invent preliminary results, prior funding, partners, or letters; if the support does not exist, flag\nthe gap for the author rather than papering over it.\n\n---\n\n## Output\nReturn the cleaned text plus a short change report: patterns removed (by type), claims softened or given\nevidence pointers, and any voice\u002Fvenue notes. Confirm that no number, equation, or citation was altered.\n",{"name":5,"license":15,"version":25,"description":7,"allowed-tools":26,"compatibility":33},"0.3.3",[27,28,29,30,31,32],"Read","Write","Edit","Grep","Glob","AskUserQuestion","claude-code codex morphmind opencode","master","fd76f882a04e445e899d5cfb2732f2105ea054ee","skills\u002Fawesome-skills\u002Facademic-humanizer",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill academic-humanizer",{"tool":50,"command":51},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill academic-humanizer",{"tool":53,"command":54},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill academic-humanizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Facademic-humanizer\u002FSKILL.md",true,[58,62],{"path":59,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":16},"LICENSE","许可证",890,{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"README.md","REFERENCE","参考文档",6205,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Facademic-humanizer\u002FREADME.md",[69,77,84,91,98,105],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":76},"01M7DXW9N826PKXK174PVW3038","serpmaven","Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fserpmaven\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"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":76},"01M7DXVHSTWDV65475QEQ915M7","revnu-landing-page-audit","Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: \"audit my landing page\", \"why isn't this page converting\", \"review my homepage\", \"my ads get clicks but no signups\", \"people bounce from the pricing page\", \"CRO review\", \"improve conversion rate\", \"is my hero section clear\", \"roast my landing page\", \"rewrite my headline\", \"what's wrong with this page\", \"landing page feedback\", \"make the signup page convert better\". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-landing-page-audit\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":76},"01M7DXV8X2D7B3VTD4HHYYHTGR","revnu-growth-context","Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents\u002Frevnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says \"set up our marketing context\", \"who is our ideal customer\", \"write our ICP\", \"describe the product for marketing\", \"positioning doc\", \"what's our brand voice\", \"remember this about our customers\", \"log what we tried\", \"what have we learned from marketing\", \"we changed pricing, update the context\", \"update our growth notes\", \"summarize the business for the agent\", \"import my product-marketing.md\", \"start a growth doc\", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-growth-context\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":76},"01M7DXV0DGJ1G0A60PAHC6J3C5","revnu-get-listed","Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: \"best X\" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says \"get us listed\", \"which directories should we submit to\", \"how do we get into best-of lists\", \"why does ChatGPT recommend competitors and not us\", \"get mentioned in AI answers\", \"submit to awesome lists\", \"get on G2\", \"where are our competitors listed\", \"pitch listicle authors\", \"find backlink opportunities\", \"launch directories\", \"get into roundups\", \"Product Hunt alternatives\", \"where should we be listed\", \"get cited by Perplexity\". Never submits, pays or posts without a yes. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-get-listed\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":76},"01M7DXTSPMGT9D6DSS0HP9BSTA","revnu-ai-readiness-audit","Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks \"is my site ready for AI search\", \"audit my site for AI answers\", \"AEO audit\", \"GEO audit\", \"why doesn't ChatGPT quote our pricing\", \"make our pages citable by AI\", \"do I need llms.txt\", \"does schema help with ChatGPT\", \"check our structured data\", \"is our content visible without JavaScript\", \"AI SEO audit\", \"optimize our homepage for AI answers\", \"LLM SEO check\", \"why does AI get our product wrong\", \"fix our site for AI Overviews\". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-ai-readiness-audit\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":76},"01M7DXSZHCVTRS620GC3S97JZV","proxy-troubleshooting","Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fproxy-troubleshooting\u002FSKILL.md",[],[]]