{"id":"ec3b7547-bb77-421c-8b98-0510ab4ea849","entityType":"agent","slug":"clawhub-figpad-academic-writing-polisher","name":"Academic Writing Polisher","canonicalUrl":"https://www.xpersona.co/agent/clawhub-figpad-academic-writing-polisher","canonicalPath":"/agent/clawhub-figpad-academic-writing-polisher","generatedAt":"2026-10-14T21:01:22.871Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-12T00:10:49.066Z","emptyReason":null},"description":"Use when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or ed... Skill: Academic Writing Polisher Owner: figpad Summary: Use when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or ed... Tags: academic-writing:1.0.1, latest:1.0.1, nature-inspired:1.0.1, paper-polishing:1.0.1, peer-review:1.0.1, research-writing:1.0.1 Version history: v1.0.1 | 2026-06-09T07:03:51.494Z | user Add ClawHub i","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 970 downloads reported by the source. Last updated 10/12/2026.","installCommand":"clawhub skill install s17510watqy1c8md11evy21qp988bwyq:academic-writing-polisher","sourceUrl":"https://clawhub.ai/figpad/academic-writing-polisher","homepage":"https://clawhub.ai/figpad/skills/academic-writing-polisher","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/figpad/academic-writing-polisher","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/figpad/skills/academic-writing-polisher","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or ed..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:10:49.066Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:10:49.066Z","emptyReason":null},"stars":null,"forks":null,"downloads":970,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.1","tractionLabel":"970 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:10:49.053Z","emptyReason":null},"lastUpdatedAt":"2026-10-12T00:10:49.066Z","lastCrawledAt":"2026-10-12T00:10:49.053Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-13T00:10:49.053Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.1","createdAt":"2026-06-09T07:03:51.494Z","changelog":"Add ClawHub install link","fileCount":7,"zipByteSize":8532},{"version":"1.0.0","createdAt":"2026-06-09T07:02:20.175Z","changelog":"Initial release","fileCount":7,"zipByteSize":8410}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17510watqy1c8md11evy21qp988bwyq:academic-writing-polisher","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-figpad-academic-writing-polisher/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-figpad-academic-writing-polisher/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-figpad-academic-writing-polisher/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-figpad-academic-writing-polisher/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-figpad-academic-writing-polisher/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-figpad-academic-writing-polisher/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-14T21:01:22.870Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-figpad-academic-writing-polisher/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-figpad-academic-writing-polisher/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-figpad-academic-writing-polisher/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-figpad-academic-writing-polisher/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-12T00:10:49.066Z","emptyReason":null},"readme":"Skill: Academic Writing Polisher\n\nOwner: figpad\n\nSummary: Use when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or ed...\n\nTags: academic-writing:1.0.1, latest:1.0.1, nature-inspired:1.0.1, paper-polishing:1.0.1, peer-review:1.0.1, research-writing:1.0.1\n\nVersion history:\n\nv1.0.1 | 2026-06-09T07:03:51.494Z | user\n\nAdd ClawHub install link\n\nv1.0.0 | 2026-06-09T07:02:20.175Z | user\n\nInitial release\n\nArchive index:\n\nArchive v1.0.1: 7 files, 8532 bytes\n\nFiles: LICENSE (901b), README.md (2985b), references/examples.md (1917b), references/prompt-patterns.md (2324b), skill-card.md (2340b), SKILL.md (5309b), _meta.json (144b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: academic-writing-polisher\ndescription: Use when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or editorial feedback. Revises for clarity, coherence, concision, and journal-ready tone while preserving author intent, avoiding invented claims or citations, and flagging ambiguity or meaning risks.\nversion: 1.0.0\nmetadata:\n  openclaw:\n    emoji: \"✍️\"\n    homepage: https://github.com/Figpad/academic-writing-polisher\n---\n\n# Academic Writing Polisher\n\nUse this skill to polish academic writing responsibly. The goal is not to write the paper for the user. The goal is to help the user express their own research meaning more clearly, coherently, concisely, and professionally.\n\nThis workflow is inspired by context-first academic writing practices discussed in Dritjon Gruda's Nature Career Column, \"Three ways ChatGPT helps me in my academic writing\" (2024), DOI: `10.1038/d41586-024-01042-3`.\n\n## When To Use\n\nUse this skill when the user asks to:\n\n- Polish, revise, or improve academic writing.\n- Improve clarity, coherence, concision, flow, or journal-ready tone.\n- Rewrite an abstract, paragraph, introduction, discussion, limitation, or conclusion.\n- Draft or refine responses to reviewers.\n- Organize peer-review comments or editorial feedback.\n- Improve academic English while preserving the user's meaning.\n\nDo not use this skill for literature review, citation discovery, data analysis, journal selection, or generating new scientific claims unless the user separately asks for that workflow.\n\n## Core Rule\n\nNever silently add intellectual content. Do not invent claims, mechanisms, citations, results, limitations, methods, implications, or author intent.\n\nIf meaning is unclear, flag the ambiguity and offer a conservative revision.\n\n## Context First\n\nBefore revising, collect missing context when it materially affects the edit. Ask only the questions needed for the current passage.\n\nUseful context:\n\n- Field or discipline.\n- Document type: paper, thesis, abstract, rebuttal, review, editorial letter.\n- Target audience or journal level.\n- Section role: introduction, method, results, discussion, limitation, response to reviewer.\n- Intended meaning in plain language.\n- Desired edit strength: light polish, moderate rewrite, heavy restructure.\n- Tone: concise, formal, direct, diplomatic, assertive, cautious.\n- Terms, phrases, citations, or claims that must stay unchanged.\n\nIf the user already supplied enough context, proceed without asking.\n\n## Revision Modes\n\nChoose the smallest mode that solves the task:\n\n- `Light polish`: grammar, word choice, flow, and academic tone.\n- `Clarity rewrite`: restructures sentences to make the intended meaning easier to follow.\n- `Concision`: removes repetition, filler, and unnecessary hedging.\n- `Coherence`: improves paragraph order, transitions, and logical flow.\n- `Reviewer response`: makes responses specific, respectful, and action-oriented.\n- `Peer-review feedback`: organizes the user's notes into clear review comments without uploading or exposing confidential manuscript text beyond what the user provided.\n- `Editorial feedback`: turns decision notes into direct, respectful, actionable letters.\n\n## Output Format\n\nFor most polishing tasks, return:\n\n```markdown\n**Polished Version**\n[revised text]\n\n**What Changed**\n- [brief explanation of major edits]\n\n**Meaning Check**\n- Preserved: [key meaning preserved]\n- Please verify: [any assumption or ambiguous point]\n\n**Risk Flags**\n- [invented-claim/citation/overstatement/ambiguity risks, or \"None noticed\"]\n```\n\nFor very short requests, you may omit headings if a concise answer is better, but still preserve meaning and flag risks.\n\n## Style Principles\n\n- Prefer clear academic prose over ornate phrasing.\n- Preserve field-specific terminology unless the user asks to simplify jargon.\n- Keep claims calibrated: \"suggests\", \"may\", \"is associated with\", and \"demonstrates\" are not interchangeable.\n- Keep citations exactly as provided.\n- Keep statistical values, gene/protein names, chemical names, model names, and labels unchanged unless the user asks otherwise.\n- Do not make the text sound more certain than the evidence supports.\n- Avoid generic filler such as \"plays a crucial role\" unless the user's field and sentence require it.\n\n## Reviewer Response Rules\n\nWhen revising responses to reviewers:\n\n- Start by acknowledging the reviewer's point.\n- State what was changed, where it was changed, and why.\n- If disagreeing, be respectful and evidence-based.\n- Do not claim that a change was made unless the user says it was made.\n- Separate \"response text\" from \"manuscript revision text\" when both are requested.\n\n## Peer Review And Editorial Rules\n\nWhen helping with peer review or editorial feedback:\n\n- Work from the user's summary, notes, and judgments.\n- Do not pretend to have read a manuscript that was not provided.\n- Do not create confidential details.\n- Organize limitations by importance when asked.\n- Make feedback specific, constructive, and professional.\n\n## Reference Templates\n\nIf the user needs reusable prompts or examples, read:\n\n- `references/prompt-patterns.md` for reusable task prompts.\n- `references/examples.md` for before/after examples and launch copy.\n\nFile v1.0.1:README.md\n\n# Academic Writing Polisher\n\nA context-first academic writing Skill for researchers who need clearer, more coherent, journal-ready text without losing author intent.\n\nInspired by Dritjon Gruda's Nature Career Column, \"Three ways ChatGPT helps me in my academic writing,\" this Skill turns responsible academic revision into an installable Agent workflow: ask for context first, revise second, and always flag meaning risks.\n\n## What It Helps With\n\n- Polish research paragraphs for clarity, coherence, concision, and academic tone.\n- Improve abstracts, introductions, discussions, limitations, and conclusions.\n- Refine reviewer responses without sounding defensive or vague.\n- Organize peer-review comments and editorial feedback.\n- Preserve the author's intended meaning while avoiding invented claims or citations.\n\n## Why This Skill Exists\n\nGeneric AI polishing often changes too much: it can add unsupported claims, overstate findings, flatten disciplinary nuance, or silently change what the author meant.\n\nThis Skill gives the Agent a stricter academic writing workflow:\n\n1. Collect the research context.\n2. Revise only for the requested purpose.\n3. Preserve citations, claims, and technical terms.\n4. Explain what changed.\n5. Flag ambiguity, overstatement, or meaning risks.\n\n## Install\n\nInstall from ClawHub:\n\n```bash\nclawhub install academic-writing-polisher\n```\n\nIf you use OpenClaw:\n\n```bash\nopenclaw skills install academic-writing-polisher\n```\n\nClawHub page: [academic-writing-polisher](https://clawhub.ai/skills/academic-writing-polisher)\n\nIf installing from this repository manually, copy the Skill folder into your local skills directory:\n\n```bash\ncp -R academic-writing-polisher ~/.codex/skills/\n```\n\n## Example Prompts\n\n```text\nPolish this paragraph for clarity and journal-ready academic tone. Preserve all claims and citations.\n```\n\n```text\nI am writing a discussion section for a biomedical paper. I want this paragraph to sound more concise and coherent without overstating the findings.\n```\n\n```text\nRevise this response to Reviewer 2. Keep it respectful, specific, and clear about what we changed.\n```\n\n## Output Shape\n\nThe Skill normally returns:\n\n- Polished Version\n- What Changed\n- Meaning Check\n- Risk Flags\n\nThis makes the revision auditable instead of a black-box rewrite.\n\n## Search Keywords\n\nacademic writing, research writing, paper polishing, Nature-inspired, ChatGPT academic writing, reviewer response, peer review, editorial feedback, journal-ready tone, clarity, coherence, concision, author intent\n\n## Source Inspiration\n\nGruda, D. (2024). \"Three ways ChatGPT helps me in my academic writing.\" Nature. DOI: [10.1038/d41586-024-01042-3](https://doi.org/10.1038/d41586-024-01042-3)\n\nThis Skill is not affiliated with or endorsed by Nature, Springer Nature, or the article author.\n\n## By Figpad\n\nCreated by [Figpad](https://github.com/Figpad), makers of [Figpad AI](https://figpad.ai), an AI-powered scientific illustration platform for researchers.\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7f24n4q86k9d3zcct1jh87nh88afef\",\n  \"slug\": \"academic-writing-polisher\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1780988631494\n}\n\nFile v1.0.1:references/examples.md\n\n# Examples\n\n## Paragraph Polish\n\nUser context:\n\n```text\nField: biomedical research\nSection: discussion\nIntent: The treatment may improve outcomes, but our data are observational, so we should avoid causal language.\nEdit strength: moderate rewrite\n```\n\nDraft:\n\n```text\nThese results prove that the treatment improves patient survival and should be used broadly in clinical settings.\n```\n\nBetter revision:\n\n```text\nThese findings suggest that the treatment is associated with improved patient survival, although the observational design prevents causal interpretation. Further prospective studies are needed before broad clinical adoption can be recommended.\n```\n\nMeaning risk:\n\n```text\nThe original \"prove\" was too strong for observational data. The revision keeps the positive association but lowers the certainty.\n```\n\n## Reviewer Response\n\nReviewer comment:\n\n```text\nThe authors should clarify how missing values were handled.\n```\n\nUser notes:\n\n```text\nWe added a sentence to Methods, page 6, lines 120-123. We used multiple imputation with 20 datasets.\n```\n\nResponse:\n\n```text\nThank you for this helpful suggestion. We have clarified the handling of missing values in the Methods section (page 6, lines 120-123). Specifically, we now state that missing covariate values were handled using multiple imputation with 20 imputed datasets.\n```\n\n## Launch Copy\n\nShort social post:\n\n```text\nI turned a context-first academic writing workflow into an installable Agent Skill.\n\nIt helps researchers polish paragraphs, abstracts, and reviewer responses without inventing claims or silently changing the author's meaning.\n\nThe Agent asks for context first, revises second, and always outputs a meaning-risk check.\n```\n\nGitHub repository description:\n\n```text\nNature-inspired academic writing Skill for polishing research paragraphs, abstracts, reviewer responses, and peer-review feedback while preserving author intent.\n```\n\nFile v1.0.1:references/prompt-patterns.md\n\n# Prompt Patterns\n\nUse these patterns when the user asks for reusable prompts or wants to adapt the workflow.\n\n## Research Paragraph Polish\n\n```text\nI am writing a paper on [topic] for a [field] academic audience.\nThis paragraph appears in the [section].\nMy intended meaning is: [plain-language meaning].\nPlease revise the text for clarity, coherence, concision, and professional academic tone.\nPreserve all claims, citations, technical terms, and uncertainty levels.\nDo not add new claims or references.\nFlag any sentence whose meaning is ambiguous.\n\nText:\n[paste text]\n```\n\n## Abstract Polish\n\n```text\nI am revising an abstract for a [field] paper.\nThe study's core contribution is: [contribution].\nThe target tone is concise, concrete, and journal-ready.\nPlease improve flow and readability without changing the claims, results, methods, or implications.\nFlag any sentence that sounds overstated or underspecified.\n\nAbstract:\n[paste abstract]\n```\n\n## Discussion Section\n\n```text\nI am revising the discussion section of a [field] paper.\nThe key finding is: [finding].\nThe evidence supports: [supported interpretation].\nThe evidence does not support: [boundary].\nPlease improve clarity and logical flow while keeping claims appropriately cautious.\n\nText:\n[paste text]\n```\n\n## Reviewer Response\n\n```text\nI am responding to a reviewer comment.\nReviewer comment:\n[paste comment]\n\nWhat we changed:\n[state actual change]\n\nWhat we did not change, if relevant:\n[state boundary]\n\nPlease draft a respectful, specific response.\nDo not claim that we changed something unless it appears in my notes.\nSeparate the response to the reviewer from any suggested manuscript wording.\n```\n\n## Peer Review Notes\n\n```text\nI have read a manuscript and wrote the following review notes.\nPlease organize them into a concise, professional peer-review report.\nFirst summarize the manuscript's core contribution, then list major concerns in order of importance, then minor comments.\nDo not invent details beyond my notes.\n\nNotes:\n[paste notes]\n```\n\n## Editorial Feedback\n\n```text\nI am preparing editorial feedback based on my decision notes.\nPlease draft a direct, respectful, and actionable letter.\nMake the key reason for the decision clear.\nAvoid vague phrases and do not add criticisms that are not in my notes.\n\nDecision notes:\n[paste notes]\n```\n\nFile v1.0.1:skill-card.md\n\n## Description:\n\nUse when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or editorial feedback while preserving author intent, avoiding invented claims or citations, and flagging ambiguity or meaning risks.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[figpad](https://clawhub.ai/user/figpad)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nResearchers and academic authors use this skill to polish user-provided scholarly text for clarity, coherence, concision, and professional tone. It is also used to refine reviewer responses and organize peer-review or editorial feedback without inventing claims, citations, or manuscript details.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users may paste confidential manuscript or review material into the agent workflow.\n\nMitigation: Use the skill only with text that the user's normal agent workflow is allowed to process, and avoid sharing confidential manuscript material unless permitted.\n\nRisk: Academic polishing can unintentionally change meaning, certainty, citations, or author intent.\n\nMitigation: Review the polished output, meaning check, and risk flags before using the text in scholarly or publication workflows.\n\n## Reference(s):\n\n- [Academic Writing Polisher on ClawHub](https://clawhub.ai/figpad/skills/academic-writing-polisher)\n- [Homepage](https://github.com/Figpad/academic-writing-polisher)\n- [Source Inspiration: Nature Career Column](https://doi.org/10.1038/d41586-024-01042-3)\n- [Prompt Patterns](references/prompt-patterns.md)\n- [Examples](references/examples.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown with revised text, change notes, meaning checks, and risk flags]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Works on user-provided academic text and may ask for context before revising.]\n\n## Skill Version(s):\n\n1.0.1 (source: ClawHub release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.1:LICENSE\n\nMIT No Attribution\n\nCopyright 2026 Figpad\n\nPermission is hereby granted, free of charge, to any person obtaining a copy of this\nsoftware and associated documentation files (the \"Software\"), to deal in the Software\nwithout restriction, including without limitation the rights to use, copy, modify,\nmerge, publish, distribute, sublicense, and/or sell copies of the Software, and to\npermit persons to whom the Software is furnished to do so.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,\nINCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A\nPARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT\nHOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF\nCONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE\nOR THE USE OR OTHER DEALINGS IN THE SOFTWARE.\n\nArchive v1.0.0: 7 files, 8410 bytes\n\nFiles: LICENSE (901b), README.md (2831b), references/examples.md (1917b), references/prompt-patterns.md (2324b), skill-card.md (2263b), SKILL.md (5309b), _meta.json (144b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: academic-writing-polisher\ndescription: Use when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or editorial feedback. Revises for clarity, coherence, concision, and journal-ready tone while preserving author intent, avoiding invented claims or citations, and flagging ambiguity or meaning risks.\nversion: 1.0.0\nmetadata:\n  openclaw:\n    emoji: \"✍️\"\n    homepage: https://github.com/Figpad/academic-writing-polisher\n---\n\n# Academic Writing Polisher\n\nUse this skill to polish academic writing responsibly. The goal is not to write the paper for the user. The goal is to help the user express their own research meaning more clearly, coherently, concisely, and professionally.\n\nThis workflow is inspired by context-first academic writing practices discussed in Dritjon Gruda's Nature Career Column, \"Three ways ChatGPT helps me in my academic writing\" (2024), DOI: `10.1038/d41586-024-01042-3`.\n\n## When To Use\n\nUse this skill when the user asks to:\n\n- Polish, revise, or improve academic writing.\n- Improve clarity, coherence, concision, flow, or journal-ready tone.\n- Rewrite an abstract, paragraph, introduction, discussion, limitation, or conclusion.\n- Draft or refine responses to reviewers.\n- Organize peer-review comments or editorial feedback.\n- Improve academic English while preserving the user's meaning.\n\nDo not use this skill for literature review, citation discovery, data analysis, journal selection, or generating new scientific claims unless the user separately asks for that workflow.\n\n## Core Rule\n\nNever silently add intellectual content. Do not invent claims, mechanisms, citations, results, limitations, methods, implications, or author intent.\n\nIf meaning is unclear, flag the ambiguity and offer a conservative revision.\n\n## Context First\n\nBefore revising, collect missing context when it materially affects the edit. Ask only the questions needed for the current passage.\n\nUseful context:\n\n- Field or discipline.\n- Document type: paper, thesis, abstract, rebuttal, review, editorial letter.\n- Target audience or journal level.\n- Section role: introduction, method, results, discussion, limitation, response to reviewer.\n- Intended meaning in plain language.\n- Desired edit strength: light polish, moderate rewrite, heavy restructure.\n- Tone: concise, formal, direct, diplomatic, assertive, cautious.\n- Terms, phrases, citations, or claims that must stay unchanged.\n\nIf the user already supplied enough context, proceed without asking.\n\n## Revision Modes\n\nChoose the smallest mode that solves the task:\n\n- `Light polish`: grammar, word choice, flow, and academic tone.\n- `Clarity rewrite`: restructures sentences to make the intended meaning easier to follow.\n- `Concision`: removes repetition, filler, and unnecessary hedging.\n- `Coherence`: improves paragraph order, transitions, and logical flow.\n- `Reviewer response`: makes responses specific, respectful, and action-oriented.\n- `Peer-review feedback`: organizes the user's notes into clear review comments without uploading or exposing confidential manuscript text beyond what the user provided.\n- `Editorial feedback`: turns decision notes into direct, respectful, actionable letters.\n\n## Output Format\n\nFor most polishing tasks, return:\n\n```markdown\n**Polished Version**\n[revised text]\n\n**What Changed**\n- [brief explanation of major edits]\n\n**Meaning Check**\n- Preserved: [key meaning preserved]\n- Please verify: [any assumption or ambiguous point]\n\n**Risk Flags**\n- [invented-claim/citation/overstatement/ambiguity risks, or \"None noticed\"]\n```\n\nFor very short requests, you may omit headings if a concise answer is better, but still preserve meaning and flag risks.\n\n## Style Principles\n\n- Prefer clear academic prose over ornate phrasing.\n- Preserve field-specific terminology unless the user asks to simplify jargon.\n- Keep claims calibrated: \"suggests\", \"may\", \"is associated with\", and \"demonstrates\" are not interchangeable.\n- Keep citations exactly as provided.\n- Keep statistical values, gene/protein names, chemical names, model names, and labels unchanged unless the user asks otherwise.\n- Do not make the text sound more certain than the evidence supports.\n- Avoid generic filler such as \"plays a crucial role\" unless the user's field and sentence require it.\n\n## Reviewer Response Rules\n\nWhen revising responses to reviewers:\n\n- Start by acknowledging the reviewer's point.\n- State what was changed, where it was changed, and why.\n- If disagreeing, be respectful and evidence-based.\n- Do not claim that a change was made unless the user says it was made.\n- Separate \"response text\" from \"manuscript revision text\" when both are requested.\n\n## Peer Review And Editorial Rules\n\nWhen helping with peer review or editorial feedback:\n\n- Work from the user's summary, notes, and judgments.\n- Do not pretend to have read a manuscript that was not provided.\n- Do not create confidential details.\n- Organize limitations by importance when asked.\n- Make feedback specific, constructive, and professional.\n\n## Reference Templates\n\nIf the user needs reusable prompts or examples, read:\n\n- `references/prompt-patterns.md` for reusable task prompts.\n- `references/examples.md` for before/after examples and launch copy.\n\nFile v1.0.0:README.md\n\n# Academic Writing Polisher\n\nA context-first academic writing Skill for researchers who need clearer, more coherent, journal-ready text without losing author intent.\n\nInspired by Dritjon Gruda's Nature Career Column, \"Three ways ChatGPT helps me in my academic writing,\" this Skill turns responsible academic revision into an installable Agent workflow: ask for context first, revise second, and always flag meaning risks.\n\n## What It Helps With\n\n- Polish research paragraphs for clarity, coherence, concision, and academic tone.\n- Improve abstracts, introductions, discussions, limitations, and conclusions.\n- Refine reviewer responses without sounding defensive or vague.\n- Organize peer-review comments and editorial feedback.\n- Preserve the author's intended meaning while avoiding invented claims or citations.\n\n## Why This Skill Exists\n\nGeneric AI polishing often changes too much: it can add unsupported claims, overstate findings, flatten disciplinary nuance, or silently change what the author meant.\n\nThis Skill gives the Agent a stricter academic writing workflow:\n\n1. Collect the research context.\n2. Revise only for the requested purpose.\n3. Preserve citations, claims, and technical terms.\n4. Explain what changed.\n5. Flag ambiguity, overstatement, or meaning risks.\n\n## Install\n\nAfter the Skill is published on ClawHub:\n\n```bash\nopenclaw skills install academic-writing-polisher\n```\n\nIf installing from this repository manually, copy the Skill folder into your local skills directory:\n\n```bash\ncp -R academic-writing-polisher ~/.codex/skills/\n```\n\n## Example Prompts\n\n```text\nPolish this paragraph for clarity and journal-ready academic tone. Preserve all claims and citations.\n```\n\n```text\nI am writing a discussion section for a biomedical paper. I want this paragraph to sound more concise and coherent without overstating the findings.\n```\n\n```text\nRevise this response to Reviewer 2. Keep it respectful, specific, and clear about what we changed.\n```\n\n## Output Shape\n\nThe Skill normally returns:\n\n- Polished Version\n- What Changed\n- Meaning Check\n- Risk Flags\n\nThis makes the revision auditable instead of a black-box rewrite.\n\n## Search Keywords\n\nacademic writing, research writing, paper polishing, Nature-inspired, ChatGPT academic writing, reviewer response, peer review, editorial feedback, journal-ready tone, clarity, coherence, concision, author intent\n\n## Source Inspiration\n\nGruda, D. (2024). \"Three ways ChatGPT helps me in my academic writing.\" Nature. DOI: [10.1038/d41586-024-01042-3](https://doi.org/10.1038/d41586-024-01042-3)\n\nThis Skill is not affiliated with or endorsed by Nature, Springer Nature, or the article author.\n\n## By Figpad\n\nCreated by [Figpad](https://github.com/Figpad), makers of [Figpad AI](https://figpad.ai), an AI-powered scientific illustration platform for researchers.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7f24n4q86k9d3zcct1jh87nh88afef\",\n  \"slug\": \"academic-writing-polisher\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1780988540175\n}\n\nFile v1.0.0:references/examples.md\n\n# Examples\n\n## Paragraph Polish\n\nUser context:\n\n```text\nField: biomedical research\nSection: discussion\nIntent: The treatment may improve outcomes, but our data are observational, so we should avoid causal language.\nEdit strength: moderate rewrite\n```\n\nDraft:\n\n```text\nThese results prove that the treatment improves patient survival and should be used broadly in clinical settings.\n```\n\nBetter revision:\n\n```text\nThese findings suggest that the treatment is associated with improved patient survival, although the observational design prevents causal interpretation. Further prospective studies are needed before broad clinical adoption can be recommended.\n```\n\nMeaning risk:\n\n```text\nThe original \"prove\" was too strong for observational data. The revision keeps the positive association but lowers the certainty.\n```\n\n## Reviewer Response\n\nReviewer comment:\n\n```text\nThe authors should clarify how missing values were handled.\n```\n\nUser notes:\n\n```text\nWe added a sentence to Methods, page 6, lines 120-123. We used multiple imputation with 20 datasets.\n```\n\nResponse:\n\n```text\nThank you for this helpful suggestion. We have clarified the handling of missing values in the Methods section (page 6, lines 120-123). Specifically, we now state that missing covariate values were handled using multiple imputation with 20 imputed datasets.\n```\n\n## Launch Copy\n\nShort social post:\n\n```text\nI turned a context-first academic writing workflow into an installable Agent Skill.\n\nIt helps researchers polish paragraphs, abstracts, and reviewer responses without inventing claims or silently changing the author's meaning.\n\nThe Agent asks for context first, revises second, and always outputs a meaning-risk check.\n```\n\nGitHub repository description:\n\n```text\nNature-inspired academic writing Skill for polishing research paragraphs, abstracts, reviewer responses, and peer-review feedback while preserving author intent.\n```\n\nFile v1.0.0:references/prompt-patterns.md\n\n# Prompt Patterns\n\nUse these patterns when the user asks for reusable prompts or wants to adapt the workflow.\n\n## Research Paragraph Polish\n\n```text\nI am writing a paper on [topic] for a [field] academic audience.\nThis paragraph appears in the [section].\nMy intended meaning is: [plain-language meaning].\nPlease revise the text for clarity, coherence, concision, and professional academic tone.\nPreserve all claims, citations, technical terms, and uncertainty levels.\nDo not add new claims or references.\nFlag any sentence whose meaning is ambiguous.\n\nText:\n[paste text]\n```\n\n## Abstract Polish\n\n```text\nI am revising an abstract for a [field] paper.\nThe study's core contribution is: [contribution].\nThe target tone is concise, concrete, and journal-ready.\nPlease improve flow and readability without changing the claims, results, methods, or implications.\nFlag any sentence that sounds overstated or underspecified.\n\nAbstract:\n[paste abstract]\n```\n\n## Discussion Section\n\n```text\nI am revising the discussion section of a [field] paper.\nThe key finding is: [finding].\nThe evidence supports: [supported interpretation].\nThe evidence does not support: [boundary].\nPlease improve clarity and logical flow while keeping claims appropriately cautious.\n\nText:\n[paste text]\n```\n\n## Reviewer Response\n\n```text\nI am responding to a reviewer comment.\nReviewer comment:\n[paste comment]\n\nWhat we changed:\n[state actual change]\n\nWhat we did not change, if relevant:\n[state boundary]\n\nPlease draft a respectful, specific response.\nDo not claim that we changed something unless it appears in my notes.\nSeparate the response to the reviewer from any suggested manuscript wording.\n```\n\n## Peer Review Notes\n\n```text\nI have read a manuscript and wrote the following review notes.\nPlease organize them into a concise, professional peer-review report.\nFirst summarize the manuscript's core contribution, then list major concerns in order of importance, then minor comments.\nDo not invent details beyond my notes.\n\nNotes:\n[paste notes]\n```\n\n## Editorial Feedback\n\n```text\nI am preparing editorial feedback based on my decision notes.\nPlease draft a direct, respectful, and actionable letter.\nMake the key reason for the decision clear.\nAvoid vague phrases and do not add criticisms that are not in my notes.\n\nDecision notes:\n[paste notes]\n```\n\nFile v1.0.0:skill-card.md\n\n## Description: <br>\nUse when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or editorial feedback. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[figpad](https://clawhub.ai/user/figpad) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal researchers use this skill to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, and editorial feedback while preserving author intent and avoiding invented claims or citations. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Unpublished manuscripts, reviewer comments, or editorial notes may contain confidential material. <br>\nMitigation: Only provide text that is allowed to be processed with the user's agent and publication workflow. <br>\nRisk: Polished prose can accidentally change factual meaning, certainty, or attribution. <br>\nMitigation: Review the final text for factual accuracy, preserved citations, unchanged technical terms, and appropriate uncertainty before reuse. <br>\n\n\n## Reference(s): <br>\n- [Skill page](https://clawhub.ai/figpad/academic-writing-polisher) <br>\n- [Project homepage](https://github.com/Figpad/academic-writing-polisher) <br>\n- [Prompt patterns](references/prompt-patterns.md) <br>\n- [Examples](references/examples.md) <br>\n- [Nature Career Column DOI](https://doi.org/10.1038/d41586-024-01042-3) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Guidance] <br>\n**Output Format:** [Markdown with polished text, change notes, meaning checks, and risk flags] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Preserves user-provided claims, citations, technical terms, and uncertainty levels unless the user requests otherwise.] <br>\n\n## Skill Version(s): <br>\n1.0.0 (source: frontmatter and server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nFile v1.0.0:LICENSE\n\nMIT No Attribution\n\nCopyright 2026 Figpad\n\nPermission is hereby granted, free of charge, to any person obtaining a copy of this\nsoftware and associated documentation files (the \"Software\"), to deal in the Software\nwithout restriction, including without limitation the rights to use, copy, modify,\nmerge, publish, distribute, sublicense, and/or sell copies of the Software, and to\npermit persons to whom the Software is furnished to do so.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,\nINCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A\nPARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT\nHOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF\nCONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE\nOR THE USE OR OTHER DEALINGS IN THE SOFTWARE.","readmeExcerpt":"Skill: Academic Writing Polisher Owner: figpad Summary: Use when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or ed... Tags: academic-writing:1.0.1, latest:1.0.1, nature-inspired:1.0.1, paper-polishing:1.0.1, peer-review:1.0.1, research-writing:1.0.1 Version history: v1.0.1 | 2026-06-09T07:03:51.494Z | user Add ClawHub i","codeSnippets":[],"executableExamples":[{"language":"markdown","snippet":"**Polished Version**\n[revised text]\n\n**What Changed**\n- [brief explanation of major edits]\n\n**Meaning Check**\n- Preserved: [key meaning preserved]\n- Please verify: [any assumption or ambiguous point]\n\n**Risk Flags**\n- [invented-claim/citation/overstatement/ambiguity risks, or \"None noticed\"]"},{"language":"bash","snippet":"clawhub install academic-writing-polisher"},{"language":"bash","snippet":"openclaw skills install academic-writing-polisher"},{"language":"bash","snippet":"cp -R academic-writing-polisher ~/.codex/skills/"},{"language":"text","snippet":"Polish this paragraph for clarity and journal-ready academic tone. Preserve all claims and citations."},{"language":"text","snippet":"I am writing a discussion section for a biomedical paper. I want this paragraph to sound more concise and coherent without overstating the findings."}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: academic-writing-polisher\ndescription: Use when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or editorial feedback. Revises for clarity, coherence, concision, and journal-ready tone while preserving author intent, avoiding invented claims or citations, and flagging ambiguity or meaning risks.\nversion: 1.0.0\nmetadata:\n  openclaw:\n    emoji: \"✍️\"\n    homepage: https://github.com/Figpad/academic-writing-polisher\n---\n\n# Academic Writing Polisher\n\nUse this skill to polish academic writing responsibly. The goal is not to write the paper for the user. The goal is to help the user express their own research meaning more clearly, coherently, concisely, and professionally.\n\nThis workflow is inspired by context-first academic writing practices discussed in Dritjon Gruda's Nature Career Column, \"Three ways ChatGPT helps me in my academic writing\" (2024), DOI: `10.1038/d41586-024-01042-3`.\n\n## When To Use\n\nUse this skill when the user asks to:\n\n- Polish, revise, or improve academic writing.\n- Improve clarity, coherence, concision, flow, or journal-ready tone.\n- Rewrite an abstract, paragraph, introduction, discussion, limitation, or conclusion.\n- Draft or refine responses to reviewers.\n- Organize peer-review comments or editorial feedback.\n- Improve academic English while preserving the user's meaning.\n\nDo not use this skill for literature review, citation discovery, data analysis, journal selection, or generating new scientific claims unless the user separately asks for that workflow.\n\n## Core Rule\n\nNever silently add intellectual content. Do not invent claims, mechanisms, citations, results, limitations, methods, implications, or author intent.\n\nIf meaning is unclear, flag the ambiguity and offer a conservative revision.\n\n## Context First\n\nBefore revising, collect missing context when it materially affects the edit. Ask only the questions needed for the current passage.\n\nUseful context:\n\n- Field or discipline.\n- Document type: paper, thesis, abstract, rebuttal, review, editorial letter.\n- Target audience or journal level.\n- Section role: introduction, method, results, discussion, limitation, response to reviewer.\n- Intended meaning in plain language.\n- Desired edit strength: light polish, moderate rewrite, heavy restructure.\n- Tone: concise, formal, direct, diplomatic, assertive, cautious.\n- Terms, phrases, citations, or claims that must stay unchanged.\n\nIf the user already supplied enough context, proceed without asking.\n\n## Revision Modes\n\nChoose the smallest mode that solves the task:\n\n- `Light polish`: grammar, word choice, flow, and academic tone.\n- `Clarity rewrite`: restructures sentences to make the intended meaning easier to follow.\n- `Concision`: removes repetition, filler, and unnecessary hedging.\n- `Coherence`: improves paragraph order, transitions, and logical flow.\n- `Reviewer response`: makes responses specific, respectful, and action-o"},{"path":"README.md","content":"# Academic Writing Polisher\n\nA context-first academic writing Skill for researchers who need clearer, more coherent, journal-ready text without losing author intent.\n\nInspired by Dritjon Gruda's Nature Career Column, \"Three ways ChatGPT helps me in my academic writing,\" this Skill turns responsible academic revision into an installable Agent workflow: ask for context first, revise second, and always flag meaning risks.\n\n## What It Helps With\n\n- Polish research paragraphs for clarity, coherence, concision, and academic tone.\n- Improve abstracts, introductions, discussions, limitations, and conclusions.\n- Refine reviewer responses without sounding defensive or vague.\n- Organize peer-review comments and editorial feedback.\n- Preserve the author's intended meaning while avoiding invented claims or citations.\n\n## Why This Skill Exists\n\nGeneric AI polishing often changes too much: it can add unsupported claims, overstate findings, flatten disciplinary nuance, or silently change what the author meant.\n\nThis Skill gives the Agent a stricter academic writing workflow:\n\n1. Collect the research context.\n2. Revise only for the requested purpose.\n3. Preserve citations, claims, and technical terms.\n4. Explain what changed.\n5. Flag ambiguity, overstatement, or meaning risks.\n\n## Install\n\nInstall from ClawHub:\n\n```bash\nclawhub install academic-writing-polisher\n```\n\nIf you use OpenClaw:\n\n```bash\nopenclaw skills install academic-writing-polisher\n```\n\nClawHub page: [academic-writing-polisher](https://clawhub.ai/skills/academic-writing-polisher)\n\nIf installing from this repository manually, copy the Skill folder into your local skills directory:\n\n```bash\ncp -R academic-writing-polisher ~/.codex/skills/\n```\n\n## Example Prompts\n\n```text\nPolish this paragraph for clarity and journal-ready academic tone. Preserve all claims and citations.\n```\n\n```text\nI am writing a discussion section for a biomedical paper. I want this paragraph to sound more concise and coherent without overstating the findings.\n```\n\n```text\nRevise this response to Reviewer 2. Keep it respectful, specific, and clear about what we changed.\n```\n\n## Output Shape\n\nThe Skill normally returns:\n\n- Polished Version\n- What Changed\n- Meaning Check\n- Risk Flags\n\nThis makes the revision auditable instead of a black-box rewrite.\n\n## Search Keywords\n\nacademic writing, research writing, paper polishing, Nature-inspired, ChatGPT academic writing, reviewer response, peer review, editorial feedback, journal-ready tone, clarity, coherence, concision, author intent\n\n## Source Inspiration\n\nGruda, D. (2024). \"Three ways ChatGPT helps me in my academic writing.\" Nature. DOI: [10.1038/d41586-024-01042-3](https://doi.org/10.1038/d41586-024-01042-3)\n\nThis Skill is not affiliated with or endorsed by Nature, Springer Nature, or the article author.\n\n## By Figpad\n\nCreated by [Figpad](https://github.com/Figpad), makers of [Figpad AI](https://figpad.ai), an AI-powered scientific illustration platform for researchers."},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7f24n4q86k9d3zcct1jh87nh88afef\",\n  \"slug\": \"academic-writing-polisher\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1780988631494\n}"},{"path":"references/examples.md","content":"# Examples\n\n## Paragraph Polish\n\nUser context:\n\n```text\nField: biomedical research\nSection: discussion\nIntent: The treatment may improve outcomes, but our data are observational, so we should avoid causal language.\nEdit strength: moderate rewrite\n```\n\nDraft:\n\n```text\nThese results prove that the treatment improves patient survival and should be used broadly in clinical settings.\n```\n\nBetter revision:\n\n```text\nThese findings suggest that the treatment is associated with improved patient survival, although the observational design prevents causal interpretation. Further prospective studies are needed before broad clinical adoption can be recommended.\n```\n\nMeaning risk:\n\n```text\nThe original \"prove\" was too strong for observational data. The revision keeps the positive association but lowers the certainty.\n```\n\n## Reviewer Response\n\nReviewer comment:\n\n```text\nThe authors should clarify how missing values were handled.\n```\n\nUser notes:\n\n```text\nWe added a sentence to Methods, page 6, lines 120-123. We used multiple imputation with 20 datasets.\n```\n\nResponse:\n\n```text\nThank you for this helpful suggestion. We have clarified the handling of missing values in the Methods section (page 6, lines 120-123). Specifically, we now state that missing covariate values were handled using multiple imputation with 20 imputed datasets.\n```\n\n## Launch Copy\n\nShort social post:\n\n```text\nI turned a context-first academic writing workflow into an installable Agent Skill.\n\nIt helps researchers polish paragraphs, abstracts, and reviewer responses without inventing claims or silently changing the author's meaning.\n\nThe Agent asks for context first, revises second, and always outputs a meaning-risk check.\n```\n\nGitHub repository description:\n\n```text\nNature-inspired academic writing Skill for polishing research paragraphs, abstracts, reviewer responses, and peer-review feedback while preserving author intent.\n```"},{"path":"references/prompt-patterns.md","content":"# Prompt Patterns\n\nUse these patterns when the user asks for reusable prompts or wants to adapt the workflow.\n\n## Research Paragraph Polish\n\n```text\nI am writing a paper on [topic] for a [field] academic audience.\nThis paragraph appears in the [section].\nMy intended meaning is: [plain-language meaning].\nPlease revise the text for clarity, coherence, concision, and professional academic tone.\nPreserve all claims, citations, technical terms, and uncertainty levels.\nDo not add new claims or references.\nFlag any sentence whose meaning is ambiguous.\n\nText:\n[paste text]\n```\n\n## Abstract Polish\n\n```text\nI am revising an abstract for a [field] paper.\nThe study's core contribution is: [contribution].\nThe target tone is concise, concrete, and journal-ready.\nPlease improve flow and readability without changing the claims, results, methods, or implications.\nFlag any sentence that sounds overstated or underspecified.\n\nAbstract:\n[paste abstract]\n```\n\n## Discussion Section\n\n```text\nI am revising the discussion section of a [field] paper.\nThe key finding is: [finding].\nThe evidence supports: [supported interpretation].\nThe evidence does not support: [boundary].\nPlease improve clarity and logical flow while keeping claims appropriately cautious.\n\nText:\n[paste text]\n```\n\n## Reviewer Response\n\n```text\nI am responding to a reviewer comment.\nReviewer comment:\n[paste comment]\n\nWhat we changed:\n[state actual change]\n\nWhat we did not change, if relevant:\n[state boundary]\n\nPlease draft a respectful, specific response.\nDo not claim that we changed something unless it appears in my notes.\nSeparate the response to the reviewer from any suggested manuscript wording.\n```\n\n## Peer Review Notes\n\n```text\nI have read a manuscript and wrote the following review notes.\nPlease organize them into a concise, professional peer-review report.\nFirst summarize the manuscript's core contribution, then list major concerns in order of importance, then minor comments.\nDo not invent details beyond my notes.\n\nNotes:\n[paste notes]\n```\n\n## Editorial Feedback\n\n```text\nI am preparing editorial feedback based on my decision notes.\nPlease draft a direct, respectful, and actionable letter.\nMake the key reason for the decision clear.\nAvoid vague phrases and do not add criticisms that are not in my notes.\n\nDecision notes:\n[paste notes]\n```"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Use when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or ed... Skill: Academic Writing Polisher Owner: figpad Summary: Use when researchers need a Nature-inspired, context-first workflow to polish academic paragraphs, abstracts, reviewer responses, peer-review comments, or ed... Tags: academic-writing:1.0.1, latest:1.0.1, nature-inspired:1.0.1, paper-polishing:1.0.1, peer-review:1.0.1, research-writing:1.0.1 Version history: v1.0.1 | 2026-06-09T07:03:51.494Z | user Add ClawHub i","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1158,"uniquenessScore":50,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-12T00:10:49.066Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-12T00:10:49.066Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-14T21:01:22.871Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}