{"id":"165f63d7-9b06-4503-8f20-df75de54e16f","entityType":"agent","slug":"clawhub-phy041-phy-paper-polish","name":"Phy Paper Polish","canonicalUrl":"https://www.xpersona.co/agent/clawhub-phy041-phy-paper-polish","canonicalPath":"/agent/clawhub-phy041-phy-paper-polish","generatedAt":"2026-10-14T14:15:05.901Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T21:11:52.556Z","emptyReason":null},"description":"This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document stru... Skill: Phy Paper Polish Owner: phy041 Summary: This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document stru... Tags: academic:1.0.0, latest:1.0.2, latex:1.0.0, review:1.0.0, writing:1.0.0 Version history: v1.0.2 | 2026-03-22T14:03:07.936Z | auto - Added an \"Author\" section with contact and project links at the end of the","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 992 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s175g2rty8e4mw6h9zcwwgxmfn884t23:phy-paper-polish","sourceUrl":"https://clawhub.ai/phy041/phy-paper-polish","homepage":"https://clawhub.ai/phy041/skills/phy-paper-polish","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/phy041/phy-paper-polish","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/phy041/skills/phy-paper-polish","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document stru..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:11:52.556Z","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":"2026-10-11T21:11:52.556Z","emptyReason":null},"stars":null,"forks":null,"downloads":992,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"992 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:11:52.433Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T21:11:52.556Z","lastCrawledAt":"2026-10-11T21:11:52.433Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T21:11:52.433Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-03-22T14:03:07.936Z","changelog":"- Added an \"Author\" section with contact and project links at the end of the documentation. - No other content changes were made.","fileCount":3,"zipByteSize":4177},{"version":"1.0.1","createdAt":"2026-03-22T12:12:34.559Z","changelog":"- Added a homepage link (https://canlah.ai) to the skill metadata. - No changes to documentation content or logic.","fileCount":2,"zipByteSize":2816},{"version":"1.0.0","createdAt":"2026-03-06T09:19:43.575Z","changelog":"Initial release — review and polish LaTeX research papers","fileCount":2,"zipByteSize":2802}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s175g2rty8e4mw6h9zcwwgxmfn884t23:phy-paper-polish","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-phy041-phy-paper-polish/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-phy041-phy-paper-polish/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-phy041-phy-paper-polish/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-phy041-phy-paper-polish/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-phy041-phy-paper-polish/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-phy041-phy-paper-polish/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-14T14:15:05.901Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-phy041-phy-paper-polish/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-phy041-phy-paper-polish/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-phy041-phy-paper-polish/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-phy041-phy-paper-polish/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":"2026-10-11T21:11:52.556Z","emptyReason":null},"readme":"Skill: Phy Paper Polish\n\nOwner: phy041\n\nSummary: This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document stru...\n\nTags: academic:1.0.0, latest:1.0.2, latex:1.0.0, review:1.0.0, writing:1.0.0\n\nVersion history:\n\nv1.0.2 | 2026-03-22T14:03:07.936Z | auto\n\n- Added an \"Author\" section with contact and project links at the end of the documentation.\n- No other content changes were made.\n\nv1.0.1 | 2026-03-22T12:12:34.559Z | auto\n\n- Added a homepage link (https://canlah.ai) to the skill metadata.  \n- No changes to documentation content or logic.\n\nv1.0.0 | 2026-03-06T09:19:43.575Z | user\n\nInitial release — review and polish LaTeX research papers\n\nArchive index:\n\nArchive v1.0.2: 3 files, 4177 bytes\n\nFiles: skill-card.md (2249b), SKILL.md (5644b), _meta.json (135b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: paper-polish\ndescription: This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document structure.\nhomepage: https://canlah.ai\nmetadata:\n  short-description: fixing writing errors in academic papers\n\n---\n# Polishing and reviewing research papers in LaTeX\n\n## On writing\n\n### Contents\n\n- Your paper should be easily comprehensible by its reviewers.\n  They are far less familiar with your work than you.\n  They may not be an expert on the topic and may not be able to afford much time on your paper.\n- The introduction should convey curiosity or excitement\n  (new problem, new solution, improved solution, impressive results, or high impact),\n  the design novelty, substantiality, and correctness,\n  and the evaluation relevancy and comprehensiveness.\n- Conciseness: Remove every word that contributes no meaning, such as `kind of`.\n- Use proper tenses:\n  - [1](https://www.unlv.edu/sites/default/files/page_files/27/GradCollege-VerbTenseScientificManuscripts.pdf)\n  - [2](https://berks.psu.edu/sites/berks/files/campus/VerbTense_Handout.pdf)\n  - [3](https://www.nature.com/scitable/topicpage/effective-writing-13815989/)\n\n### Grammar\n\n- Section titles should have consistent [capitalization](https://www.grammarly.com/blog/title-case-sentence-case/).\n  - Title Case: Capitalize the first and last words and all major words in between.\n    - Good: Introduction to Fuzzing with LLMs\n  - Sentence case: Capitalize only the first word and proper nouns.\n    - Good: Introduction to fuzzing with LLMs\n  - Choose one style and be consistent throughout the paper.\n\n- Avoid passive voice unless strongly justifiable.\n  Passive voice is ambiguous because it has no subject unless followed by \"by...\".\n  - Bad: LLM was applied to fuzzing. (Who applied it? The authors or someone else?)\n  - Good: We applied LLM to fuzzing.\n\n- Avoid [nominalization](https://en.wikipedia.org/wiki/Nominalization).\n  - Bad: He made a proposal to use Rust.\n  - Good: He proposed to use Rust.\n\n- Avoid \"There is/are\".\n  - Bad: There are many developers of Rust.\n  - Good: Many developers use Rust.\n  - Good: Rust has many developers.\n\n- \"Which\" vs \"that\": Use \"which\" in a nonrestrictive clause and \"that\" in a restrictive clause.\n  [More...](https://www.grammarly.com/blog/which-vs-that/)\n  - Wrong: Rust that is safe is popular.\n    (This is wrong because there is only one Rust.)\n  - Right: Rust, which is safe, is popular.\n\n- Distinguish [coordinating conjunction vs conjunctive adverbs](https://www.iup.edu/writingcenter/writing-resources/grammar/common-problems-with-however-therefore-and-similar-words.html).\n  - Wrong: C is dangerous, Rust is safe. (Cannot join two sentences by a comma)\n  - Right: C is dangerous, but Rust is safe.\n  - Wrong: C is dangerous, however Rust is safe.\n  - Right: C is dangerous; however, Rust is safe.\n\n- \"Fewer\" modifies countable nouns whereas \"less\" uncountable nouns.\n  - Wrong: ten items or less\n  - Right: ten items or fewer\n  - Wrong: fewer feedback\n  - Right: less feedback\n\n- Use articles (`a`, `an`, `the`) properly.\n  - A singular countable noun must be preceded by an article.\n    - Wrong: I wrote Rust program.\n    - Right: I wrote a Rust program.\n    - Right: I wrote Rust programs.\n\n  - `The` must have a reference that is unique either by fact or in the context.\n    - Right: the first Rust programmer (unique by fact)\n    - Right: Our team has a Rust and a C++ programmer.\n      The Rust programmer produces the fastest, most robust code.\n      (unique in the context)\n    - Wrong: Our team has two Rust and two C++ programmers.\n      The Rust programmer is more productive than the C++ programmer.\n\n- Distinguish between [compare with and compare to](https://www.noslangues-ourlanguages.gc.ca/en/writing-tips-plus/compare-to-compare-with)\n  - Right: Rust is safer compared with C.\n  - Right: Some people compare Rust to a panacea for memory safety problems.\n\n## On LaTeX\n\n- Use modern implementations of LaTeX to take advantage of Unicode and other useful features.\n  - Use [LuaLaTeX](https://www.luatex.org/) instead of LaTeX or pdfLaTeX\n  - Use [BibLaTeX](https://www.overleaf.com/learn/latex/Bibliography_management_with_biblatex) for `acmart` and `ieeetrans` templates instead of BibTex\n\n- Use correct [typefaces](https://physics.nist.gov/cuu/pdf/typefaces.pdf).\n  Particularly, _italics_ should be used for variables but not for descriptive terms. [More...](https://en.wikibooks.org/wiki/LaTeX/Mathematics#Adding_text_to_equations)\n  - Wrong: $t_{max}$\n  - Right: $t_\\text{max}$\n\n- Do not manually add separators in large numbers.\n  `\\usepackage{siunitx}`.\n  Then, wrap large numbers in `\\num{}`.\n  - Bad: 12,345\n  - Good: `\\num{12345}`\n\n- Do not manually type reference names, such as Table, Figure, Theorem.\n  Instead, `\\usepackage{hyperref}`,\n  and then `\\autoref{fig:xxx}`, `\\autoref{sec:xxx}`, `\\autoref{table:xxx}`.\n  - Not recommended: In Figure~\\ref{fig:overview}\n  - Good: In \\autoref{fig:overview}\n\n## Structure\n\n- `main.tex` is the entry root of the LaTeX project, containing the `usepackage` commands and the document structure.\n- `src/` contains all the sections.\n- `tables/` contains all the tables.\n- `figures/` or `fig/` contains the figures. Figures are PDF files or `.tex` files.\n  `.tex` in figures are algorithms.\n- `code/` contains code listings used in the text.\n\n---\n\n## Author\n\n**[Canlah AI](https://canlah.ai)** — Run performance marketing without breaking your brand.\n\n- GitHub: [github.com/PHY041](https://github.com/PHY041)\n- All Skills: [clawhub.ai/PHY041](https://clawhub.ai/PHY041)\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn7fdhcxytgt3k2vvnc24c8ke581g5j1\",\n  \"slug\": \"phy-paper-polish\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1774188187936\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nThis skill helps agents review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document structure.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[phy041](https://clawhub.ai/user/phy041)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nResearchers, authors, and technical editors use this skill to review LaTeX research papers for clearer writing, grammar, consistent structure, and LaTeX best practices before submission.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Suggested edits may change technical meaning or introduce inappropriate wording into a manuscript.\n\nMitigation: Review proposed changes against the author's technical intent before applying them.\n\nRisk: Manuscripts may contain unpublished or sensitive research content.\n\nMitigation: Provide only the manuscript files intended for review and follow the applicable confidentiality requirements.\n\n## Reference(s):\n\n- [Phy Paper Polish on ClawHub](https://clawhub.ai/phy041/skills/phy-paper-polish)\n- [Canlah AI](https://canlah.ai)\n- [Verb Tense in Scientific Manuscripts](https://www.unlv.edu/sites/default/files/page_files/27/GradCollege-VerbTenseScientificManuscripts.pdf)\n- [Effective Writing](https://www.nature.com/scitable/topicpage/effective-writing-13815989/)\n- [LuaTeX](https://www.luatex.org/)\n- [BibLaTeX Documentation](https://www.overleaf.com/learn/latex/Bibliography_management_with_biblatex)\n- [NIST Typefaces for Symbols in Scientific Manuscripts](https://physics.nist.gov/cuu/pdf/typefaces.pdf)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown prose with suggested edits and LaTeX guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [No executable code; output should be reviewed before applying changes to manuscripts.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release evidence)\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\nArchive v1.0.1: 2 files, 2816 bytes\n\nFiles: SKILL.md (5414b), _meta.json (135b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: paper-polish\ndescription: This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document structure.\nhomepage: https://canlah.ai\nmetadata:\n  short-description: fixing writing errors in academic papers\n\n---\n# Polishing and reviewing research papers in LaTeX\n\n## On writing\n\n### Contents\n\n- Your paper should be easily comprehensible by its reviewers.\n  They are far less familiar with your work than you.\n  They may not be an expert on the topic and may not be able to afford much time on your paper.\n- The introduction should convey curiosity or excitement\n  (new problem, new solution, improved solution, impressive results, or high impact),\n  the design novelty, substantiality, and correctness,\n  and the evaluation relevancy and comprehensiveness.\n- Conciseness: Remove every word that contributes no meaning, such as `kind of`.\n- Use proper tenses:\n  - [1](https://www.unlv.edu/sites/default/files/page_files/27/GradCollege-VerbTenseScientificManuscripts.pdf)\n  - [2](https://berks.psu.edu/sites/berks/files/campus/VerbTense_Handout.pdf)\n  - [3](https://www.nature.com/scitable/topicpage/effective-writing-13815989/)\n\n### Grammar\n\n- Section titles should have consistent [capitalization](https://www.grammarly.com/blog/title-case-sentence-case/).\n  - Title Case: Capitalize the first and last words and all major words in between.\n    - Good: Introduction to Fuzzing with LLMs\n  - Sentence case: Capitalize only the first word and proper nouns.\n    - Good: Introduction to fuzzing with LLMs\n  - Choose one style and be consistent throughout the paper.\n\n- Avoid passive voice unless strongly justifiable.\n  Passive voice is ambiguous because it has no subject unless followed by \"by...\".\n  - Bad: LLM was applied to fuzzing. (Who applied it? The authors or someone else?)\n  - Good: We applied LLM to fuzzing.\n\n- Avoid [nominalization](https://en.wikipedia.org/wiki/Nominalization).\n  - Bad: He made a proposal to use Rust.\n  - Good: He proposed to use Rust.\n\n- Avoid \"There is/are\".\n  - Bad: There are many developers of Rust.\n  - Good: Many developers use Rust.\n  - Good: Rust has many developers.\n\n- \"Which\" vs \"that\": Use \"which\" in a nonrestrictive clause and \"that\" in a restrictive clause.\n  [More...](https://www.grammarly.com/blog/which-vs-that/)\n  - Wrong: Rust that is safe is popular.\n    (This is wrong because there is only one Rust.)\n  - Right: Rust, which is safe, is popular.\n\n- Distinguish [coordinating conjunction vs conjunctive adverbs](https://www.iup.edu/writingcenter/writing-resources/grammar/common-problems-with-however-therefore-and-similar-words.html).\n  - Wrong: C is dangerous, Rust is safe. (Cannot join two sentences by a comma)\n  - Right: C is dangerous, but Rust is safe.\n  - Wrong: C is dangerous, however Rust is safe.\n  - Right: C is dangerous; however, Rust is safe.\n\n- \"Fewer\" modifies countable nouns whereas \"less\" uncountable nouns.\n  - Wrong: ten items or less\n  - Right: ten items or fewer\n  - Wrong: fewer feedback\n  - Right: less feedback\n\n- Use articles (`a`, `an`, `the`) properly.\n  - A singular countable noun must be preceded by an article.\n    - Wrong: I wrote Rust program.\n    - Right: I wrote a Rust program.\n    - Right: I wrote Rust programs.\n\n  - `The` must have a reference that is unique either by fact or in the context.\n    - Right: the first Rust programmer (unique by fact)\n    - Right: Our team has a Rust and a C++ programmer.\n      The Rust programmer produces the fastest, most robust code.\n      (unique in the context)\n    - Wrong: Our team has two Rust and two C++ programmers.\n      The Rust programmer is more productive than the C++ programmer.\n\n- Distinguish between [compare with and compare to](https://www.noslangues-ourlanguages.gc.ca/en/writing-tips-plus/compare-to-compare-with)\n  - Right: Rust is safer compared with C.\n  - Right: Some people compare Rust to a panacea for memory safety problems.\n\n## On LaTeX\n\n- Use modern implementations of LaTeX to take advantage of Unicode and other useful features.\n  - Use [LuaLaTeX](https://www.luatex.org/) instead of LaTeX or pdfLaTeX\n  - Use [BibLaTeX](https://www.overleaf.com/learn/latex/Bibliography_management_with_biblatex) for `acmart` and `ieeetrans` templates instead of BibTex\n\n- Use correct [typefaces](https://physics.nist.gov/cuu/pdf/typefaces.pdf).\n  Particularly, _italics_ should be used for variables but not for descriptive terms. [More...](https://en.wikibooks.org/wiki/LaTeX/Mathematics#Adding_text_to_equations)\n  - Wrong: $t_{max}$\n  - Right: $t_\\text{max}$\n\n- Do not manually add separators in large numbers.\n  `\\usepackage{siunitx}`.\n  Then, wrap large numbers in `\\num{}`.\n  - Bad: 12,345\n  - Good: `\\num{12345}`\n\n- Do not manually type reference names, such as Table, Figure, Theorem.\n  Instead, `\\usepackage{hyperref}`,\n  and then `\\autoref{fig:xxx}`, `\\autoref{sec:xxx}`, `\\autoref{table:xxx}`.\n  - Not recommended: In Figure~\\ref{fig:overview}\n  - Good: In \\autoref{fig:overview}\n\n## Structure\n\n- `main.tex` is the entry root of the LaTeX project, containing the `usepackage` commands and the document structure.\n- `src/` contains all the sections.\n- `tables/` contains all the tables.\n- `figures/` or `fig/` contains the figures. Figures are PDF files or `.tex` files.\n  `.tex` in figures are algorithms.\n- `code/` contains code listings used in the text.\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7fdhcxytgt3k2vvnc24c8ke581g5j1\",\n  \"slug\": \"phy-paper-polish\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1774181554559\n}\n\nArchive v1.0.0: 2 files, 2802 bytes\n\nFiles: SKILL.md (5386b), _meta.json (135b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: paper-polish\ndescription: This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document structure.\nmetadata:\n  short-description: fixing writing errors in academic papers\n\n---\n# Polishing and reviewing research papers in LaTeX\n\n## On writing\n\n### Contents\n\n- Your paper should be easily comprehensible by its reviewers.\n  They are far less familiar with your work than you.\n  They may not be an expert on the topic and may not be able to afford much time on your paper.\n- The introduction should convey curiosity or excitement\n  (new problem, new solution, improved solution, impressive results, or high impact),\n  the design novelty, substantiality, and correctness,\n  and the evaluation relevancy and comprehensiveness.\n- Conciseness: Remove every word that contributes no meaning, such as `kind of`.\n- Use proper tenses:\n  - [1](https://www.unlv.edu/sites/default/files/page_files/27/GradCollege-VerbTenseScientificManuscripts.pdf)\n  - [2](https://berks.psu.edu/sites/berks/files/campus/VerbTense_Handout.pdf)\n  - [3](https://www.nature.com/scitable/topicpage/effective-writing-13815989/)\n\n### Grammar\n\n- Section titles should have consistent [capitalization](https://www.grammarly.com/blog/title-case-sentence-case/).\n  - Title Case: Capitalize the first and last words and all major words in between.\n    - Good: Introduction to Fuzzing with LLMs\n  - Sentence case: Capitalize only the first word and proper nouns.\n    - Good: Introduction to fuzzing with LLMs\n  - Choose one style and be consistent throughout the paper.\n\n- Avoid passive voice unless strongly justifiable.\n  Passive voice is ambiguous because it has no subject unless followed by \"by...\".\n  - Bad: LLM was applied to fuzzing. (Who applied it? The authors or someone else?)\n  - Good: We applied LLM to fuzzing.\n\n- Avoid [nominalization](https://en.wikipedia.org/wiki/Nominalization).\n  - Bad: He made a proposal to use Rust.\n  - Good: He proposed to use Rust.\n\n- Avoid \"There is/are\".\n  - Bad: There are many developers of Rust.\n  - Good: Many developers use Rust.\n  - Good: Rust has many developers.\n\n- \"Which\" vs \"that\": Use \"which\" in a nonrestrictive clause and \"that\" in a restrictive clause.\n  [More...](https://www.grammarly.com/blog/which-vs-that/)\n  - Wrong: Rust that is safe is popular.\n    (This is wrong because there is only one Rust.)\n  - Right: Rust, which is safe, is popular.\n\n- Distinguish [coordinating conjunction vs conjunctive adverbs](https://www.iup.edu/writingcenter/writing-resources/grammar/common-problems-with-however-therefore-and-similar-words.html).\n  - Wrong: C is dangerous, Rust is safe. (Cannot join two sentences by a comma)\n  - Right: C is dangerous, but Rust is safe.\n  - Wrong: C is dangerous, however Rust is safe.\n  - Right: C is dangerous; however, Rust is safe.\n\n- \"Fewer\" modifies countable nouns whereas \"less\" uncountable nouns.\n  - Wrong: ten items or less\n  - Right: ten items or fewer\n  - Wrong: fewer feedback\n  - Right: less feedback\n\n- Use articles (`a`, `an`, `the`) properly.\n  - A singular countable noun must be preceded by an article.\n    - Wrong: I wrote Rust program.\n    - Right: I wrote a Rust program.\n    - Right: I wrote Rust programs.\n\n  - `The` must have a reference that is unique either by fact or in the context.\n    - Right: the first Rust programmer (unique by fact)\n    - Right: Our team has a Rust and a C++ programmer.\n      The Rust programmer produces the fastest, most robust code.\n      (unique in the context)\n    - Wrong: Our team has two Rust and two C++ programmers.\n      The Rust programmer is more productive than the C++ programmer.\n\n- Distinguish between [compare with and compare to](https://www.noslangues-ourlanguages.gc.ca/en/writing-tips-plus/compare-to-compare-with)\n  - Right: Rust is safer compared with C.\n  - Right: Some people compare Rust to a panacea for memory safety problems.\n\n## On LaTeX\n\n- Use modern implementations of LaTeX to take advantage of Unicode and other useful features.\n  - Use [LuaLaTeX](https://www.luatex.org/) instead of LaTeX or pdfLaTeX\n  - Use [BibLaTeX](https://www.overleaf.com/learn/latex/Bibliography_management_with_biblatex) for `acmart` and `ieeetrans` templates instead of BibTex\n\n- Use correct [typefaces](https://physics.nist.gov/cuu/pdf/typefaces.pdf).\n  Particularly, _italics_ should be used for variables but not for descriptive terms. [More...](https://en.wikibooks.org/wiki/LaTeX/Mathematics#Adding_text_to_equations)\n  - Wrong: $t_{max}$\n  - Right: $t_\\text{max}$\n\n- Do not manually add separators in large numbers.\n  `\\usepackage{siunitx}`.\n  Then, wrap large numbers in `\\num{}`.\n  - Bad: 12,345\n  - Good: `\\num{12345}`\n\n- Do not manually type reference names, such as Table, Figure, Theorem.\n  Instead, `\\usepackage{hyperref}`,\n  and then `\\autoref{fig:xxx}`, `\\autoref{sec:xxx}`, `\\autoref{table:xxx}`.\n  - Not recommended: In Figure~\\ref{fig:overview}\n  - Good: In \\autoref{fig:overview}\n\n## Structure\n\n- `main.tex` is the entry root of the LaTeX project, containing the `usepackage` commands and the document structure.\n- `src/` contains all the sections.\n- `tables/` contains all the tables.\n- `figures/` or `fig/` contains the figures. Figures are PDF files or `.tex` files.\n  `.tex` in figures are algorithms.\n- `code/` contains code listings used in the text.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7fdhcxytgt3k2vvnc24c8ke581g5j1\",\n  \"slug\": \"phy-paper-polish\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1772788783575\n}","readmeExcerpt":"Skill: Phy Paper Polish Owner: phy041 Summary: This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document stru... Tags: academic:1.0.0, latest:1.0.2, latex:1.0.0, review:1.0.0, writing:1.0.0 Version history: v1.0.2 | 2026-03-22T14:03:07.936Z | auto - Added an \"Author\" section with contact and project links at the end of the ","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: paper-polish\ndescription: This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document structure.\nhomepage: https://canlah.ai\nmetadata:\n  short-description: fixing writing errors in academic papers\n\n---\n# Polishing and reviewing research papers in LaTeX\n\n## On writing\n\n### Contents\n\n- Your paper should be easily comprehensible by its reviewers.\n  They are far less familiar with your work than you.\n  They may not be an expert on the topic and may not be able to afford much time on your paper.\n- The introduction should convey curiosity or excitement\n  (new problem, new solution, improved solution, impressive results, or high impact),\n  the design novelty, substantiality, and correctness,\n  and the evaluation relevancy and comprehensiveness.\n- Conciseness: Remove every word that contributes no meaning, such as `kind of`.\n- Use proper tenses:\n  - [1](https://www.unlv.edu/sites/default/files/page_files/27/GradCollege-VerbTenseScientificManuscripts.pdf)\n  - [2](https://berks.psu.edu/sites/berks/files/campus/VerbTense_Handout.pdf)\n  - [3](https://www.nature.com/scitable/topicpage/effective-writing-13815989/)\n\n### Grammar\n\n- Section titles should have consistent [capitalization](https://www.grammarly.com/blog/title-case-sentence-case/).\n  - Title Case: Capitalize the first and last words and all major words in between.\n    - Good: Introduction to Fuzzing with LLMs\n  - Sentence case: Capitalize only the first word and proper nouns.\n    - Good: Introduction to fuzzing with LLMs\n  - Choose one style and be consistent throughout the paper.\n\n- Avoid passive voice unless strongly justifiable.\n  Passive voice is ambiguous because it has no subject unless followed by \"by...\".\n  - Bad: LLM was applied to fuzzing. (Who applied it? The authors or someone else?)\n  - Good: We applied LLM to fuzzing.\n\n- Avoid [nominalization](https://en.wikipedia.org/wiki/Nominalization).\n  - Bad: He made a proposal to use Rust.\n  - Good: He proposed to use Rust.\n\n- Avoid \"There is/are\".\n  - Bad: There are many developers of Rust.\n  - Good: Many developers use Rust.\n  - Good: Rust has many developers.\n\n- \"Which\" vs \"that\": Use \"which\" in a nonrestrictive clause and \"that\" in a restrictive clause.\n  [More...](https://www.grammarly.com/blog/which-vs-that/)\n  - Wrong: Rust that is safe is popular.\n    (This is wrong because there is only one Rust.)\n  - Right: Rust, which is safe, is popular.\n\n- Distinguish [coordinating conjunction vs conjunctive adverbs](https://www.iup.edu/writingcenter/writing-resources/grammar/common-problems-with-however-therefore-and-similar-words.html).\n  - Wrong: C is dangerous, Rust is safe. (Cannot join two sentences by a comma)\n  - Right: C is dangerous, but Rust is safe.\n  - Wrong: C is dangerous, however Rust is safe.\n  - Right: C is dangerous; however, Rust is safe.\n\n- \"Fewer\" modifies countable nouns whereas \"less\" uncountable nouns.\n  - Wrong: ten items o"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7fdhcxytgt3k2vvnc24c8ke581g5j1\",\n  \"slug\": \"phy-paper-polish\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1774188187936\n}"},{"path":"skill-card.md","content":"## Description:\n\nThis skill helps agents review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document structure.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[phy041](https://clawhub.ai/user/phy041)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nResearchers, authors, and technical editors use this skill to review LaTeX research papers for clearer writing, grammar, consistent structure, and LaTeX best practices before submission.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Suggested edits may change technical meaning or introduce inappropriate wording into a manuscript.\n\nMitigation: Review proposed changes against the author's technical intent before applying them.\n\nRisk: Manuscripts may contain unpublished or sensitive research content.\n\nMitigation: Provide only the manuscript files intended for review and follow the applicable confidentiality requirements.\n\n## Reference(s):\n\n- [Phy Paper Polish on ClawHub](https://clawhub.ai/phy041/skills/phy-paper-polish)\n- [Canlah AI](https://canlah.ai)\n- [Verb Tense in Scientific Manuscripts](https://www.unlv.edu/sites/default/files/page_files/27/GradCollege-VerbTenseScientificManuscripts.pdf)\n- [Effective Writing](https://www.nature.com/scitable/topicpage/effective-writing-13815989/)\n- [LuaTeX](https://www.luatex.org/)\n- [BibLaTeX Documentation](https://www.overleaf.com/learn/latex/Bibliography_management_with_biblatex)\n- [NIST Typefaces for Symbols in Scientific Manuscripts](https://physics.nist.gov/cuu/pdf/typefaces.pdf)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown prose with suggested edits and LaTeX guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [No executable code; output should be reviewed before applying changes to manuscripts.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release evidence)\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."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document stru... Skill: Phy Paper Polish Owner: phy041 Summary: This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document stru... Tags: academic:1.0.0, latest:1.0.2, latex:1.0.0, review:1.0.0, writing:1.0.0 Version history: v1.0.2 | 2026-03-22T14:03:07.936Z | auto - Added an \"Author\" section with contact and project links at the end of the","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1032,"uniquenessScore":52,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T21:11:52.556Z","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":"2026-10-11T21:11:52.556Z","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":"2026-10-14T14:15:05.901Z","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"}]}}}