[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD3M6KTEDX7FM12DX7D1F1":3,"skill-same:01M7FD3M6KTEDX7FM12DX7D1F1":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7FD3M6KTEDX7FM12DX7D1F1","paper-compile",null,"Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \"编译论文\", \"compile paper\", \"build PDF\", \"生成PDF\", or wants to compile LaTeX into a submission-ready PDF.","CZX-LBJ\u002Fdeepseek-science","CZX-LBJ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204594689?v=4","01M7FC59WQ9PFXT04MKGJDCFFT","czx","01M7FC59XB2GW0BKWN9JTDBQS7",1,"MIT","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-compile\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: paper-compile\ndescription: \"Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \\\"编译论文\\\", \\\"compile paper\\\", \\\"build PDF\\\", \\\"生成PDF\\\", or wants to compile LaTeX into a submission-ready PDF.\"\nargument-hint: \"[paper-directory]\"\nallowed-tools: Bash(*), Read, Write, Edit, Grep, Glob\n---\n\n# Paper Compile: LaTeX to Submission-Ready PDF\n\nCompile the LaTeX paper and fix any issues: **$ARGUMENTS**\n\n## Constants\n\n- **COMPILER = `latexmk`** — LaTeX build tool. Handles multi-pass compilation automatically.\n- **ENGINE = `pdflatex`** — LaTeX engine. Options: `pdflatex` (default), `xelatex` (for CJK\u002Fcustom fonts), `lualatex`.\n- **MAX_COMPILE_ATTEMPTS = 3** — Maximum attempts to fix errors and recompile.\n- **PAPER_DIR = `paper\u002F`** — Directory containing LaTeX source files.\n- **MAX_PAGES** — Page limit. ML conferences: main body to Conclusion end (excluding references & appendix). ICLR=9, NeurIPS=9, ICML=8. **IEEE venues: references ARE included in page count.** IEEE journal ≈ 12-14 pages, IEEE conference ≈ 5-8 pages (all inclusive).\n\n## Workflow\n\n### Step 1: Verify Prerequisites\n\nCheck that the compilation environment is ready:\n\n```bash\n# Check LaTeX installation\nwhich pdflatex && which latexmk && which bibtex\n\n# If not installed, provide instructions:\n# macOS: brew install --cask mactex-no-gui\n# Ubuntu: sudo apt-get install texlive-full\n# Server: conda install -c conda-forge texlive-core\n```\n\nVerify all required files exist:\n\n```bash\n# Must exist\nls $PAPER_DIR\u002Fmain.tex\n\n# Should exist\nls $PAPER_DIR\u002Freferences.bib\nls $PAPER_DIR\u002Fsections\u002F*.tex\nls $PAPER_DIR\u002Ffigures\u002F*.pdf 2>\u002Fdev\u002Fnull || ls $PAPER_DIR\u002Ffigures\u002F*.png 2>\u002Fdev\u002Fnull\n```\n\n### Step 2: First Compilation Attempt\n\n```bash\ncd $PAPER_DIR\n\n# Clean previous build artifacts\nlatexmk -C\n\n# Full compilation (pdflatex + bibtex + pdflatex × 2)\nlatexmk -pdf -interaction=nonstopmode -halt-on-error main.tex 2>&1 | tee compile.log\n```\n\n### Step 3: Error Diagnosis and Auto-Fix\n\nIf compilation fails, read `compile.log` and fix common errors:\n\n**Missing packages:**\n```\n! LaTeX Error: File `somepackage.sty' not found.\n```\n→ Install via `tlmgr install somepackage` or remove the `\\usepackage` if unused.\n\n**Undefined references:**\n```\nLaTeX Warning: Reference `fig:xyz' on page 3 undefined\n```\n→ Check `\\label{fig:xyz}` exists in the correct figure environment.\n\n**Missing figures:**\n```\n! LaTeX Error: File `figures\u002Ffig1.pdf' not found.\n```\n→ Check if the file exists with a different extension (.png vs .pdf). Update the `\\includegraphics` path.\n\n**Citation undefined:**\n```\nLaTeX Warning: Citation `smith2024' undefined\n```\n→ Add the missing entry to `references.bib` or fix the citation key.\n\n**`[VERIFY]` markers in text:**\n→ Search for `[VERIFY]` markers left by `\u002Fpaper-write`. These indicate unverified citations or facts. Search for the correct information or flag to the user.\n\n**Overfull hbox:**\n```\nOverfull \\hbox (12.5pt too wide) in paragraph at lines 42--45\n```\n→ Minor: usually ignorable. If severe (>20pt), rephrase the text or adjust figure width.\n\n**BibTeX errors:**\n```\nI was expecting a `,' or a `}'---line 15 of references.bib\n```\n→ Fix BibTeX syntax (missing comma, unmatched braces, special characters in title).\n\n**`\\crefname` undefined for custom theorem types:**\n→ Ensure `\\crefname{assumption}{Assumption}{Assumptions}` and similar are in the preamble after `\\newtheorem{assumption}`.\n\n### Step 4: Iterative Fix Loop\n\n```\nfor attempt in 1..MAX_COMPILE_ATTEMPTS:\n    compile()\n    if success:\n        break\n    parse_errors()\n    auto_fix()\n```\n\nFor each error:\n1. Read the error message from `compile.log`\n2. Locate the source file and line number\n3. Apply the fix\n4. Recompile\n\n**Stuck after 2 attempts?** If Codex plugin is installed, invoke `\u002Fcodex:rescue` — Codex can independently read the LaTeX source and `compile.log` to spot issues Claude missed (e.g., conflicting packages, encoding problems, subtle macro errors). If not installed, continue with Claude's own diagnosis.\n\n### Step 5: Post-Compilation Checks\n\nAfter successful compilation, verify the output:\n\n```bash\n# Check PDF exists and has content\nls -la main.pdf\n# Check page count\npdfinfo main.pdf | grep Pages\n\n# macOS: open for visual inspection\n# open main.pdf\n```\n\n**Visual review (automated):**\nIf the compiled PDF exists, read it directly to check visual presentation:\n- Figure quality: readable labels, legible text, distinguishable colors\n- Layout: no orphaned section headers, no awkward page breaks\n- Figures appear near their first text reference (not pages away)\n- Tables: aligned columns, consistent decimal precision\n- No overfull content visibly extending past margins\n\nThis is a quick visual scan, not a full review — the improvement loop does deeper visual review.\n\n**Automated checks:**\n\n- [ ] PDF file exists and is > 100KB (not empty\u002Fcorrupt)\n- [ ] Total page count is reasonable (MAX_PAGES + appendix + references)\n- [ ] No \"??\" in the PDF (undefined references — grep the log)\n- [ ] No \"[?]\" in the PDF (undefined citations — grep the log)\n- [ ] Figures are rendered (not missing image placeholders)\n\n```bash\n# Check for undefined references\ngrep -c \"LaTeX Warning.*undefined\" compile.log\n\n# Check for missing citations\ngrep -c \"Citation.*undefined\" compile.log\n```\n\n### Step 6: Page Count Verification\n\n**CRITICAL**: Verify paper fits within MAX_PAGES.\n\n**For ML conferences (ICLR\u002FNeurIPS\u002FICML\u002FCVPR\u002FACL\u002FAAAI):** Main body = first page through end of Conclusion section (not necessarily §5 — could be §6, §7, or §8 depending on structure). References and appendix are NOT counted.\n\n**For IEEE venues:** The TOTAL page count (including references) must fit within the limit. There is no separate \"main body\" counting — everything up to and including the references counts.\n\n**Precise check using `pdftotext`:**\n```bash\n# Extract text and find where Conclusion ends vs References begin\npdftotext main.pdf - | python3 -c \"\nimport sys\ntext = sys.stdin.read()\npages = text.split('\\f')\nfor i, page in enumerate(pages):\n    if 'Ethics Statement' in page or 'Reproducibility' in page:\n        print(f'Conclusion ends on page {i+1}')\n    if any(w in page for w in ['References', 'Bibliography']):\n        lines = [l for l in page.split('\\n') if l.strip()]\n        for l in lines[:3]:\n            if 'References' in l or 'Bibliography' in l:\n                print(f'References start on page {i+1}')\n                break\n\"\n```\n\nIf Conclusion ends mid-page and References start on the same page, the main body is that page number (e.g., if both are on page 9, main body = ~8.5 pages, which is fine for a 9-page limit since it leaves room for the References header).\n\nIf over limit:\n- Identify which sections are longest\n- Suggest specific cuts (move proofs to appendix, compress tables, tighten writing)\n- Report: \"Main body is X pages (limit: MAX_PAGES). Suggestion: move [specific content] to appendix.\"\n\n### Step 6.5: Stale File Detection\n\nCheck for orphaned section files not referenced by `main.tex`:\n\n```bash\n# Find all .tex files in sections\u002F and check which are \\input'ed by main.tex\nfor f in paper\u002Fsections\u002F*.tex; do\n    base=$(basename \"$f\")\n    if ! grep -q \"$base\" paper\u002Fmain.tex; then\n        echo \"WARNING: $f is not referenced by main.tex — consider removing\"\n    fi\ndone\n```\n\nThis prevents confusion from leftover files when section structure changes (e.g., old `5_conclusion.tex` left behind after restructuring to 7 sections).\n\n### Step 7: Submission Readiness\n\nFor conference submission, additional checks:\n\n- [ ] **Anonymous**: no author names, affiliations, or self-citations that reveal identity\n- [ ] **Page limit**: main body within MAX_PAGES (to end of Conclusion)\n- [ ] **Font embedding**: all fonts embedded in PDF\n  ```bash\n  pdffonts main.pdf | grep -v \"yes\"  # should return nothing (or only header)\n  ```\n- [ ] **No supplementary mixed in**: appendix clearly after `\\newpage\\appendix`\n- [ ] **File size**: reasonable (\u003C 50MB for most venues, \u003C 10MB preferred)\n- [ ] **No `[VERIFY]` markers**: search the PDF text for leftover markers\n\n### Step 8: Output Summary\n\n```markdown\n## Compilation Report\n\n- **Status**: SUCCESS \u002F FAILED\n- **PDF**: paper\u002Fmain.pdf\n- **Pages**: X (main body to Conclusion) + Y (references) + Z (appendix)\n- **Within page limit**: YES\u002FNO (MAX_PAGES = N)\n- **Errors fixed**: [list of auto-fixed issues]\n- **Warnings remaining**: [list of non-critical warnings]\n- **Undefined references**: 0\n- **Undefined citations**: 0\n\n### Next Steps\n- [ ] Visual inspection of PDF\n- [ ] Run `\u002Fpaper-write` to fix any content issues\n- [ ] Submit to [venue] via OpenReview \u002F CMT \u002F HotCRP\n```\n\n## Key Rules\n\n- **Never delete the user's source files** — only modify to fix errors\n- **Keep compile.log** — useful for debugging\n- **Don't suppress warnings** — report them, let the user decide\n- **If LaTeX is not installed**, provide clear installation instructions rather than failing silently\n- **Font embedding is critical** — some venues reject PDFs with non-embedded fonts\n- **Page count rules differ by venue** — ML conferences: main body to Conclusion (refs excluded). **IEEE venues: total pages including references.**\n\n## Common Venue Requirements\n\n| Venue | Style File | Citation | Page Limit | Refs in limit? | Submission |\n|-------|-----------|----------|------------|----------------|------------|\n| ICLR 2026 | `iclr2026_conference.sty` | `natbib` (`\\citep`\u002F`\\citet`) | 9 pages (to Conclusion end) | No | OpenReview |\n| NeurIPS 2025 | `neurips_2025.sty` | `natbib` (`\\citep`\u002F`\\citet`) | 9 pages (to Conclusion end) | No | OpenReview |\n| ICML 2025 | `icml2025.sty` | `natbib` (`\\citep`\u002F`\\citet`) | 8 pages (to Conclusion end) | No | OpenReview |\n| IEEE Journal | `IEEEtran.cls` [journal] | `cite` (`\\cite{}`, numeric) | ~12-14 pages (Transactions) \u002F ~4-5 (Letters) | **Yes** | IEEE Author Portal \u002F ScholarOne |\n| IEEE Conference | `IEEEtran.cls` [conference] | `cite` (`\\cite{}`, numeric) | 5-8 pages (varies by conf) | **Yes** | EDAS \u002F IEEE Author Portal |\n","# Paper Compile: LaTeX to Submission-Ready PDF\n\nCompile the LaTeX paper and fix any issues: **$ARGUMENTS**\n\n## Constants\n\n- **COMPILER = `latexmk`** — LaTeX build tool. Handles multi-pass compilation automatically.\n- **ENGINE = `pdflatex`** — LaTeX engine. Options: `pdflatex` (default), `xelatex` (for CJK\u002Fcustom fonts), `lualatex`.\n- **MAX_COMPILE_ATTEMPTS = 3** — Maximum attempts to fix errors and recompile.\n- **PAPER_DIR = `paper\u002F`** — Directory containing LaTeX source files.\n- **MAX_PAGES** — Page limit. ML conferences: main body to Conclusion end (excluding references & appendix). ICLR=9, NeurIPS=9, ICML=8. **IEEE venues: references ARE included in page count.** IEEE journal ≈ 12-14 pages, IEEE conference ≈ 5-8 pages (all inclusive).\n\n## Workflow\n\n### Step 1: Verify Prerequisites\n\nCheck that the compilation environment is ready:\n\n```bash\n# Check LaTeX installation\nwhich pdflatex && which latexmk && which bibtex\n\n# If not installed, provide instructions:\n# macOS: brew install --cask mactex-no-gui\n# Ubuntu: sudo apt-get install texlive-full\n# Server: conda install -c conda-forge texlive-core\n```\n\nVerify all required files exist:\n\n```bash\n# Must exist\nls $PAPER_DIR\u002Fmain.tex\n\n# Should exist\nls $PAPER_DIR\u002Freferences.bib\nls $PAPER_DIR\u002Fsections\u002F*.tex\nls $PAPER_DIR\u002Ffigures\u002F*.pdf 2>\u002Fdev\u002Fnull || ls $PAPER_DIR\u002Ffigures\u002F*.png 2>\u002Fdev\u002Fnull\n```\n\n### Step 2: First Compilation Attempt\n\n```bash\ncd $PAPER_DIR\n\n# Clean previous build artifacts\nlatexmk -C\n\n# Full compilation (pdflatex + bibtex + pdflatex × 2)\nlatexmk -pdf -interaction=nonstopmode -halt-on-error main.tex 2>&1 | tee compile.log\n```\n\n### Step 3: Error Diagnosis and Auto-Fix\n\nIf compilation fails, read `compile.log` and fix common errors:\n\n**Missing packages:**\n```\n! LaTeX Error: File `somepackage.sty' not found.\n```\n→ Install via `tlmgr install somepackage` or remove the `\\usepackage` if unused.\n\n**Undefined references:**\n```\nLaTeX Warning: Reference `fig:xyz' on page 3 undefined\n```\n→ Check `\\label{fig:xyz}` exists in the correct figure environment.\n\n**Missing figures:**\n```\n! LaTeX Error: File `figures\u002Ffig1.pdf' not found.\n```\n→ Check if the file exists with a different extension (.png vs .pdf). Update the `\\includegraphics` path.\n\n**Citation undefined:**\n```\nLaTeX Warning: Citation `smith2024' undefined\n```\n→ Add the missing entry to `references.bib` or fix the citation key.\n\n**`[VERIFY]` markers in text:**\n→ Search for `[VERIFY]` markers left by `\u002Fpaper-write`. These indicate unverified citations or facts. Search for the correct information or flag to the user.\n\n**Overfull hbox:**\n```\nOverfull \\hbox (12.5pt too wide) in paragraph at lines 42--45\n```\n→ Minor: usually ignorable. If severe (>20pt), rephrase the text or adjust figure width.\n\n**BibTeX errors:**\n```\nI was expecting a `,' or a `}'---line 15 of references.bib\n```\n→ Fix BibTeX syntax (missing comma, unmatched braces, special characters in title).\n\n**`\\crefname` undefined for custom theorem types:**\n→ Ensure `\\crefname{assumption}{Assumption}{Assumptions}` and similar are in the preamble after `\\newtheorem{assumption}`.\n\n### Step 4: Iterative Fix Loop\n\n```\nfor attempt in 1..MAX_COMPILE_ATTEMPTS:\n    compile()\n    if success:\n        break\n    parse_errors()\n    auto_fix()\n```\n\nFor each error:\n1. Read the error message from `compile.log`\n2. Locate the source file and line number\n3. Apply the fix\n4. Recompile\n\n**Stuck after 2 attempts?** If Codex plugin is installed, invoke `\u002Fcodex:rescue` — Codex can independently read the LaTeX source and `compile.log` to spot issues Claude missed (e.g., conflicting packages, encoding problems, subtle macro errors). If not installed, continue with Claude's own diagnosis.\n\n### Step 5: Post-Compilation Checks\n\nAfter successful compilation, verify the output:\n\n```bash\n# Check PDF exists and has content\nls -la main.pdf\n# Check page count\npdfinfo main.pdf | grep Pages\n\n# macOS: open for visual inspection\n# open main.pdf\n```\n\n**Visual review (automated):**\nIf the compiled PDF exists, read it directly to check visual presentation:\n- Figure quality: readable labels, legible text, distinguishable colors\n- Layout: no orphaned section headers, no awkward page breaks\n- Figures appear near their first text reference (not pages away)\n- Tables: aligned columns, consistent decimal precision\n- No overfull content visibly extending past margins\n\nThis is a quick visual scan, not a full review — the improvement loop does deeper visual review.\n\n**Automated checks:**\n\n- [ ] PDF file exists and is > 100KB (not empty\u002Fcorrupt)\n- [ ] Total page count is reasonable (MAX_PAGES + appendix + references)\n- [ ] No \"??\" in the PDF (undefined references — grep the log)\n- [ ] No \"[?]\" in the PDF (undefined citations — grep the log)\n- [ ] Figures are rendered (not missing image placeholders)\n\n```bash\n# Check for undefined references\ngrep -c \"LaTeX Warning.*undefined\" compile.log\n\n# Check for missing citations\ngrep -c \"Citation.*undefined\" compile.log\n```\n\n### Step 6: Page Count Verification\n\n**CRITICAL**: Verify paper fits within MAX_PAGES.\n\n**For ML conferences (ICLR\u002FNeurIPS\u002FICML\u002FCVPR\u002FACL\u002FAAAI):** Main body = first page through end of Conclusion section (not necessarily §5 — could be §6, §7, or §8 depending on structure). References and appendix are NOT counted.\n\n**For IEEE venues:** The TOTAL page count (including references) must fit within the limit. There is no separate \"main body\" counting — everything up to and including the references counts.\n\n**Precise check using `pdftotext`:**\n```bash\n# Extract text and find where Conclusion ends vs References begin\npdftotext main.pdf - | python3 -c \"\nimport sys\ntext = sys.stdin.read()\npages = text.split('\\f')\nfor i, page in enumerate(pages):\n    if 'Ethics Statement' in page or 'Reproducibility' in page:\n        print(f'Conclusion ends on page {i+1}')\n    if any(w in page for w in ['References', 'Bibliography']):\n        lines = [l for l in page.split('\\n') if l.strip()]\n        for l in lines[:3]:\n            if 'References' in l or 'Bibliography' in l:\n                print(f'References start on page {i+1}')\n                break\n\"\n```\n\nIf Conclusion ends mid-page and References start on the same page, the main body is that page number (e.g., if both are on page 9, main body = ~8.5 pages, which is fine for a 9-page limit since it leaves room for the References header).\n\nIf over limit:\n- Identify which sections are longest\n- Suggest specific cuts (move proofs to appendix, compress tables, tighten writing)\n- Report: \"Main body is X pages (limit: MAX_PAGES). Suggestion: move [specific content] to appendix.\"\n\n### Step 6.5: Stale File Detection\n\nCheck for orphaned section files not referenced by `main.tex`:\n\n```bash\n# Find all .tex files in sections\u002F and check which are \\input'ed by main.tex\nfor f in paper\u002Fsections\u002F*.tex; do\n    base=$(basename \"$f\")\n    if ! grep -q \"$base\" paper\u002Fmain.tex; then\n        echo \"WARNING: $f is not referenced by main.tex — consider removing\"\n    fi\ndone\n```\n\nThis prevents confusion from leftover files when section structure changes (e.g., old `5_conclusion.tex` left behind after restructuring to 7 sections).\n\n### Step 7: Submission Readiness\n\nFor conference submission, additional checks:\n\n- [ ] **Anonymous**: no author names, affiliations, or self-citations that reveal identity\n- [ ] **Page limit**: main body within MAX_PAGES (to end of Conclusion)\n- [ ] **Font embedding**: all fonts embedded in PDF\n  ```bash\n  pdffonts main.pdf | grep -v \"yes\"  # should return nothing (or only header)\n  ```\n- [ ] **No supplementary mixed in**: appendix clearly after `\\newpage\\appendix`\n- [ ] **File size**: reasonable (\u003C 50MB for most venues, \u003C 10MB preferred)\n- [ ] **No `[VERIFY]` markers**: search the PDF text for leftover markers\n\n### Step 8: Output Summary\n\n```markdown\n## Compilation Report\n\n- **Status**: SUCCESS \u002F FAILED\n- **PDF**: paper\u002Fmain.pdf\n- **Pages**: X (main body to Conclusion) + Y (references) + Z (appendix)\n- **Within page limit**: YES\u002FNO (MAX_PAGES = N)\n- **Errors fixed**: [list of auto-fixed issues]\n- **Warnings remaining**: [list of non-critical warnings]\n- **Undefined references**: 0\n- **Undefined citations**: 0\n\n### Next Steps\n- [ ] Visual inspection of PDF\n- [ ] Run `\u002Fpaper-write` to fix any content issues\n- [ ] Submit to [venue] via OpenReview \u002F CMT \u002F HotCRP\n```\n\n## Key Rules\n\n- **Never delete the user's source files** — only modify to fix errors\n- **Keep compile.log** — useful for debugging\n- **Don't suppress warnings** — report them, let the user decide\n- **If LaTeX is not installed**, provide clear installation instructions rather than failing silently\n- **Font embedding is critical** — some venues reject PDFs with non-embedded fonts\n- **Page count rules differ by venue** — ML conferences: main body to Conclusion (refs excluded). **IEEE venues: total pages including references.**\n\n## Common Venue Requirements\n\n| Venue | Style File | Citation | Page Limit | Refs in limit? | Submission |\n|-------|-----------|----------|------------|----------------|------------|\n| ICLR 2026 | `iclr2026_conference.sty` | `natbib` (`\\citep`\u002F`\\citet`) | 9 pages (to Conclusion end) | No | OpenReview |\n| NeurIPS 2025 | `neurips_2025.sty` | `natbib` (`\\citep`\u002F`\\citet`) | 9 pages (to Conclusion end) | No | OpenReview |\n| ICML 2025 | `icml2025.sty` | `natbib` (`\\citep`\u002F`\\citet`) | 8 pages (to Conclusion end) | No | OpenReview |\n| IEEE Journal | `IEEEtran.cls` [journal] | `cite` (`\\cite{}`, numeric) | ~12-14 pages (Transactions) \u002F ~4-5 (Letters) | **Yes** | IEEE Author Portal \u002F ScholarOne |\n| IEEE Conference | `IEEEtran.cls` [conference] | `cite` (`\\cite{}`, numeric) | 5-8 pages (varies by conf) | **Yes** | EDAS \u002F IEEE Author Portal |\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(*), Read, Write, Edit, Grep, Glob","[paper-directory]","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-compile",0,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science","https:\u002F\u002Fgithub.com\u002FCZX-LBJ","一个没事喜欢随便写点代码的小菜鸡\r\n","2026-10-22 09:48:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill paper-compile",{"tool":40,"command":41},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill paper-compile",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill paper-compile","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpaper-compile\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7FEEKSNMRMKW6JEK93PFDFY","bio-free-energy-calculations","Performs alchemical free-energy calculations including relative binding free energy (RBFE \u002F FEP+) and absolute binding free energy (ABFE) via OpenFE, FEP+, GROMACS, AMBER pmemd, and OpenMM with explicit lambda scheduling, soft-core potentials, MBAR\u002FBAR analysis, cycle-closure validation, and protocol-appropriate enhanced sampling. Compares ML alternatives (Boltz-2 affinity, DeepDock). Use when ranking analogs by binding affinity beyond docking accuracy, performing prospective lead optimization, or validating SAR predictions.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Ffree-energy-calculations\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7FEE5CTE5QK55CEMXNNVWY9","bio-conformer-generation","Generates 3D conformer ensembles using RDKit ETKDGv3 with knowledge-enhanced distance geometry, MMFF94\u002FUFF force-field optimization, CREST + GFN2-xTB semi-empirical refinement, and macrocycle-aware torsion preferences. Provides explicit decision rules for single vs ensemble conformer use, RMSD pruning, energy windows, conformer count, and force-field choice. Use when preparing 3D ligands for docking, generating descriptor input for 3D QSAR, or sampling macrocycle\u002Fpeptide conformational ensembles.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fconformer-generation\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7FEDNGFEMFWD1MSEDR5H7CY","bio-admet-prediction","Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG\u002FCYP\u002FAMES endpoints, and PAINS \u002F Lipinski \u002F Ro5 \u002F Veber \u002F BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fadmet-prediction\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FED69GFB54FRF7AV5066DN","writing-systems-papers","Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says \"写系统论文\", \"systems paper structure\", \"OSDI paper\", \"SOSP paper\", or wants fine-grained structural guidance for a systems conference submission.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FECVVDWZ0X0VEDTCE4B4DZ","wiki-enrich","Fill in the per-paper TODO sections of research-wiki\u002Fpapers\u002F\u003Cslug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers\u002F as TODO scaffolds.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwiki-enrich\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FECD4BCJ2MTSBDDSE3ZAJ5","web-debug-search","Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fweb-debug-search\u002FSKILL.md",[],[]]