Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/35-bahayonghang-academic-writing-skills/skills/latex-paper-en

latex-paper-en

Verified

English LaTeX academic paper assistant for existing `.tex` projects. Use this skill whenever the user wants to compile, lint, audit, or improve an English LaTeX conference or journal paper such as IEEE, ACM, Springer, NeurIPS, or ICML submissions. Trigger even when the user only mentions one paper issue, such as bibliography errors, grammar cleanup, sentence splitting, logic review, expression polishing, translation, title optimization, figure checks, pseudocode review, algorithm block cleanup, de-AI editing, experiment-section review, table structure validation, three-line table generation, abstract structure diagnosis, or journal adaptation. Also trigger for "proofread my paper", "fix my LaTeX", "prepare for submission", "check my manuscript", "improve my writing", "three-line table", "booktabs", "check abstract", "reformat for another journal", "换投", `algorithm2e`, `algorithmicx`, `algpseudocodex`, `Require/Ensure`, or "Algorithm 1" when the user has a .tex file.

FileKindSize
SKILL.mdskill md8.5 KB
agents/openai.yamlconfig390 B
evals/evals.jsonconfig7.8 KB
examples/compile-and-bibliography.mdmarkdown551 B
examples/experiment-review.mdmarkdown527 B
examples/figures-and-title.mdmarkdown513 B
examples/grammar-and-logic.mdmarkdown687 B
examples/translation-and-deai.mdmarkdown630 B
references/ABSTRACT_STRUCTURE.mdmarkdown4.9 KB
references/BEST_PRACTICES.mdmarkdown456 B
references/CITATION_STYLES.mdmarkdown4.2 KB
references/CITATION_VERIFICATION.mdmarkdown4.1 KB
references/COMMON_ERRORS.mdmarkdown2.8 KB
references/COMPILATION.mdmarkdown2.0 KB
references/DEAI_GUIDE.mdmarkdown16.8 KB
references/FORBIDDEN_TERMS.mdmarkdown1.6 KB
references/JOURNAL_ABBREVIATIONS.mdmarkdown3.5 KB
references/JOURNAL_ADAPTATION_WORKFLOW.mdmarkdown3.6 KB
references/NUMBER_UNIT_GUIDE.mdmarkdown2.3 KB
references/REVIEWER_PERSPECTIVE.mdmarkdown4.9 KB
references/STYLE_GUIDE.mdmarkdown6.5 KB
references/TABLE_GUIDE.mdmarkdown3.7 KB
references/TERMINOLOGY.mdmarkdown9.9 KB
references/TRANSLATION_GUIDE.mdmarkdown11.4 KB
references/VENUES.mdmarkdown6.4 KB
references/WRITING_PHILOSOPHY.mdmarkdown6.7 KB
references/modules/ABSTRACT.mdmarkdown1.2 KB
references/modules/ADAPT.mdmarkdown1.3 KB
references/modules/BIBLIOGRAPHY.mdmarkdown1.3 KB
references/modules/CAPTION.mdmarkdown2.0 KB
references/modules/COMPILE.mdmarkdown2.8 KB
references/modules/DEAI.mdmarkdown1.0 KB
references/modules/EXPERIMENT.mdmarkdown3.8 KB
references/modules/EXPRESSION.mdmarkdown789 B
references/modules/FORMAT.mdmarkdown440 B
references/modules/GRAMMAR.mdmarkdown980 B
references/modules/LOGIC.mdmarkdown7.6 KB
references/modules/PSEUDOCODE.mdmarkdown1.7 KB
references/modules/SENTENCES.mdmarkdown575 B
references/modules/TABLES.mdmarkdown1.3 KB
references/modules/TITLE.mdmarkdown7.7 KB
references/modules/TRANSLATION.mdmarkdown1.1 KB
references/modules/WORKFLOW.mdmarkdown910 B
scripts/analyze_abstract.pyscript17.3 KB
scripts/analyze_experiment.pyscript18.1 KB
scripts/analyze_grammar.pyscript3.6 KB
scripts/analyze_logic.pyscript18.4 KB
scripts/analyze_sentences.pyscript3.6 KB
scripts/check_figures.pyscript6.4 KB
scripts/check_format.pyscript6.4 KB
scripts/check_pseudocode.pyscript11.2 KB
scripts/check_references.pyscript14.2 KB
scripts/check_tables.pyscript16.3 KB
scripts/compile.pyscript17.4 KB
scripts/deai_batch.pyscript9.9 KB
scripts/deai_check.pyscript16.4 KB
scripts/extract_prose.pyscript2.7 KB
scripts/generate_table.pyscript8.8 KB
scripts/improve_expression.pyscript3.2 KB
scripts/online_bib_verify.pyscript11.9 KB
scripts/optimize_title.pyscript15.4 KB
scripts/parsers.pyscript14.9 KB
scripts/translate_academic.pyscript5.1 KB
scripts/verify_bib.pyscript18.9 KB

evals/evals.json

View on GitHub
{
  "skill_name": "latex-paper-en",
  "evals": [
    {
      "id": 1,
      "prompt": "Compile my IEEE paper in main.tex, then explain why two citations are unresolved after BibTeX.",
      "expected_output": "Select compile and bibliography modules, run the correct commands in sequence, and report the build plus citation findings in LaTeX-oriented review format with exact failing steps, exit codes, or unresolved keys.",
      "files": [],
      "assertions": [
        {"type": "regex", "pattern": "(compile|bibliography)", "description": "correct modules routed"},
        {"type": "regex", "pattern": "\\\\cite\\{", "description": "\\cite{} references preserved"},
        {"type": "regex", "pattern": "(exit code|error|unresolved)", "description": "build diagnostics reported"}
      ]
    },
    {
      "id": 2,
      "prompt": "Review the introduction section for grammar, sentence length, and logic, but do not touch equations or citation keys.",
      "expected_output": "Route to grammar, sentences, and logic modules with source-preserving comments, keeping equations, citation keys, labels, and math untouched.",
      "files": [],
      "assertions": [
        {"type": "regex", "pattern": "(grammar|sentences|logic)", "description": "correct modules routed"},
        {"type": "not_contains", "text": "\\cite{", "description": "citation keys not rewritten"},
        {"type": "regex", "pattern": "% .+\\[Severity:", "description": "LaTeX comment format used"}
      ]
    },
    {
      "id": 3,
      "prompt": "Before I submit to ACM, check whether my figures are publication-ready and whether the title sounds too generic.",
      "expected_output": "Route to figures and title modules and return concrete pre-submission findings about figure readiness, missing assets, resolution risks, caption problems, or weak title wording.",
      "files": [],
      "assertions": [
        {"type": "regex", "pattern": "(figures|title)", "description": "correct modules routed"},
        {"type": "regex", "pattern": "(DPI|resolution|caption|figure)", "description": "figure quality assessed"},
        {"type": "regex", "pattern": "\\[Severity: (Critical|Major|Minor)\\]", "description": "severity format correct"}
      ]
    },
    {
      "id": 4,
      "prompt": "Translate this Chinese methods paragraph into academic English, but keep \\\\cite{zhang2024} and $L_{pred}$ unchanged and use deep-learning terminology.",
      "expected_output": "Route to the translation module, preserve LaTeX fragments verbatim, surface terminology choices, and avoid silently rewriting citations, labels, or math.",
      "files": [],
      "assertions": [
        {"type": "contains", "text": "translation", "description": "translation module routed"},
        {"type": "contains", "text": "\\cite{zhang2024}", "description": "citation key preserved verbatim"},
        {"type": "contains", "text": "$L_{pred}$", "description": "math expression preserved"}
      ]
    },
    {
      "id": 5,
      "prompt": "Check the introduction section for AI-sounding phrases and tell me what to revise, but do not rewrite labels, citations, or equations.",
      "expected_output": "Route to the deai module and return source-preserving findings, risk notes, and revision targets without editing labels, citations, or math environments.",
      "files": [],
      "assertions": [
        {"type": "contains", "text": "deai", "description": "deai module routed"},
        {"type": "regex", "pattern": "(AI.?writing|AI.?trace|AI.?pattern)", "description": "AI pattern detection present"},
        {"type": "not_contains", "text": "\\label{", "description": "labels not rewritten"}
      ]
    },
    {
      "id": 6,
      "prompt": "Review the experiments section for weak baselines, unsupported claims, missing ablations, and absent significance reporting, but do not draft a replacement paragraph.",
      "expected_output": "Route to the experiment module and return reviewer-style LaTeX comments about comparator specificity, metric evidence, ablation coverage, significance reporting, efficiency comparisons, results discussion, and overclaiming.",
      "files": [],
      "assertions": [
        {"type": "contains", "text": "experiment", "description": "experiment module routed"},
        {"type": "regex", "pattern": "(ablation|baseline|significance)", "description": "experiment criteria covered"},
        {"type": "regex", "pattern": "\\[Severity: (Critical|Major|Minor)\\]", "description": "severity format correct"}
      ]
    },
    {
      "id": 7,
      "prompt": "Check whether the introduction jumps from background directly to our method without establishing the technical bottleneck or prior-work limitations.",
      "expected_output": "Route to the logic module and flag introduction funnel breaks such as background-to-contribution jumps or missing prior-work insufficiency derivation.",
      "files": [],
      "assertions": [
        {"type": "contains", "text": "logic", "description": "logic module routed"},
        {"type": "regex", "pattern": "(funnel|gap|bottleneck|jump)", "description": "funnel analysis present"}
      ]
    },
    {
      "id": 8,
      "prompt": "Tell me whether the abstract, the contribution claims in the introduction, and the conclusion are saying the same core story or drifting apart.",
      "expected_output": "Route to the logic module and return a cross-section consistency finding about problem, method, key result, and contribution alignment.",
      "files": [],
      "assertions": [
        {"type": "contains", "text": "logic", "description": "logic module routed"},
        {"type": "regex", "pattern": "(cross-section|alignment|consistency|drift)", "description": "cross-section analysis present"}
      ]
    },
    {
      "id": 9,
      "prompt": "Review the discussion section and tell me whether it is layered enough, or if it just repeats results without mechanism, comparison, limitations, or implications.",
      "expected_output": "Route to the experiment module and report shallow or unlayered discussion structure with concrete section-level comments.",
      "files": [],
      "assertions": [
        {"type": "contains", "text": "experiment", "description": "experiment module routed"},
        {"type": "regex", "pattern": "(layer|mechanism|limitation|implication)", "description": "discussion depth assessed"}
      ]
    },
    {
      "id": 10,
      "prompt": "Check whether the pseudocode in my IEEE LaTeX paper still uses a floating algorithm environment or misses the caption and label conventions reviewers expect.",
      "expected_output": "Route to the pseudocode module, apply IEEE-aware checks, and separate hard float violations from caption, label, or reference hygiene issues.",
      "files": [],
      "assertions": [
        {"type": "contains", "text": "pseudocode", "description": "pseudocode module routed"},
        {"type": "regex", "pattern": "(IEEE|algorithm|caption|label)", "description": "IEEE-aware pseudocode review present"},
        {"type": "regex", "pattern": "\\[Severity: (Critical|Major|Minor)\\]", "description": "severity format correct"}
      ]
    },
    {
      "id": 11,
      "prompt": "Rewrite the guidance around this algorithm2e block so it becomes IEEE-safe, and tell me whether line numbers or Require/Ensure are mandatory or only recommended.",
      "expected_output": "Route to the pseudocode module, explain that floating algorithm environments are the hard issue, and clearly distinguish line numbers or Require/Ensure as IEEE-safe defaults rather than official mandates.",
      "files": [],
      "assertions": [
        {"type": "contains", "text": "pseudocode", "description": "pseudocode module routed"},
        {"type": "regex", "pattern": "(recommended|not required|IEEE-safe)", "description": "advisory distinction present"},
        {"type": "regex", "pattern": "(algorithm2e|figure)", "description": "migration guidance present"}
      ]
    }
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall