Skip to content

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

paper-audit

Verified

Deep-review-first audit for Chinese and English academic papers across LaTeX, Typst, and PDF formats. Use whenever the user wants reviewer-style paper critique, pre-submission readiness checks, pass/fail gate decisions, structured revision roadmaps, or re-audits of revised manuscripts. Trigger even if the user only says "review my paper", "check if this is ready to submit", "audit this PDF", "simulate peer review", "find the biggest problems in this manuscript", or "re-check whether I fixed the review issues". Do not use for direct source editing or compilation-heavy repair; route those to the format-specific writing skills instead.

FileKindSize
SKILL.mdskill md14.3 KB
agents/claims_evidence_reviewer_agent.mdmarkdown354 B
agents/committee_editor_agent.mdmarkdown1.9 KB
agents/committee_literature_agent.mdmarkdown1.9 KB
agents/committee_logic_agent.mdmarkdown1.5 KB
agents/committee_methodology_agent.mdmarkdown1.8 KB
agents/committee_theory_agent.mdmarkdown1.9 KB
agents/critical_reviewer_agent.mdmarkdown8.4 KB
agents/domain_reviewer_agent.mdmarkdown7.1 KB
agents/editor_in_chief_agent.mdmarkdown5.2 KB
agents/evaluation_fairness_reviewer_agent.mdmarkdown371 B
agents/literature_reviewer_agent.mdmarkdown3.6 KB
agents/methodology_reviewer_agent.mdmarkdown7.2 KB
agents/notation_consistency_reviewer_agent.mdmarkdown398 B
agents/prior_art_reviewer_agent.mdmarkdown2.9 KB
agents/section_reviewer_agent.mdmarkdown365 B
agents/self_consistency_reviewer_agent.mdmarkdown420 B
agents/synthesis_agent.mdmarkdown951 B
evals/evals.jsonconfig12.0 KB
evals/fixtures/deep_review_fixture.texother699 B
evals/fixtures/gate_ieee_fixture.texother617 B
evals/fixtures/polish_fixture.texother396 B
evals/fixtures/previous_final_issues.jsonconfig1.1 KB
evals/fixtures/previous_review_report.mdmarkdown205 B
evals/fixtures/quick_audit_fixture.texother538 B
examples/gate_example.mdmarkdown3.5 KB
examples/review_example.mdmarkdown2.5 KB
examples/self_check_example.mdmarkdown2.9 KB
references/AUDIT_GUIDE.mdmarkdown3.4 KB
references/CHANGELOG.mdmarkdown530 B
references/CHECKLIST.mdmarkdown6.0 KB
references/CONSOLIDATION_RULES.mdmarkdown907 B
references/DEEP_REVIEW_CRITERIA.mdmarkdown2.8 KB
references/FORBIDDEN_TERMS.mdmarkdown6.4 KB
references/ISSUE_SCHEMA.mdmarkdown928 B
references/LITERATURE_GROUNDING_GUIDE.mdmarkdown3.3 KB
references/POLISH_GUIDE.mdmarkdown2.3 KB
references/QUALITATIVE_STANDARDS.mdmarkdown5.5 KB
references/QUICK_REFERENCE.mdmarkdown1.1 KB
references/REVIEW_CRITERIA.mdmarkdown2.7 KB
references/REVIEW_LANE_GUIDE.mdmarkdown828 B
references/SCHOLAR_EVAL_GUIDE.mdmarkdown6.4 KB
references/SCORING_SYSTEMS.mdmarkdown1000 B
references/SUBAGENT_TEMPLATES.mdmarkdown987 B
references/TROUBLESHOOTING.mdmarkdown1.4 KB
references/VENUE_RULES.mdmarkdown764 B
references/editorial_decision_standards.mdmarkdown6.7 KB
references/quality_rubrics.mdmarkdown10.8 KB
scripts/audit.pyscript78.4 KB
scripts/build_claim_map.pyscript3.3 KB
scripts/check_citations.pyscript5.6 KB
scripts/check_references.pyscript19.9 KB
scripts/consolidate_review_findings.pyscript5.2 KB
scripts/detect_language.pyscript1.9 KB
scripts/diff_review_issues.pyscript2.0 KB
scripts/literature_compare.pyscript11.4 KB
scripts/literature_search.pyscript22.0 KB
scripts/models/scoring_model.jsonconfig737 B
scripts/parsers.pyscript3.3 KB
scripts/pdf_parser.pyscript11.4 KB
scripts/prepare_review_workspace.pyscript6.8 KB
scripts/render_deep_review_report.pyscript3.5 KB
scripts/report_generator.pyscript36.2 KB
scripts/scholar_eval.pyscript13.7 KB
scripts/scoring_model.pyscript6.2 KB
scripts/verify_quotes.pyscript1.6 KB
scripts/visual_check.pyscript10.7 KB
templates/audit_report_template.mdmarkdown2.8 KB
templates/final_issues_template.jsonconfig498 B
templates/review_report_template.mdmarkdown678 B
templates/revision_roadmap_template.mdmarkdown3.1 KB

references/FORBIDDEN_TERMS.md

View on GitHub
# FORBIDDEN_TERMS.md

Protected terms and constructs that **must never be modified** without explicit user confirmation.
These rules apply to all audit modes (`quick-audit`, `deep-review`, `gate`, `polish`, and compatibility aliases).

---

## 1. LaTeX Command Protection List

The following LaTeX commands must **never** be altered in content, spelling, or structure:

| Command | Reason | Example |
|---------|--------|---------|
| `\cite{key}` | Bibliography reference — changing key breaks citation | `\cite{lecun1998}` |
| `\citep{key}` | Parenthetical citation | `\citep{vaswani2017}` |
| `\citet{key}` | Textual citation | `\citet{hinton2006}` |
| `\ref{label}` | Cross-reference — changing breaks link | `\ref{fig:arch}` |
| `\eqref{label}` | Equation reference | `\eqref{eq:loss}` |
| `\autoref{label}` | Auto-typed reference | `\autoref{tab:results}` |
| `\cref{label}` | cleveref reference | `\cref{fig:overview}` |
| `\Cref{label}` | cleveref uppercase reference | `\Cref{tab:ablation}` |
| `\pageref{label}` | Page reference | `\pageref{sec:method}` |
| `\hyperref[label]{text}` | Hyperlink reference | `\hyperref[sec:exp]{Section 3}` |
| `\label{key}` | Label definition — changing breaks all refs | `\label{fig:arch}` |
| `\bibliography{file}` | Bibliography file reference | `\bibliography{references}` |
| `\bibliographystyle{style}` | Bibliography style | `\bibliographystyle{plain}` |
| `\input{file}` | File inclusion | `\input{sections/intro}` |
| `\include{file}` | File inclusion with page break | `\include{chapter1}` |

---

## 2. Typst Command Protection List

| Command | Reason | Example |
|---------|--------|---------|
| `@key` | Bibliography citation | `@lecun1998` |
| `#cite(<key>)` | Citation function | `#cite(<vaswani2017>)` |
| `#ref(<label>)` | Cross-reference | `#ref(<fig:arch>)` |
| `<label>` | Label definition | `<fig:overview>` |
| `#include "file"` | File inclusion | `#include "sections/intro.typ"` |
| `#bibliography("file")` | Bibliography file | `#bibliography("refs.bib")` |

---

## 3. Math Environment Protection List

These environments contain mathematical content — **never** modify the LaTeX/Typst code inside them:

### LaTeX Math Environments
- `$...$` — Inline math
- `$$...$$` — Display math (deprecated but protected)
- `\(...\)` — Inline math (preferred)
- `\[...\]` — Display math (preferred)
- `\begin{equation}...\end{equation}`
- `\begin{equation*}...\end{equation*}`
- `\begin{align}...\end{align}`
- `\begin{align*}...\end{align*}`
- `\begin{aligned}...\end{aligned}`
- `\begin{gather}...\end{gather}`
- `\begin{gather*}...\end{gather*}`
- `\begin{multline}...\end{multline}`
- `\begin{cases}...\end{cases}`
- `\begin{array}...\end{array}`
- `\begin{matrix}...\end{matrix}` (and variants: pmatrix, bmatrix, vmatrix)

### Typst Math Environments
- `$...$` — Inline math
- `$ ... $` — Display math (with spaces)

### Why Protected
Math expressions may contain domain-specific notation. Modifying symbols, operators, or
indices can silently change mathematical meaning without being syntactically wrong.

---

## 4. Domain Terminology Freeze List

These terms appear frequently in academic writing but have **precise technical meanings**.
Do **not** suggest synonyms or rewrites without user confirmation:

### Computer Science / Machine Learning
- **gradient descent** (not "slope descent" or "derivative minimization")
- **backpropagation** (not "backward propagation algorithm")
- **attention mechanism** / **self-attention** / **cross-attention**
- **transformer** (architecture, capitalized in "Transformer" when referring to the architecture)
- **perplexity** (NLP metric — not "confusion" or "uncertainty")
- **overfitting** / **underfitting** / **generalization gap**
- **hyperparameter** (not "meta-parameter" or "configuration parameter" in ML context)
- **fine-tuning** / **pre-training** / **transfer learning**
- **tokenization** / **tokenizer** / **subword tokenization**
- **embedding** (vector representation — not "encoding" interchangeably)
- **batch normalization** / **layer normalization** / **instance normalization**
- **dropout** (regularization technique)
- **cross-entropy loss** / **KL divergence** / **ELBO**
- **precision** / **recall** / **F1 score** (classification metrics — not synonyms)
- **BLEU** / **ROUGE** / **METEOR** (evaluation metrics — not interchangeable)

### Mathematics / Statistics
- **convex** / **concave** (not interchangeable)
- **bijective** / **injective** / **surjective** (not interchangeable)
- **stochastic** (not synonymous with "random" in all contexts)
- **expectation** / **variance** / **covariance** (statistical terms)
- **null hypothesis** / **p-value** / **statistical significance**
- **Monte Carlo** (proper noun — always capitalized)

### General Academic Terms
- **ablation study** (not "component analysis" or "removal experiment")
- **state-of-the-art** / **SOTA** (not "best-performing" without context)
- **baseline** (comparison reference — not synonymous with "default")
- **benchmark** (standardized evaluation — not synonymous with "test")
- **corpus** / **corpora** (linguistic dataset — not "dataset" in all contexts)

---

## 5. Usage Rules for Tools

When an audit module encounters any of the above:

1. **SKIP**: Do not flag the protected construct as an issue.
2. **CONTEXT-ONLY**: Surrounding text may be analyzed, but the protected term/command itself is off-limits.
3. **CONFIRM**: If a change to a protected term is genuinely needed (e.g., broken `\ref` with no matching `\label`), report it as an **issue** but do **not** auto-fix.
4. **REPORT**: Reference-integrity issues (`\ref` with no `\label`) should be reported via `check_references.py`, not silently corrected.

---

## 6. Audit Module Compliance

| Module | Must Skip | Must Report |
|--------|-----------|-------------|
| `analyze_grammar.py` | All math environments, all `\cite`, `\ref`, `\label` | None |
| `analyze_logic.py` | Math environments, citation content | Structural logic issues only |
| `analyze_sentences.py` | All math environments | Sentence-level issues in prose |
| `deai_check.py` | Math environments, citation keys | AI-generated patterns in prose |
| `check_format.py` | Math environments, citations | Format violations in metadata |
| `check_references.py` | Nothing (this is the reporter) | All broken/missing references |
| `verify_bib.py` | Nothing (this is the reporter) | All bib integrity issues |
| `visual_check.py` | All text content | Layout/visual issues only |

---

*Last updated: 2026-02-27*
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