7. Writing & Documentation

Polishes single H3 section files into survey-grade prose by removing templates and adding evaluation/limitations while preserving citations and structure.

Performs final consistency and coherence review of survey drafts, ensuring terminology alignment and citation hygiene without adding new content.

Automates removal of repeated boilerplate (disclaimers, summaries) in documents while preserving citations and meaning.

Generates a section-by-section claim-evidence matrix from outline and paper notes to organize arguments before writing prose.

Synthesizes evidence from extraction tables into a structured narrative document with explicit limitations and bias considerations for systematic reviews.

Generates lightweight section transitions using existing outline titles and research questions to ensure coherent flow without adding new facts or citations.

Generates evidence-based academic paragraphs following tension-contrast-evaluation-limitation structure for research documentation sections.

Extracts concrete numeric facts from evidence packs to enforce evidence-anchored writing in documentation, avoiding generic summaries.

Generates structured prose drafts from approved outlines and evidence packs, using only verified citations from a reference bibliography.

Normalizes terminology in written drafts using canonical terms and synonym policies while preserving citations and meaning.

Creates a structured systematic review protocol document with defined search strategies, inclusion/exclusion criteria, and extraction fields for research reproducibility.

Creates a structured tutorial specification including scope, target audience, prerequisites, learning objectives, and a running example for planning tutorial development.

Creates an evidence-driven claim-evidence index from evidence drafts and citations, aligned with evidence packs for QA and writing.

Audits evidence supporting claims in documentation, identifying gaps and risks to enhance content reliability.

Compiles LaTeX projects, checks for missing references and bibliography errors, and generates a PDF with a build report.

Automates iterative rewriting of failing survey sections (*.md) to achieve quality gate PASS using existing citations and evidence bindings.

Polishes technical drafts by removing template boilerplate, enhancing coherence, and ensuring proper citation anchoring without altering content or claims.

Creates evidence-driven subsection briefs without prose, using existing paper references to guide drafting via checkable comparison axes.

Generates H2-level chapter briefs to ensure coherent chapter leads and cross-H3 flow in documents, avoiding prose and ToC inflation.

Automates splitting survey content into individual section files for independent QA, ensuring evidence-bounded drafting without monolithic drafts.

Enforces explicit thesis statements and logical connectors in section files to eliminate disconnected paragraphs before merging.

Creates tutorial content with exercises and answer outlines from approved module plans, maintaining running example consistency.

Creates a 24-48 hour literature snapshot in bullet-point format from a core paper set, using only provided citations and avoiding long paragraphs.

Creates a peer review report in Markdown format using extracted claims and evidence gaps, covering novelty, soundness, clarity, and impact with actionable feedback.