Fill `outline/tables_index.md` from `outline/table_schema.md` + evidence packs (NO PROSE in cells; citation-backed rows).
The English summary is being prepared. Showing the original description.
Build a 2+ level taxonomy (`outline/taxonomy.yml`) from a core paper set and scope constraints, with short descriptions per node.
The English summary is being prepared. Showing the original description.
Normalize terminology across a draft (canonical terms + synonym policy) without changing citations or meaning.
The English summary is being prepared. Showing the original description.
为中文毕业论文补强并核验引用：找出必须有引文支撑的句子，扩展候选文献，检查引用与论断是否匹配，并回写参考文献与正文引用。
The English summary is being prepared. Showing the original description.
对中文毕业论文进行编译、warning 分级、模板模式检查、数据与引用复查，并把问题回写成可继续迭代的 review checklist。
The English summary is being prepared. Showing the original description.
在 Markdown 中间层统一毕业论文的主线、术语、符号、指标、图表口径与章节边界，让整篇论文先在中间层收敛成“一篇论文”。
The English summary is being prepared. Showing the original description.
维护中文毕业论文的 `codex_md/question_list.md`：把本轮问题、边界、优先级、协作方案和验收口径结构化，作为整条 thesis pipeline 的控制面。
The English summary is being prepared. Showing the original description.
将中文毕业论文已有材料映射到“毕业论文角色”：把论文、模板、Overleaf 源稿、PDF、图表和实验材料按章节角色、研究问题和证据用途重新归位。
The English summary is being prepared. Showing the original description.
对中文毕业论文做最终润色与去 AI 味：重点处理章首导言、章末小结、贡献描述、总结与展望中的模板腔、宣传腔与 AI 口癖。
The English summary is being prepared. Showing the original description.
初始化中文毕业论文工作区：检查学校模板与已有材料的放置位置，明确提示当前还缺什么，建立 `codex_md/` / `claude_md/` / `tmp_layout*/` 等中间层目录，并生成材料盘点与初始工作文件。
The English summary is being prepared. Showing the original description.
Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`.
The English summary is being prepared. Showing the original description.
Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance.
The English summary is being prepared. Showing the original description.
Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to fix) before writing more prose.
The English summary is being prepared. Showing the original description.
Use when a tutorial module plan exists but each module still needs a verifiable teaching loop.
The English summary is being prepared. Showing the original description.
Use when `evidence-review` has screened includes and needs a schema-aligned extraction table.
The English summary is being prepared. Showing the original description.
Write the survey's front matter files (Abstract, Introduction, Related Work, Discussion, Conclusion) in paper voice, with high citation density and a single evidence-policy paragraph.
The English summary is being prepared. Showing the original description.
Generate a compact pool of discussion-worthy research directions from the signal table, writing `output/trace/IDEA_DIRECTION_POOL.md`.
The English summary is being prepared. Showing the original description.
Screen the direction pool with a discussion-first scoring pass, writing `output/trace/IDEA_SCREENING_TABLE.md`.
The English summary is being prepared. Showing the original description.
Expand and refine search keywords (synonyms, acronyms, exclusions) and update `queries.md`.
The English summary is being prepared. Showing the original description.
Compile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report.
The English summary is being prepared. Showing the original description.
Scaffold a LaTeX project (`latex/main.tex`, optional bibliography wiring, structure) from an existing Markdown draft.
The English summary is being prepared. Showing the original description.
Rewrite limitation passages so the paper keeps limitations without falling into count-based slot phrases (e.g., \"Two limitations…\") across many H3s.
The English summary is being prepared. Showing the original description.
Multi-route literature expansion + metadata normalization for evidence-first surveys.
The English summary is being prepared. Showing the original description.
Use when `paper-review` needs a canonical manuscript text artifact before claim extraction.
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)