Agent skill
section-merger
Deterministically merge per-section files under `sections/` into `output/DRAFT.md`, preserving outline order and weaving transitions from `outline/transitions.md`. **Trigger**: merge sections, merge draft, combine section files, sections/ -> output/DRAFT.md, 合并小节, 拼接草稿. **Use when**: you have per-unit prose files under `sections/` and want a single `output/DRAFT.md` for polishing/review/LaTeX. **Skip if**: section files are missing or still contain scaffolding markers (fix `subsection-writer` first). **Network**: none. **Guardrail**: deterministic merge only (no new facts/citations); preserve section order from `outline/outline.yml`.
Install this agent skill to your Project
npx add-skill https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/section-merger
SKILL.md
Section Merger
Goal: assemble a paper-like output/DRAFT.md from:
sections/(per-section/per-subsection prose)outline/transitions.md(short hand-offs; generated bytransition-weaver)outline/tables_appendix.md(reader-facing Appendix tables; generated byappendix-table-writer)
Merge order is driven by outline/outline.yml. The draft title is taken from GOAL.md when present. sections/sections_manifest.jsonl is an optional diagnostics input.
This skill is deterministic: it does not rewrite content or invent prose; it only merges already-generated artifacts.
Transitions (injected text)
- By default,
section-mergerinserts only within-chapter H3->H3 transitions. - Optional: if you want between-H2 transitions inserted too, create
outline/transitions.insert_h2.okin the workspace. - Format contract: only lines matching
- 3.1 -> 3.2: <text>are injected by default. - Compatibility:
→is accepted, but->is the preferred contract (avoids control-character encoding issues). - Treat transitions as injected draft text: run
post-merge-voice-gateafter merging, and route fixes back tooutline/transitions.md(do not patch the merged draft).
Tables (two layers)
This pipeline uses two table layers:
-
outline/tables_index.md(internal index; produced bytable-filler)- planning/debugging artifact
- should NOT be inserted into the paper
-
outline/tables_appendix.md(reader-facing Appendix tables; produced byappendix-table-writer)- publishable tables (clean layout + high information density)
- inserted by
section-mergerunder a single Appendix heading
Appendix insertion behavior
section-mergerinsertsoutline/tables_appendix.mdat the end of the draft under## Appendix: Tables.- The inserted block is heading-free (any accidental
#headings inside the tables file are stripped). - Opt-out (rare): create
outline/tables.insert.offin the workspace.
Inputs
outline/outline.yml(drives section/subsection order)outline/transitions.md(required)sections/sections_manifest.jsonl(optional diagnostics)GOAL.md(optional title)
For arxiv-survey pipelines (default contract):
outline/tables_appendix.md(required unless opted out)
Outputs
output/DRAFT.mdoutput/MERGE_REPORT.md
Script
Quick Start
python .codex/skills/section-merger/scripts/run.py --helppython .codex/skills/section-merger/scripts/run.py --workspace workspaces/<ws>
All Options
--workspace <workspace_dir>(required)--unit-id <id>(optional; used only for runner bookkeeping)--inputs <a;b;c>(optional; override inputs; defaults are profile-aware)--outputs <draft_rel;report_rel>(optional; defaults tooutput/DRAFT.md;output/MERGE_REPORT.md)--checkpoint <C#>(optional; ignored by the merger)
Examples
-
Merge with defaults (profile-aware table insertion):
python .codex/skills/section-merger/scripts/run.py --workspace workspaces/<ws> -
Merge with explicit outputs:
python .codex/skills/section-merger/scripts/run.py --workspace workspaces/<ws> --outputs output/DRAFT.md;output/MERGE_REPORT.md
Troubleshooting
Issue: merge report says a subsection file is missing
Likely cause:
- A required
sections/*.mdfile has not been written yet.
Fix:
- Write the missing units under
sections/(typically viasubsection-writer) and rerun merge.
Issue: Appendix tables are missing in the merged draft
Fix:
- Ensure
outline/tables_appendix.mdexists and contains >=2 Markdown tables (no placeholders). - Ensure you did not create
outline/tables.insert.off. - Rerun
section-merger.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
thesis-compile-review
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。 **Trigger**: 毕业论文编译检查, thesis compile review, warning 分级, 终稿复查, main.pdf 检查. **Use when**: 论文已经回写到 TeX 交付层,需要确认是否真正达到“可提交”的质量,而不是只做到能编译。 **Skip if**: 还处于中间层重构阶段,`chapters/*.tex` 尚未形成稳定交付稿。 **Network**: none. **Guardrail**: 不在这里重构章节主线;如果发现结构问题,明确回退到上游修复。
front-matter-writer
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. **Trigger**: front matter writer, introduction writer, related work writer, abstract writer, discussion writer, conclusion writer, 引言, 相关工作, 摘要, 讨论, 结论. **Use when**: you are in C5 (prose allowed) and need the paper-like shell to stop the draft reading like stitched subsections. **Skip if**: `Approve C2` is missing in `DECISIONS.md`, or `citations/ref.bib` is missing. **Network**: none. **Guardrail**: no invented facts/citations; no pipeline jargon in final prose; no repeated evidence disclaimers; only use keys present in `citations/ref.bib`.
thesis-question-list
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。 **Trigger**: 毕业论文问题清单, thesis question list, 论文修改清单, 本轮目标, 结构问题梳理, review问题整理. **Use when**: 你已经有一批材料或上一轮 review 结果,需要明确这一轮到底修什么、不修什么,并给后续重构与编译复查提供统一入口。 **Skip if**: 当前只是在做一次性局部措辞修改,且没有形成新一轮结构/证据/编译问题。 **Network**: none. **Guardrail**: 不在这里写正文;不把问题单写成长篇散文;每条问题必须可执行、可验收。
novelty-matrix
Create a novelty/prior-work matrix comparing the submission’s contributions against related work (overlaps vs deltas). **Trigger**: novelty matrix, prior-work matrix, overlap/delta, 相关工作对比, 新颖性矩阵. **Use when**: peer review 中评估 novelty/positioning,需要把贡献与相关工作逐项对齐并写出差异点证据。 **Skip if**: 缺少 claims(先跑 `claims-extractor`)或你不打算做新颖性定位分析。 **Network**: none (retrieval of additional related work is out-of-scope unless provided). **Guardrail**: 明确 overlap 与 delta;尽量给出可追溯证据来源(来自稿件/引用/作者陈述)。
protocol-writer
Write a systematic review protocol into `output/PROTOCOL.md` (databases, queries, inclusion/exclusion, time window, extraction fields). **Trigger**: protocol, PRISMA, systematic review, inclusion/exclusion, 检索式, 纳入排除. **Use when**: systematic review pipeline 的起点(C1),需要先锁定 protocol 再开始 screening/extraction。 **Skip if**: 不是做 systematic review(或 protocol 已经锁定且不允许修改)。 **Network**: none. **Guardrail**: protocol 必须包含可执行的检索与筛选规则;需要 HUMAN 签字后才能进入 screening。
rubric-writer
Write a rubric-based peer review report (`output/REVIEW.md`) using extracted claims and evidence gaps (novelty/soundness/clarity/impact). **Trigger**: rubric review, referee report, peer review write-up, 审稿报告, REVIEW.md. **Use when**: peer-review pipeline 的最后阶段(C3),已有 `output/CLAIMS.md` + `output/MISSING_EVIDENCE.md`(以及可选 novelty matrix)。 **Skip if**: 上游产物未就绪(claims/evidence gaps 缺失)或你不打算输出完整审稿报告。 **Network**: none. **Guardrail**: 给可执行建议(actionable feedback),并覆盖 novelty/soundness/clarity/impact;避免泛泛而谈。
Didn't find tool you were looking for?