Agent skill
outline-budgeter
Merge/simplify an over-fragmented outline to hit a paper-like section budget (NO PROSE): target final ToC ~6–8 H2, fewer thicker H3. **Trigger**: outline budget, merge sections, too many sections, H3 explosion, 大纲预算, 合并小节, 大纲太碎. **Use when**: `outline/outline.yml` exists but would produce thin sections (too many H2/H3); before (or immediately after) `section-mapper`. **Skip if**: outline is already within budget and approved; or you are already drafting prose. **Network**: none. **Guardrail**: NO PROSE; do not invent new topics; keep scope consistent; if you change section ids, you must reset mapping.
Install this agent skill to your Project
npx add-skill https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/outline-budgeter
SKILL.md
Outline Budgeter (NO PROSE)
Purpose: prevent the most common survey failure mode: H3 explosion (too many tiny subsections) leading to a thin, outline-like PDF.
This skill rewrites outline/outline.yml into a paper-like budget:
- Final ToC target: ~6–8 H2 sections (Intro / Related Work + 3–4 core chapters + Discussion + Conclusion)
- H3 target: fewer, thicker subsections (per
draft_profile: survey<=10, deep<=12)
Important: Discussion/Conclusion are appended in C5 merge (global sections), so the outline itself should usually be <=6 H2.
Inputs
outline/outline.yml- Optional (helps make merges evidence-aware):
queries.md(optional: if it setsdraft_profile, use it to choose the H3 budget)outline/mapping.tsvoutline/coverage_report.mdGOAL.md
Outputs
outline/outline.yml(updated in place)outline/OUTLINE_BUDGET_REPORT.md(bullets-only; what was merged and why)
Workflow (NO PROSE)
- Read the outline and compute a simple budget snapshot:
- If
queries.mdsetsdraft_profile(survey/deep), use it to decide the H3 budget target. - H2 count (excluding Discussion/Conclusion, which are not in the outline)
- Total H3 count
- H3 count per H2 chapter
- Decide a merge plan (structure-first, evidence-aware):
- Prefer merging adjacent H3s that share similar axes/keywords.
- Prefer merging H3s with weak mapping coverage (if
mapping.tsvexists). - If
outline/coverage_report.mdexists (fromoutline-refiner), use it to identify weak-coverage or high-reuse subsections to merge. - Use
GOAL.mdas the scope constraint: avoid merges that mix distinct research questions or scope boundaries. - Prefer moving fine-grained distinctions into bullets/axes instead of creating new subsections.
- Apply merges in
outline/outline.yml:
- Merge titles into a clearer, thicker subsection title.
- Merge bullets (dedupe templates; keep Stage A fields: Intent/RQ/Evidence needs/Expected cites).
- Keep ids stable when possible.
- If you must change ids, record it explicitly in the report and assume
mapping.tsvmust be regenerated.
- If you must change ids, record it explicitly in the report and assume
- Write
outline/OUTLINE_BUDGET_REPORT.md:
- Before/after counts.
- List of merges (old ids/titles -> new id/title).
- Any risks (e.g., mapping reset required).
Quality checklist
- No placeholders (
TODO/…/(placeholder)). - Outline budget matches the paper-like target.
- Each remaining H3 is thick enough to sustain evidence-first writing (its bullets mention concrete comparisons + eval anchors + failure modes).
Troubleshooting
Issue: merging makes a subsection too broad
Fix:
- Keep one H3, but split its bullets into explicit comparison axes and required evidence fields; defer fine-grained splits to later if evidence is strong enough.
Issue: mapping breaks after id changes
Fix:
- Rerun
section-mapperto regenerateoutline/mapping.tsv, then rerunoutline-refiner.
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?