Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
idea-direction-generator
Generate a compact pool of discussion-worthy research directions from the signal table, writing `output/trace/IDEA_DIRECTION_POOL.md`.
**Trigger**: idea direction pool, brainstorm directions, research directions, 研究方向池, brainstorm pool.
**Use when**: you already have a signal table and want a small, non-isomorphic set of candidate directions.
**Skip if**: `output/trace/IDEA_DIRECTION_POOL.md` already exists and is refined.
**Network**: none.
**Guardrail**: no invented papers; directions must stay anchored to the current signal table and core set.
WILLOSCAR/research-units-pipeline-skills 377
-
tutorial-spec
Define tutorial scope, target audience, prerequisites, learning objectives, and a running example; output a tutorial spec for downstream planning.
**Trigger**: tutorial spec, scope, audience, prerequisites, learning objectives, running example, 教程规格.
**Use when**: tutorial pipeline 的起点（C1），需要先锁定教学目标与边界，再进入 concept graph / module planning。
**Skip if**: 你不是在做教程产出（或已经有明确且不允许改动的 tutorial spec）。
**Network**: none.
**Guardrail**: 结构化 spec 优先；避免提前写长教程 prose（prose 在 C3）。
WILLOSCAR/research-units-pipeline-skills 377
-
writer-context-pack
Build per-H3 writer context packs (NO PROSE): merge briefs + evidence packs + anchor facts + allowed citations into a single deterministic JSONL, so drafting is less hollow and less brittle.
**Trigger**: writer context pack, context pack, drafting pack, paragraph plan pack, 写作上下文包.
**Use when**: `outline/subsection_briefs.jsonl` + `outline/evidence_drafts.jsonl` + `outline/anchor_sheet.jsonl` exist and you want to make C5 drafting easier/more consistent.
**Skip if**: upstream evidence is missing or scaffolded (fix `paper-notes` / `evidence-binder` / `evidence-draft` / `anchor-sheet` first).
**Network**: none.
**Guardrail**: NO PROSE; do not invent facts/citations; only use citation keys present in `citations/ref.bib`.
WILLOSCAR/research-units-pipeline-skills 377
-
thesis-chapter-reconstructor
围绕毕业论文主线重构章节：把原论文式叙事改成学位论文式叙事，重写章节目标、内容比重、前后承接与论证方式。
**Trigger**: 章节重构, chapter reconstructor, 毕业论文主线重构, paper 变 thesis, 章节改写.
**Use when**: 你已经知道每份材料在毕业论文中的角色，但当前章节仍然像原论文翻译、拼接或卖点展示。
**Skip if**: 当前只是做局部句子润色，或章节角色尚未确定。
**Network**: none.
**Guardrail**: 不是翻译论文；不是简单删减；必须围绕毕业论文主线重写章节目标与承接关系。
WILLOSCAR/research-units-pipeline-skills 377
-
thesis-source-role-mapper
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。
**Trigger**: 毕业论文材料映射, source role map, paper to chapter, 章节角色映射, 论文归章, 材料归位.
**Use when**: 已经完成材料盘点，需要决定各份材料在毕业论文里扮演什么角色，而不是继续按原 paper 叙事直接写。
**Skip if**: 当前只是在修一个已经稳定的单章措辞，且没有新的来源材料进入。
**Network**: none.
**Guardrail**: 不是做翻译；不是简单 `paper -> chapter` 分桶；必须显式说明“在毕业论文里的角色”。
WILLOSCAR/research-units-pipeline-skills 377
-
unit-planner
Instantiate or update a workspace `UNITS.csv` from a selected pipeline and units template (deps/checkpoints/acceptance).
**Trigger**: unit planner, generate UNITS.csv, execution contract, units template, 生成工作单元.
**Use when**: 初始化/更新执行合同：从 pipeline 选择生成 `UNITS.csv`，或 scope 扩展需要新增 units/依赖。
**Skip if**: `UNITS.csv` 已正确反映当前 scope（无需重写）。
**Network**: none.
**Guardrail**: 保持 CSV 合法；scope 增长时新增 units；只在满足验收后标 `DONE`。
WILLOSCAR/research-units-pipeline-skills 377
-
screening-manager
Manage title/abstract screening and record decisions into `papers/screening_log.csv` according to an approved protocol.
**Trigger**: screening, title/abstract screening, inclusion/exclusion, screening_log.csv, 文献筛选, 纳入排除.
**Use when**: systematic review 的 screening 阶段（C2），protocol 已锁定并通过 HUMAN 审批。
**Skip if**: 还没有 `output/PROTOCOL.md`（或 protocol 未通过签字）。
**Network**: none.
**Guardrail**: 每条记录包含决策与理由；保持可审计（不要把“未读/不确定”当作纳入）。
WILLOSCAR/research-units-pipeline-skills 377
-
paper-notes
Write structured notes for each paper in the core set into `papers/paper_notes.jsonl` (summary/method/results/limitations).
**Trigger**: paper notes, structured notes, reading notes, 论文笔记, paper_notes.jsonl.
**Use when**: survey 的 evidence 阶段（C3），已有 `papers/core_set.csv`（以及可选 fulltext），需要为后续 claims/citations/writing 准备可引用证据。
**Skip if**: 还没有 core set（先跑 `dedupe-rank`），或你只做极轻量 snapshot 不需要细粒度证据。
**Network**: none.
**Guardrail**: 具体可核对（method/metrics/limitations），避免大量重复模板；保持结构化字段而非长 prose。
WILLOSCAR/research-units-pipeline-skills 377
-
evidence-binder
Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`.
**Trigger**: evidence binder, evidence plan, section->evidence mapping, 证据绑定, evidence_id.
**Use when**: `papers/evidence_bank.jsonl` exists and you want writer/auditor to use section-scoped evidence items (WebWeaver-style memory bank).
**Skip if**: you are not doing evidence-first section-by-section writing.
**Network**: none.
**Guardrail**: NO PROSE; do not invent evidence; only select from the existing evidence bank.
WILLOSCAR/research-units-pipeline-skills 377
-
claim-evidence-matrix
Build a section-by-section claim–evidence matrix (`outline/claim_evidence_matrix.md`) from the outline and paper notes.
**Trigger**: claim–evidence matrix, evidence mapping, 证据矩阵, 主张-证据对齐.
**Use when**: 写 prose 之前需要把每个小节的可检验主张与证据来源显式化（outline + paper notes 已就绪）。
**Skip if**: 缺少 `outline/outline.yml` 或 `papers/paper_notes.jsonl`。
**Network**: none.
**Guardrail**: bullets-only（NO PROSE）；每个 claim 至少 2 个证据来源（或显式说明例外）。
WILLOSCAR/research-units-pipeline-skills 377
-
idea-brief
Lock an ideation run into a single-source-of-truth brainstorm brief (`output/trace/IDEA_BRIEF.md`) and a replayable multi-query plan (`queries.md`).
**Trigger**: idea brief, ideation brief, research ideas, brainstorm, 找 idea, 选题, 点子, 找方向.
**Use when**: the user wants research ideas and their input is long / multi-turn; you need to clarify topic + constraints before retrieval.
**Skip if**: the goal is to write a survey draft directly (use `arxiv-survey*` pipelines instead).
**Network**: none.
**Guardrail**: do not invent papers/citations; do not start retrieval here; keep the brief structured (no long prose).
WILLOSCAR/research-units-pipeline-skills 377
-
outline-builder
Convert a taxonomy (`outline/taxonomy.yml`) into a bullet-only outline (`outline/outline.yml`) with sections/subsections.
**Trigger**: outline builder, bullet outline, outline.yml, 大纲生成, bullets-only.
**Use when**: structure 阶段（NO PROSE），已有 taxonomy，需要生成可映射/可写作的章节与小节骨架（每小节≥3 bullets）。
**Skip if**: 已经有批准过且可映射的 outline（避免无意义 churn）。
**Network**: none.
**Guardrail**: bullets-only；移除 TODO/模板语句；每小节至少 3 个可检查 bullets。
WILLOSCAR/research-units-pipeline-skills 377
-
idea-screener
Screen the direction pool with a discussion-first scoring pass, writing `output/trace/IDEA_SCREENING_TABLE.md`.
**Trigger**: idea screener, screening table, brainstorm screening, 方向筛选表.
**Use when**: you already have a direction pool and want a table-first comparison before curating the shortlist.
**Skip if**: the direction pool is still missing or obviously templated.
**Network**: none.
**Guardrail**: no invented papers; scoring should reflect discussion value and distinctness, not stylistic polish.
WILLOSCAR/research-units-pipeline-skills 377
-
manuscript-ingest
Ingest a submitted manuscript into plain text (`output/PAPER.md`) so downstream review skills can extract claims with source pointers.
**Trigger**: ingest paper, manuscript text, provide paper, paper.md, 输入论文, 导入稿件, 审稿输入.
**Use when**: You are running the `peer-review` pipeline and need `output/PAPER.md` before `claims-extractor`.
**Skip if**: `output/PAPER.md` already exists and looks like the full manuscript text.
**Network**: none.
**Guardrail**: Do not summarize or rewrite the paper; store the raw text (or a faithful extraction) so claims stay traceable.
WILLOSCAR/research-units-pipeline-skills 377
-
global-reviewer
Global consistency review for survey drafts: terminology, cross-section coherence, and scope/citation hygiene.
Writes `output/GLOBAL_REVIEW.md` and (optionally) applies safe edits to `output/DRAFT.md`.
**Trigger**: global review, consistency check, coherence audit, 术语一致性, 全局回看, 章节呼应, 拷打 writer.
**Use when**: Draft exists and you want a final evidence-first coherence pass before LaTeX/PDF.
**Skip if**: You are still changing the outline/mapping/notes (do those first), or prose writing is not approved.
**Network**: none.
**Guardrail**: Do not invent facts or citations; do not add new citation keys; treat missing evidence as a failure signal.
WILLOSCAR/research-units-pipeline-skills 377
-
subsection-briefs
Build per-subsection writing briefs (NO PROSE) so later drafting is driven by evidence and checkable comparison axes (not outline placeholders).
**Trigger**: subsection briefs, writing cards, intent cards, H3 briefs, scope_rule, axes, clusters, 写作意图卡, 小节卡片, 段落计划.
**Use when**: `outline/outline.yml` + `outline/mapping.tsv` + `papers/paper_notes.jsonl` exist and you want section-by-section drafting without template leakage.
**Skip if**: `outline/subsection_briefs.jsonl` already exists and is refined (no placeholders/ellipsis; axes+clusters+paragraph_plan are filled).
**Network**: none.
**Guardrail**: NO PROSE; do not invent papers; only reference `paper_id`/`bibkey` that exist in `papers/paper_notes.jsonl`.
WILLOSCAR/research-units-pipeline-skills 377
-
section-logic-polisher
Logic coherence pass for per-H3 section files: enforce a clear paragraph-1 thesis and surface paragraph-island risks (connector stats are diagnostic, not a quota) before merging.
**Trigger**: logic polisher, section logic, thesis statement, connectors, 段落逻辑, 连接词, 论证主线, 润色逻辑.
**Use when**: `sections/S*.md` exist but read like paragraph islands; you want a targeted, debuggable self-loop before `section-merger`.
**Skip if**: sections are missing/thin (fix `subsection-writer` first) or evidence packs/briefs are scaffolded (fix C3/C4 first).
**Network**: none.
**Guardrail**: do not add new citations; do not invent facts; do not change citation keys; do not move citations across subsections.
WILLOSCAR/research-units-pipeline-skills 377
-
table-filler
Fill `outline/tables_index.md` from `outline/table_schema.md` + evidence packs (NO PROSE in cells; citation-backed rows).
**Trigger**: table filler, fill tables, evidence-first tables, index tables, 表格填充, 索引表.
**Use when**: table schema exists and evidence packs are ready; you want a compact, citation-backed index table to support later writing and Appendix table curation.
**Skip if**: `outline/tables_index.md` already exists and is refined (>=2 tables; citations in rows; no placeholders).
**Network**: none.
**Guardrail**: do not invent facts; every row must include citations; do not write paragraph cells.
WILLOSCAR/research-units-pipeline-skills 377
-
unit-executor
Execute exactly one runnable unit from `UNITS.csv` (first TODO whose dependencies are DONE), then update unit status and artifacts.
**Trigger**: unit executor, run one unit, next unit, step-by-step pipeline, 逐条执行, UNITS.csv.
**Use when**: 需要严格“一次只做一个 unit”（可审计、可中断），并遵守 checkpoints/HUMAN 阻塞逻辑。
**Skip if**: 要端到端自动跑（用 `research-pipeline-runner`）或 workspace 不存在。
**Network**: none.
**Guardrail**: 只执行一个 unit；满足验收且输出存在才可标 `DONE`；遇到 HUMAN checkpoint 必须停下。
WILLOSCAR/research-units-pipeline-skills 377
-
literature-engineer
Multi-route literature expansion + metadata normalization for evidence-first surveys.
Produces a large candidate pool (`papers/papers_raw.jsonl`, target ≥1200) with stable IDs and provenance, ready for dedupe/rank + citation generation.
**Trigger**: evidence collector, literature engineer, 文献扩充, 多路召回, snowballing, cited by, references, 元信息增强, provenance.
**Use when**: 需要把候选文献扩充到 ≥1200 篇并补齐可追溯 meta（survey pipeline 的 Stage C1，写作前置 evidence）。
**Skip if**: 已经有高质量 `papers/papers_raw.jsonl`（≥1200 且每条都有稳定标识+来源记录）。
**Network**: 可离线（靠 imports）；雪崩/在线检索需要网络。
**Guardrail**: 不允许编造论文；每条记录必须带稳定标识（arXiv id / DOI / 可信 URL）和 provenance；不写 output/ prose。
WILLOSCAR/research-units-pipeline-skills 377
-
dedupe-rank
Dedupe and rank a raw paper set (`papers/papers_raw.jsonl`) to produce `papers/papers_dedup.jsonl` and `papers/core_set.csv`.
**Trigger**: dedupe, rank, core set, 去重, 排序, 精选论文, 核心集合.
**Use when**: 检索后需要把广覆盖集合收敛成可管理的 core set（用于 taxonomy/outline/mapping）。
**Skip if**: 已经有人手工整理了稳定的 `papers/core_set.csv`（无需再次 churn）。
**Network**: none.
**Guardrail**: 偏 deterministic；输出应可重复（稳定 paper_id、字段规范）。
WILLOSCAR/research-units-pipeline-skills 377
-
thesis-frontmatter-sync
同步中文毕业论文的非正文部分：摘要、附录、封面、成果、致谢、名单等，确保这些部分与正文口径一致，而不是最后临时补写。
**Trigger**: 摘要同步, frontmatter sync, 附录同步, 封面检查, 非正文维护, 毕业论文摘要.
**Use when**: 正文结构已经比较稳定，需要并行维护非正文部分，避免中英文摘要、封面字段、附录和成果列表与正文脱节。
**Skip if**: 正文主线还不稳定，或者还没有任何可交付版本。
**Network**: none.
**Guardrail**: 不把非正文拖到最后一刻；不让摘要、附录与正文口径脱节。
WILLOSCAR/research-units-pipeline-skills 377
-
tutorial-module-writer
Write the tutorial content (`output/TUTORIAL.md`) from an approved module plan, including exercises and answer outlines.
**Trigger**: write tutorial, tutorial modules, 教程写作, TUTORIAL.md.
**Use when**: tutorial pipeline 的写作阶段（C3），且 `DECISIONS.md` 已记录 HUMAN 对 scope/running example 的批准（C2）。
**Skip if**: module plan 未完成/未批准（先跑 `module-planner`/`exercise-builder` 并通过 Approve C2）。
**Network**: none.
**Guardrail**: 只写已批准范围；保持 running example 一致；每模块包含练习与答案要点。
WILLOSCAR/research-units-pipeline-skills 377
-
thesis-visual-layout-planner
规划中文毕业论文的图表、流程图和版面节奏：先决定哪些图表支撑主线，再做草图、拼版预演与图文映射。
**Trigger**: 图表规划, figure layout, thesis visual plan, 版面预演, 图文映射, mermaid 草图.
**Use when**: 章节结构基本明确，但图表还没有系统安排，或者担心图文节奏、图表密度和版面结构失控。
**Skip if**: 论文不依赖图表支撑主线，或仍在纯结构重构早期。
**Network**: none.
**Guardrail**: 不把图表拖成最后补丁；不先排版再倒推结构；图表服务主线而不是抢主线。
WILLOSCAR/research-units-pipeline-skills 377