Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
bias-assessor
Add bias/risk-of-bias assessment fields to an extraction table and populate them consistently.
**Trigger**: bias, risk-of-bias, RoB, evidence quality, 偏倚评估, 证据质量.
**Use when**: systematic review 已生成 `papers/extraction_table.csv`，需要在 synthesis 前补齐偏倚/质量字段。
**Skip if**: 不是 systematic review，或还没有 `papers/extraction_table.csv`。
**Network**: none.
**Guardrail**: 使用简单可复核刻度（low/unclear/high）+ 简短 notes；保持字段一致性。
WILLOSCAR/research-units-pipeline-skills 377
-
anchor-sheet
Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of generic summaries.
**Trigger**: anchor sheet, anchor facts, numeric anchors, evidence hooks, 写作锚点, 数字锚点, 证据钩子.
**Use when**: `outline/evidence_drafts.jsonl` exists and you want stronger, evidence-anchored writing in `sections/*.md`.
**Skip if**: evidence packs are incomplete (fix `evidence-draft` first).
**Network**: none.
**Guardrail**: NO PROSE; do not invent facts; only select from existing evidence snippets/highlights.
WILLOSCAR/research-units-pipeline-skills 377
-
idea-shortlist-curator
Converge the screened direction pool into a small, discussion-ready shortlist, writing `output/trace/IDEA_SHORTLIST.md`.
**Trigger**: idea shortlist, shortlist directions, brainstorm shortlist, 方向 shortlist.
**Use when**: you already have a direction pool and screening table and want the strongest 3-5 directions for the final memo.
**Skip if**: you need more direction generation first.
**Network**: none.
**Guardrail**: no invented papers; keep the shortlist discussion-ready rather than execution-spec heavy.
WILLOSCAR/research-units-pipeline-skills 377
-
concept-graph
Build a concept graph (nodes + prerequisite edges) from a tutorial spec, saving as `outline/concept_graph.yml`.
**Trigger**: concept graph, prerequisite graph, dependency graph, 概念图, 先修关系.
**Use when**: tutorial pipeline 的结构阶段（C2），需要把教程知识点拆成可排序的依赖图（在写教程 prose 前）。
**Skip if**: 还没有 tutorial spec（例如缺少 `output/TUTORIAL_SPEC.md`）。
**Network**: none.
**Guardrail**: 只做结构；避免写长 prose 段落。
WILLOSCAR/research-units-pipeline-skills 377
-
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.
WILLOSCAR/research-units-pipeline-skills 377
-
grad-paragraph
Write one survey-quality paragraph from evidence packs (tension → contrast → evaluation anchor → limitation).
**Trigger**: grad paragraph, paragraph micro-structure, argument paragraph, 研究生段落, 论证段落, 对比段, 段落写作.
**Use when**: you are drafting `sections/S*.md` (H3 body) and want subsection-specific, evidence-bounded prose instead of templates.
**Skip if**: evidence packs are missing/incomplete (fix `subsection-briefs`/`evidence-draft`/`evidence-binder` first), or `Approve C2` is not recorded in `DECISIONS.md`.
**Network**: none.
**Guardrail**: do not invent facts or citations; no placeholders/ellipsis; keep claims conservative when evidence is abstract-level (avoid repeating evidence-mode boilerplate in every paragraph).
WILLOSCAR/research-units-pipeline-skills 377
-
evidence-auditor
Audit the evidence supporting each claim and write gaps/concerns into `output/MISSING_EVIDENCE.md`.
**Trigger**: evidence audit, missing evidence, unsupported claims, 审稿证据审计, 证据缺口.
**Use when**: peer review 流程中，需要逐条检查 claim 的证据链、缺 baseline、评测薄弱点。
**Skip if**: 缺少 claims 输入（例如还没有 `output/CLAIMS.md`）。
**Network**: none.
**Guardrail**: 只写“缺口/风险/下一步验证”，不要替作者补写论述或引入新主张。
WILLOSCAR/research-units-pipeline-skills 377
-
argument-selfloop
Argument self-loop: maintain an argument ledger + premise consistency report for drafted sections.
**Trigger**: argument self-loop, argument chain, premise consistency, section self-check, paragraph contract, 论证自循环, 论证链路, 前提一致性, 段落论证动作.
**Use when**: you are in C5 (PROSE allowed), `sections/*.md` exist, and you want to prevent “smooth but hollow” writing by enforcing argument moves + premise hygiene before merge.
**Skip if**: you are pre-C2 (NO PROSE), or evidence packs are scaffolded/thin (route upstream to `evidence-selfloop` first).
**Network**: none.
**Guardrail**: do not invent facts; do not add/remove/move citation keys; do not move citations across subsections; the argument ledger is an intermediate artifact and must never be inserted into the paper.
WILLOSCAR/research-units-pipeline-skills 377
-
chapter-lead-writer
Write H2 chapter lead blocks (`sections/S<sec_id>_lead.md`) that preview the chapter's comparison lens and connect its H3 subsections, without adding new facts.
**Trigger**: chapter lead writer, section lead writer, H2 lead, lead paragraph, 章节导读, 章节导语.
**Use when**: you have H2 chapters with multiple H3 subsections and the draft reads like paragraph islands across subsections.
**Skip if**: the outline has no H3 subsections, or `outline/chapter_briefs.jsonl` is missing.
**Network**: none.
**Guardrail**: no new facts/citations; no headings; no narration templates; use only citation keys present in `citations/ref.bib`.
WILLOSCAR/research-units-pipeline-skills 377
-
style-harmonizer
De-slot and harmonize paper voice across `sections/*.md` without changing meaning or citation keys.
**Trigger**: style harmonizer, de-template stems, remove slot phrases, discourse stems, 写作风格统一, 去槽位句式, 去生成器味.
**Use when**: `writer-selfloop` is PASS but `output/WRITER_SELFLOOP_TODO.md` flags Style Smells (e.g., repeated count-based openers), or the draft reads like many sections share the same rhythm.
**Skip if**: you need new evidence/citations (route to C3/C4), or you are pre-C2 (NO PROSE).
**Network**: none.
**Guardrail**: do not invent facts; do not add/remove/move citation keys; do not move citations across subsections; keep claim->evidence anchoring intact.
WILLOSCAR/research-units-pipeline-skills 377
-
evidence-selfloop
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.
Writes `output/EVIDENCE_SELFLOOP_TODO.md`.
**Trigger**: evidence self-loop, evidence loop, evidence gaps, binding gaps, blocking_missing, 证据自循环, 证据缺口回路.
**Use when**: C4 outputs exist (`outline/evidence_bindings.jsonl`, `outline/evidence_drafts.jsonl`) but writing looks hollow or C5 is BLOCKED due to thin evidence.
**Skip if**: you are still pre-C3 (no notes/evidence bank yet), or you want to draft anyway and accept a lower evidence bar.
**Network**: none.
**Guardrail**: analysis-only; do not edit evidence/writing artifacts; do not invent facts/citations; only write the TODO report.
WILLOSCAR/research-units-pipeline-skills 377
-
pipeline-router
Select the most appropriate pipeline for a user goal, lock it in `PIPELINE.lock.md`, and route checkpoint questions into `DECISIONS.md`.
**Trigger**: pipeline router, choose pipeline, workflow selection, PIPELINE.lock.md, 选择流程.
**Use when**: 用户目标/交付物不清晰，需要在 snapshot/survey/tutorial/systematic-review/peer-review/idea-brainstorm 中选一个并设置最小 HITL 问题集。
**Skip if**: pipeline 已锁定（`PIPELINE.lock.md` 存在）且所需问题已回答/签字完成。
**Network**: none.
**Guardrail**: 尽量一次性提问；信息不足就写 `DECISIONS.md` 并停下等待。
WILLOSCAR/research-units-pipeline-skills 377
-
pdf-text-extractor
Download PDFs (when available) and extract plain text to support full-text evidence, writing `papers/fulltext_index.jsonl` and `papers/fulltext/*.txt`.
**Trigger**: PDF download, fulltext, extract text, papers/pdfs, 全文抽取, 下载PDF.
**Use when**: `queries.md` 设置 `evidence_mode: fulltext`（或你明确需要全文证据）并希望为 paper notes/claims 提供更强 evidence。
**Skip if**: `evidence_mode: abstract`（默认）；或你不希望进行下载/抽取（成本/权限/时间）。
**Network**: fulltext 下载通常需要网络（除非你手工提供 PDF 缓存在 `papers/pdfs/`）。
**Guardrail**: 缓存下载到 `papers/pdfs/`；默认不覆盖已有抽取文本（除非显式要求重抽）。
WILLOSCAR/research-units-pipeline-skills 377
-
thesis-workspace-init
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。
**Trigger**: 毕业论文初始化, thesis workspace, 中文毕业论文准备, 模板归位, 材料盘点, 初始化论文工程.
**Use when**: 你要开始一条毕业论文重构流程，手头已经有学校模板、旧 `tex`、PDF、Overleaf 源稿、bib 或图表材料，需要先把工程和中间层搭起来。
**Skip if**: 工作区已经稳定，且 `codex_md/material_index.md`、`codex_md/question_list.md`、`codex_md/00_thesis_outline.md` 都已存在并在使用。
**Network**: none.
**Guardrail**: 不改正文内容；不把 `chapters/` 当思考区；不在 repo root 散落毕业论文工件。
WILLOSCAR/research-units-pipeline-skills 377
-
module-planner
Plan tutorial modules from a concept graph, including module objectives and sequencing, saving as `outline/module_plan.yml`.
**Trigger**: module plan, tutorial modules, course outline, 模块规划, module_plan.yml.
**Use when**: tutorial pipeline 的结构阶段（C2），已有 `outline/concept_graph.yml`，需要把概念依赖转成可教学的模块序列。
**Skip if**: 还没有 concept graph（先跑 `concept-graph`）。
**Network**: none.
**Guardrail**: 每模块明确 objectives + outputs（最好含 running example 步骤）；避免 prose 段落。
WILLOSCAR/research-units-pipeline-skills 377
-
thesis-tex-writeback
把已经在 Markdown 中间层收敛的中文毕业论文内容回写到 `chapters/*.tex` 与相关交付层文件，保持结构、图表、公式、交叉引用与章节承接一致。
**Trigger**: tex 回写, thesis tex writeback, md 回 tex, 章节回写, 论文交付层同步.
**Use when**: 章节主线、术语、符号和图表计划已经在 Markdown 层基本稳定，需要进入 TeX 交付层。
**Skip if**: 结构还没稳定，或者仍在章级重构阶段。
**Network**: none.
**Guardrail**: 不在这里重新发明结构；优先把结构问题回到 Markdown 层处理；TeX 层负责交付而非重新思考。
WILLOSCAR/research-units-pipeline-skills 377
-
table-schema
Define evidence-first table schemas for a survey: what each table must answer, row unit, columns, and which evidence-pack fields are required to fill it.
**Trigger**: table schema, schema-first tables, table design, 表格 schema, 先 schema 后填充.
**Use when**: you want survey tables that are verifiable and fillable before LaTeX (typically Stage C4, after evidence packs exist).
**Skip if**: `outline/table_schema.md` already exists and is refined (covers both index tables and Appendix tables; no placeholders; evidence mapping is explicit).
**Network**: none.
**Guardrail**: no invented facts; schema must be checkable and map each column to an evidence source.
WILLOSCAR/research-units-pipeline-skills 377
-
artifact-contract-auditor
Audit the workspace against the pipeline artifact contract (DONE outputs + pipeline target_artifacts).
Writes `output/CONTRACT_REPORT.md`.
**Trigger**: contract audit, artifact contract, missing artifacts, target_artifacts, CONTRACT_REPORT.
**Use when**: you want an auditable PASS/FAIL view of whether a workspace is complete and self-contained (end of run or before sharing).
**Skip if**: you are still intentionally mid-run and don’t care about completeness yet (but it’s still useful as a snapshot).
**Network**: none.
**Guardrail**: analysis-only; do not edit content artifacts; only write the report.
WILLOSCAR/research-units-pipeline-skills 377
-
deliverable-selfloop
Self-loop a deliverable until it is publishable by the pipeline standard: diagnose -> fix -> re-check, and write a PASS/FAIL report.
**Trigger**: self loop, self-loop, polish deliverable, quality gate, fix-on-fail, 收敛, 自循环, 质量门.
**Use when**: A pipeline has produced a reader-facing deliverable (`output/*.md`) and you want deterministic convergence to PASS.
**Skip if**: You are still pre-approval for prose or the upstream evidence/structure artifacts are missing.
**Network**: none.
**Guardrail**: Do not invent papers/citations/results. Only use in-scope inputs already present in the workspace.
WILLOSCAR/research-units-pipeline-skills 377
-
agent-survey-corpus
Download a small corpus of open-access arXiv survey/review PDFs about LLM agents and extract text for style learning.
**Trigger**: agent survey corpus, ref corpus, download surveys, 学习综述写法, 下载 survey.
**Use when**: you want to study how real agent surveys structure sections (6–8 H2), size subsections, and write evidence-backed comparisons.
**Skip if**: you cannot download PDFs (no network) or you don't want local PDF files.
**Network**: required.
**Guardrail**: only download arXiv PDFs; store under `ref/` and keep large files out of git.
WILLOSCAR/research-units-pipeline-skills 377
-
chapter-skeleton
Build a retrieval-informed chapter skeleton (`outline/chapter_skeleton.yml`) from taxonomy/core scope before stable H3 decomposition.
**Trigger**: chapter skeleton, chapter-level outline, H2 skeleton, section-first survey, 章节骨架, 章级骨架.
**Use when**: survey structure should stabilize chapter-level intent before subsection mapping and writing cards.
**Skip if**: `outline/chapter_skeleton.yml` already exists and is refined.
**Network**: none.
**Guardrail**: NO PROSE; do not invent papers; keep output chapter-level only.
WILLOSCAR/research-units-pipeline-skills 377
-
opener-variator
Rewrite subsection openers so they stop reading like a generated table-of-contents: remove \"overview/narration\" stems and reduce repeated opener cadences across H3s.
**Trigger**: opener variator, opener rewrite, rewrite openers, overview opener, 开头改写, 小节开头, 去overview, 去旁白.
**Use when**: `writer-selfloop` is PASS but flags repeated opener stems / overview narration in `output/WRITER_SELFLOOP_TODO.md`, or the draft still has a subtle “generator cadence”.
**Skip if**: you are pre-C2 (NO PROSE), or the section is evidence-thin (route upstream; don’t stylize filler).
**Network**: none.
**Guardrail**: do not invent facts; do not add/remove/move citation keys; do not move citations across subsections; keep meaning intact.
WILLOSCAR/research-units-pipeline-skills 377
-
workspace-init
Initialize a new workspace by copying the standard artifact template (STATUS.md, CHECKPOINTS.md, UNITS.csv, DECISIONS.md + folders).
**Trigger**: workspace init, initialize workspace, workspace template, 初始化 workspace.
**Use when**: 启动任何 pipeline run（必须先有 workspace 工件与目录骨架）。
**Skip if**: workspace 已初始化且不希望覆盖既有文件（除非显式 `--overwrite`）。
**Network**: none.
**Guardrail**: 不要修改 `.codex/skills/workspace-init/assets/` 模板；默认不覆盖已有文件。
WILLOSCAR/research-units-pipeline-skills 377
-
latex-scaffold
Scaffold a LaTeX project (`latex/main.tex`, bibliography wiring, structure) from an existing Markdown draft and `citations/ref.bib`.
**Trigger**: latex scaffold, md→tex, LaTeX 项目骨架, 生成 main.tex.
**Use when**: 需要 LaTeX/PDF 交付（例如 arxiv-survey-latex pipeline），且 draft 已生成/已进入写作阶段。
**Skip if**: 还没有 `output/DRAFT.md`（或你不需要 LaTeX 交付）。
**Network**: none.
**Guardrail**: 移除 markdown 残留（`##`, `**`, `[@...]`）；bibliography 指向 `citations/ref.bib`；不在此步骤改写内容。
WILLOSCAR/research-units-pipeline-skills 377