Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
claims-extractor
Extract key claims, contributions, and assumptions from a paper/manuscript into `output/CLAIMS.md` with traceability to source locations.
**Trigger**: claims extractor, extract claims, contributions, assumptions, peer review, 审稿, 主张提取.
**Use when**: 审稿/评审或 evidence audit，需要把主张列表落盘并可追溯到原文位置（section/page/quote）。
**Skip if**: 没有可用的稿件/全文（例如缺少 `output/PAPER.md` 或等价文本）。
**Network**: none.
**Guardrail**: 每条 claim 必须带可定位的 source pointer；区分 empirical vs conceptual claims。
WILLOSCAR/research-units-pipeline-skills 377
-
section-briefs
Build chapter-level briefs (`outline/section_briefs.jsonl`) from chapter skeleton plus section bindings before stable H3 decomposition.
**Trigger**: section briefs, chapter planning cards, section-first briefs, 章节 brief, 章级 brief.
**Use when**: section bindings exist and the run needs chapter-level rationale and decomposition guidance before emitting stable H3 ids.
**Skip if**: `outline/section_briefs.jsonl` already exists and is refined.
**Network**: none.
**Guardrail**: NO PROSE; do not invent papers; emit planning constraints, not reader-facing text.
WILLOSCAR/research-units-pipeline-skills 377
-
idea-signal-mapper
Map paper notes + taxonomy into a signal table of tensions, missing pieces, and promising academic axes for brainstorm discussion. Writes `output/trace/IDEA_SIGNAL_TABLE.md`.
**Trigger**: idea signal table, brainstorm signals, research tensions, signal map, 研究信号表, tension map.
**Use when**: you have a core set, a taxonomy, and paper notes, and need a table-first bridge from literature evidence to possible directions.
**Skip if**: `output/trace/IDEA_SIGNAL_TABLE.md` already exists and is refined.
**Network**: none.
**Guardrail**: no invented papers; every row must point to existing `paper_id`s.
WILLOSCAR/research-units-pipeline-skills 377
-
human-checkpoint
Record a human sign-off at a declared checkpoint (tick `Approve C*` in `DECISIONS.md`) so the pipeline can resume.
**Trigger**: approve checkpoint, human approval, sign off, HITL, Approve C2, 审批, 签字, 人类检查点.
**Use when**: A unit has `owner=HUMAN` and is BLOCKED waiting for a checkbox in `DECISIONS.md`.
**Skip if**: The approval is already recorded (the checkbox is ticked).
**Network**: none.
**Guardrail**: Do not modify any content artifacts; only update `DECISIONS.md` (and optionally append a short sign-off note).
WILLOSCAR/research-units-pipeline-skills 377
-
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`.
WILLOSCAR/research-units-pipeline-skills 377
-
idea-memo-writer
Synthesize the shortlist into a discussion-ready research idea brainstorm memo, writing `output/REPORT.md`, `output/APPENDIX.md`, and `output/REPORT.json`.
**Trigger**: idea memo, brainstorm memo, research direction memo, report md, 研究备忘录, brainstorm report.
**Use when**: the shortlist exists and you want the final reader-facing brainstorm deliverable for PI / PhD discussion.
**Skip if**: you only need an internal shortlist and do not want a final memo.
**Network**: none.
**Guardrail**: do not invent papers; all final directions must remain anchored to the shortlist and core set.
WILLOSCAR/research-units-pipeline-skills 377
-
schema-normalizer
Normalize cross-skill JSONL interfaces (ids + titles + citation key formats) so downstream skills do not rely on best-effort joins.
**Trigger**: schema normalize, jsonl contract, interface drift, join drift, 字段不一致, schema 规范化.
**Use when**: you have generated C2-C4 JSONL artifacts (outline/briefs/bindings/packs/anchors) and want deterministic, stable fields before self-loops/writing.
**Skip if**: you are not using the survey pipelines, or the workspace already has a fresh PASS `output/SCHEMA_NORMALIZATION_REPORT.md` for the current artifacts.
**Network**: none.
**Guardrail**: NO PROSE; deterministic transforms only; do not invent evidence/claims; only fill missing ids/titles from `outline/outline.yml`.
WILLOSCAR/research-units-pipeline-skills 377
-
writer-selfloop
Writing self-loop for surveys: run the strict section-quality gate, then rewrite only the failing `sections/*.md` files until the report is PASS.
**Trigger**: writer self-loop, writing loop, quality gate loop, rewrite failing sections, 自循环, 反复改到 PASS.
**Use when**: per-section files exist but C5 is FAIL/BLOCKED (thin sections, missing leads/front matter, citation-scope violations, generator voice).
**Skip if**: you are still pre-C2 (NO PROSE), or evidence packs are incomplete (fix C3/C4 first).
**Network**: none.
**Guardrail**: do not invent facts; only use citation keys present in `citations/ref.bib`; keep citations in-scope per `outline/evidence_bindings.jsonl`; do not add/remove citation keys during rewrites.
WILLOSCAR/research-units-pipeline-skills 377
-
terminology-normalizer
Normalize terminology across a draft (canonical terms + synonym policy) without changing citations or meaning.
**Trigger**: terminology, glossary, consistent terms, 术语统一, 统一叫法, 术语表.
**Use when**: the draft has concept drift (same thing called 2–3 names) or global-review flags terminology inconsistency.
**Skip if**: you are still changing the outline/taxonomy heavily (do that first).
**Network**: none.
**Guardrail**: do not add/remove citation keys; do not introduce new claims; avoid moving citations across subsections.
WILLOSCAR/research-units-pipeline-skills 377
-
pipeline-auditor
Audit/regression checks for the evidence-first survey pipeline: citation health, per-section coverage, placeholder leakage, and template repetition.
**Trigger**: auditor, audit, regression test, quality report, 审计, 回归测试.
**Use when**: `output/DRAFT.md` exists and you want a deterministic PASS/FAIL report before LaTeX/PDF.
**Skip if**: you are still changing retrieval/outline/evidence packs heavily (audit later).
**Network**: none.
**Guardrail**: do not change content; only analyze and report.
WILLOSCAR/research-units-pipeline-skills 377
-
citation-diversifier
Raise citation diversity/density (NO NEW FACTS): generate an in-scope “citation budget” plan per H3 so drafts stop failing the global unique-citation gate and stop looking under-cited.
**Trigger**: cite boost, citation budget, unique citations too low, add more citations, improve reference density, 引用太少, 增加引用, 引用密度.
**Use when**: `pipeline-auditor` FAILs due to low unique citations, or you want to increase cite density without changing claims.
**Skip if**: you need new papers (fix C1/C2 mapping first), or `citations/ref.bib` / `outline/writer_context_packs.jsonl` is missing.
**Network**: none.
**Guardrail**: NO NEW FACTS; do not invent citations; only use keys already present in `citations/ref.bib`; keep citations within each H3’s allowed scope (`outline/writer_context_packs.jsonl` / `outline/evidence_bindings.jsonl`).
WILLOSCAR/research-units-pipeline-skills 377
-
thesis-style-polisher
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。
**Trigger**: 论文润色, thesis style polish, 去 AI 味, 中文论文风格统一, 章首导言润色, 总结展望润色.
**Use when**: 结构、证据、数据和编译已经基本稳定，需要做最后一轮中文学位论文风格收口。
**Skip if**: 正文结构还在大改，或关键引用 / 数字 / 图表还没稳定。
**Network**: none.
**Guardrail**: 不用润色掩盖结构问题；不引入新事实；先去模板腔，再做措辞提升。
WILLOSCAR/research-units-pipeline-skills 377
-
evaluation-anchor-checker
Audit and rewrite evaluation/numeric claims to ensure they carry minimal protocol context (task + metric + constraint) and avoid underspecified model naming.
**Trigger**: evaluation anchor checker, numeric claim hygiene, underspecified numbers, protocol context, 评测锚点检查, 数字断言, 指标上下文.
**Use when**: before final merge/polish, or when reviewers would likely flag claims as underspecified (numbers without task/metric/budget), or `pipeline-auditor` warns about suspicious model naming.
**Skip if**: evidence is too thin to justify numeric claims (route upstream to C3/C4), or you are pre-C2 (NO PROSE).
**Network**: none.
**Guardrail**: do not invent numbers; do not add/remove/move citation keys; if protocol context is missing, weaken/remove the numeric claim rather than guessing.
WILLOSCAR/research-units-pipeline-skills 377
-
citation-anchoring
Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.
**Trigger**: citation anchoring, citation drift, regression, cite stability, 引用锚定, 引用漂移.
**Use when**: after editing/polishing, you want to confirm citations did not migrate across `###` subsections.
**Skip if**: you do not have a baseline anchor file yet.
**Network**: none.
**Guardrail**: analysis-only; do not edit content.
WILLOSCAR/research-units-pipeline-skills 377
-
_template_reference_first
Internal template for creating or refactoring a skill into the repository's reference-first shape.
**Trigger**: reference-first template, blueprint skill, create a reusable skill, refactor a script-heavy skill.
**Use when**: you need a lean `SKILL.md`, explicit `references/`, machine-readable `assets/`, and a minimal deterministic `run.py`.
**Skip if**: the task is a one-off workflow that will not be reused as a skill.
**Network**: none.
**Guardrail**: keep domain knowledge and writing exemplars out of `run.py`; make reference loading explicit; do not ship reader-facing placeholder text.
WILLOSCAR/research-units-pipeline-skills 377
-
draft-polisher
Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring.
**Trigger**: polish draft, de-template, coherence pass, remove boilerplate, 润色, 去套话, 去重复, 统一术语.
**Use when**: a first-pass draft exists but reads like scaffolding (repetition/ellipsis/template phrases) or needs a coherence pass before global review/LaTeX.
**Skip if**: the draft already reads human-grade and passes quality gates; or prose is not approved in `DECISIONS.md`.
**Network**: none.
**Guardrail**: do not add/remove/invent citation keys; do not move citations across subsections; do not change claims beyond what existing citations support.
WILLOSCAR/research-units-pipeline-skills 377
-
thesis-markdown-aligner
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”。
**Trigger**: markdown 对齐, thesis markdown align, 术语统一, 符号统一, 指标统一, 章节归并.
**Use when**: 各章已经初步重构，但整篇论文仍有术语漂移、指标口径不一致、章节边界混乱或像多篇 paper 拼接。
**Skip if**: 章节角色还没定，或当前只是在局部修一章。
**Network**: none.
**Guardrail**: 不在这里回写 tex；先收敛中间层，再进入交付层。
WILLOSCAR/research-units-pipeline-skills 377
-
outline-refiner
Planner-pass coverage + redundancy report for an outline+mapping, producing `outline/coverage_report.md` and `outline/outline_state.jsonl`.
**Trigger**: planner, dynamic outline, outline refinement, coverage report, 大纲迭代, 覆盖率报告.
**Use when**: you have `outline/outline.yml` + `outline/mapping.tsv` and want a verifiable, NO-PROSE planner pass before writing.
**Skip if**: you don't want any outline/mapping diagnostics (or you have a frozen/approved structure and will not change it).
**Network**: none.
**Guardrail**: NO PROSE; do not invent papers; only report coverage/reuse and propose structural actions as bullets.
WILLOSCAR/research-units-pipeline-skills 377
-
prose-writer
Write `output/DRAFT.md` (or `output/SNAPSHOT.md`) from an approved outline and evidence packs, using only verified citation keys from `citations/ref.bib`.
**Trigger**: write draft, prose writer, snapshot, survey writing, 写综述, 生成草稿, section-by-section drafting.
**Use when**: structure is approved (`DECISIONS.md` has `Approve C2`) and evidence packs exist (`outline/subsection_briefs.jsonl`, `outline/evidence_drafts.jsonl`).
**Skip if**: approvals are missing, or evidence packs are incomplete / scaffolded (missing-fields, TODO markers).
**Network**: none.
**Guardrail**: do not invent facts or citations; only cite keys present in `citations/ref.bib`; avoid pipeline-jargon leakage in final prose.
WILLOSCAR/research-units-pipeline-skills 377
-
section-bindings
Bind papers to chapter-level sections first, writing `outline/section_bindings.jsonl` and `outline/section_binding_report.md`.
**Trigger**: section bindings, chapter bindings, section-first binding, 章节绑定, 章级绑定.
**Use when**: survey structure should measure chapter saturation before stable H3 decomposition.
**Skip if**: chapter skeleton is missing or the bindings are already refined.
**Network**: none.
**Guardrail**: NO PROSE; do not invent papers; produce auditable PASS/BLOCKED/REROUTE signals.
WILLOSCAR/research-units-pipeline-skills 377
-
subsection-polisher
Polish a single H3 unit file under `sections/` into survey-grade prose (de-template + contrast/eval/limitation), without changing citation keys.
**Trigger**: subsection polisher, per-subsection polish, polish section file, 小节润色, 去模板, 结构化段落.
**Use when**: `sections/S*.md` exists but reads rigid/template-y; you want to fix quality locally before `section-merger`.
**Skip if**: subsection files are missing, evidence packs are incomplete, or `Approve C2` is not recorded.
**Network**: none.
**Guardrail**: do not invent facts/citations; do not add/remove citation keys; keep citations within the same H3; keep citations subsection-scoped.
WILLOSCAR/research-units-pipeline-skills 377
-
transition-weaver
Generate lightweight section/subsection transitions (NO NEW FACTS) to prevent “island” subsections; outputs a transition map that merging/writing can weave in.
**Trigger**: transition weaver, weave transitions, coherence, 过渡句, 承接句, 章节连贯性.
**Use when**: `outline/subsection_briefs.jsonl` exists and you want coherent flow before/after drafting (typically Stage C5).
**Skip if**: `outline/transitions.md` exists and is refined (no placeholders).
**Network**: none.
**Guardrail**: do not add new factual claims or citations; transitions may only refer to titles/RQs/bridge terms already present in briefs.
WILLOSCAR/research-units-pipeline-skills 377
-
latex-compile-qa
Compile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report.
**Trigger**: latex compile, build PDF, LaTeX errors, missing refs, 编译PDF, 引用错误.
**Use when**: 已有 `latex/main.tex`（通常来自 `latex-scaffold`），需要确认可编译并输出失败原因报告。
**Skip if**: 还没有 LaTeX scaffold（先跑 `latex-scaffold`）。
**Network**: none.
**Guardrail**: 编译失败也要落盘 `output/LATEX_BUILD_REPORT.md`；不做“内容改写”，只做编译/QA。
WILLOSCAR/research-units-pipeline-skills 377
-
chapter-briefs
Build per-chapter (H2) writing briefs (NO PROSE) so the final survey reads like a paper (chapter leads + cross-H3 coherence) without inflating the ToC.
**Trigger**: chapter briefs, H2 briefs, chapter lead plan, section intent, 章节意图, 章节导读, H2 卡片.
**Use when**: `outline/outline.yml` + `outline/subsection_briefs.jsonl` exist and you want thicker chapters (fewer headings, more logic).
**Skip if**: the outline is still changing heavily (fix outline/mapping first).
**Network**: none.
**Guardrail**: NO PROSE; do not invent papers; only reference subsection ids and already-mapped papers.
WILLOSCAR/research-units-pipeline-skills 377