Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
citation-verifier
Generate and verify BibTeX entries from paper notes, writing `citations/ref.bib` and `citations/verified.jsonl`.
**Trigger**: citation, BibTeX, ref.bib, verified.jsonl, references, 引用, 参考文献.
**Use when**: 已有 `papers/paper_notes.jsonl`，需要为 prose/LaTeX 准备可追溯的引用（每条都有 url/date/title 验证记录）。
**Skip if**: 还没有 paper notes（或本次产出不需要引用/参考文献）。
**Network**: 自动验证通常需要网络；无网络时可先 record，再标注 needs manual verification。
**Guardrail**: 每个 BibTeX entry 必须对应一条 `citations/verified.jsonl` 记录；prose 只能使用已存在于 `citations/ref.bib` 的 citation keys。
WILLOSCAR/research-units-pipeline-skills 377
-
survey-visuals
Draft non-prose visuals artifacts (timeline, figure specs) for a survey, grounded in evidence and using citation keys from `citations/ref.bib`.
**Trigger**: survey visuals, timeline, figures, visuals, 图表, 时间线, figure spec.
**Use when**: survey 的 C4（NO PROSE），已有 outline + claim/evidence + citations，需要先把时间线/图规格落盘。
**Skip if**: 你只关心正文（可跳过）；或缺少 `citations/ref.bib`。
**Network**: none.
**Guardrail**: NO PROSE；产物必须具体且可核对（含 citations），禁止遗留 TODO/SCAFFOLD。
WILLOSCAR/research-units-pipeline-skills 377
-
survey-seed-harvest
Identify survey/review papers in a retrieved set and extract taxonomy seeds into `outline/taxonomy.yml` (topics/subtopics/terminology).
**Trigger**: survey seed harvest, taxonomy seeds, 从 survey 提 taxonomy, bootstrap taxonomy.
**Use when**: retrieval/dedup 后想快速从已有 survey/review 论文中提取术语与主题结构，用于加速 `taxonomy-builder`。
**Skip if**: 已经有高质量 taxonomy（或你不想被 survey 既有框架限制）。
**Network**: none.
**Guardrail**: 产物是 seed，必须经 `taxonomy-builder` 重写与对齐 scope；避免生成泛化占位节点。
WILLOSCAR/research-units-pipeline-skills 377
-
subsection-writer
Write survey prose into per-section files under `sections/` so each unit can be QA'd independently before merging.
**Trigger**: subsection writer, per-section writing, split sections, sections/, 分小节写, 按章节拆分写作.
**Use when**: `Approve C2` is recorded and writer packs exist (`outline/writer_context_packs.jsonl`); you want evidence-bounded drafting without a monolithic one-shot draft.
**Skip if**: `DECISIONS.md` approval is missing, or `outline/evidence_drafts.jsonl` / `citations/ref.bib` is missing.
**Network**: none.
**Guardrail**: do not invent facts/citations; no TODO/ellipsis leakage; keep citations subsection- or chapter-scoped; H3 body files and chapter leads must not contain headings.
WILLOSCAR/research-units-pipeline-skills 377
-
paragraph-curator
Structured paragraph curation for C5: **select -> evaluate -> subset -> fuse**, so drafts converge instead of only expanding.
**Trigger**: paragraph curator, curation, select evaluate fuse, paragraph selection, 选段, 评价, 融合, 收敛, 去冗余.
**Use when**: you are in C5, `sections/*.md` exist, and the writing loop drifts toward 'longer by accumulation' (repetition, redundant paragraphs, weak synthesis).
**Skip if**: evidence packs are thin / `evidence-selfloop` is BLOCKED; or you are pre-C2 (NO PROSE).
**Network**: none.
**Guardrail**: do not invent facts; do not add/remove citation keys; do not move citations across subsections; keep section-level claims consistent with `output/ARGUMENT_SKELETON.md# Consistency Contract`.
WILLOSCAR/research-units-pipeline-skills 377
-
redundancy-pruner
Remove repeated boilerplate across sections (methodology disclaimers, generic transitions, repeated summaries) while preserving citations and meaning.
**Trigger**: redundancy, repetition, boilerplate removal, 去重复, 去套话, 合并重复段落.
**Use when**: the draft feels rigid because the same paragraph shape and disclaimer repeats across many subsections.
**Skip if**: you are still drafting major missing sections (finish drafting first).
**Network**: none.
**Guardrail**: do not add/remove citation keys; do not move citations across subsections; do not delete subsection-specific content.
WILLOSCAR/research-units-pipeline-skills 377
-
section-mapper
Map papers from the core set to each outline subsection and write `outline/mapping.tsv` with coverage tracking.
**Trigger**: section mapper, mapping.tsv, coverage, paper-to-section mapping, 论文映射, 覆盖率.
**Use when**: structure 阶段（C2），已有 `papers/core_set.csv` + `outline/outline.yml`，需要确保每小节有足够支持论文再进入 evidence/writing。
**Skip if**: 还没有 outline（先跑 `outline-builder`）或 core set 还没收敛。
**Network**: none.
**Guardrail**: 覆盖率可审计（避免所有小节重复用同几篇）；为弱覆盖小节留下明确补救方向（扩 query / 合并小节）。
WILLOSCAR/research-units-pipeline-skills 377
-
extraction-form
Extract study data into a structured table (`papers/extraction_table.csv`) using the protocol’s extraction schema.
**Trigger**: extraction form, extraction table, data extraction, 信息提取, 提取表.
**Use when**: systematic review 在 screening 后进入 extraction（C3），需要把纳入论文按字段落到 CSV 以支持后续 synthesis。
**Skip if**: 还没有 `papers/screening_log.csv` 或 protocol 未锁定。
**Network**: none.
**Guardrail**: 严格按 schema 填字段；不要在此阶段写 narrative synthesis（那是 `synthesis-writer`）。
WILLOSCAR/research-units-pipeline-skills 377
-
research-pipeline-runner
Run this repo’s Units+Checkpoints research pipelines end-to-end (survey/综述/review/调研/教程/系统综述/审稿), with workspaces + checkpoints.
**Trigger**: run pipeline, kickoff, 继续执行, 自动跑, 写一篇, survey/综述/review/调研/教程/系统综述/审稿.
**Use when**: 用户希望端到端跑流程（创建 `workspaces/<name>/`、生成/执行 `UNITS.csv`、遇到 HUMAN checkpoint 停下等待）。
**Skip if**: 用户明确要手工逐条执行（用 `unit-executor`），或你不应自动推进到 prose 阶段。
**Network**: depends on selected pipeline (arXiv/PDF/citation verification may need network; offline import supported where available).
**Guardrail**: 必须尊重 checkpoints（无 Approve 不写 prose）；遇到 HUMAN 单元必须停下等待；禁止在 repo root 创建 workspace 工件。
WILLOSCAR/research-units-pipeline-skills 377
-
taxonomy-builder
Build a 2+ level taxonomy (`outline/taxonomy.yml`) from a core paper set and scope constraints, with short descriptions per node.
**Trigger**: taxonomy, taxonomy builder, 分类, 主题树, taxonomy.yml.
**Use when**: survey/snapshot 的结构阶段（NO PROSE），已有 `papers/core_set.csv`，需要生成可映射且读者友好的主题结构。
**Skip if**: 已经有批准过且可映射的 taxonomy（不要无意义重构）。
**Network**: none.
**Guardrail**: 避免泛化占位桶；保持 2+ 层且每节点有具体描述。
WILLOSCAR/research-units-pipeline-skills 377
-
thesis-citation-enhance-review
为中文毕业论文补强并核验引用：找出必须有引文支撑的句子，扩展候选文献，检查引用与论断是否匹配，并回写参考文献与正文引用。
**Trigger**: 引用补强, citation enhance, 文献补充, 引用核验, 毕业论文参考文献检查.
**Use when**: 正文已有一定稳定度，需要系统补足背景、定义、对照工作和关键结论的引用支撑，并检查是否存在误引或漏引。
**Skip if**: 还没有稳定正文，或当前仅在做早期结构重构。
**Network**: optional.
**Guardrail**: 不为了堆引用而堆引用；引用必须与论断匹配；先补对，再补多。
WILLOSCAR/research-units-pipeline-skills 377
-
exercise-builder
Add exercises to each tutorial module (inputs, expected outputs, verification steps) and update `outline/module_plan.yml`.
**Trigger**: exercises, practice, verification checklist, 教程练习, 可验证作业.
**Use when**: 已有模块计划（`outline/module_plan.yml`），需要为每个模块补齐至少 1 个可验证练习以形成 teaching loop。
**Skip if**: 还没有 module plan（先跑 `module-planner`）。
**Network**: none.
**Guardrail**: 每个练习必须包含 expected output + verification steps；避免只给“思考题”无验收。
WILLOSCAR/research-units-pipeline-skills 377
-
claim-matrix-rewriter
Rewrite `outline/claim_evidence_matrix.md` as a projection/index of evidence packs (NO PROSE), so claims/axes are driven by `outline/evidence_drafts.jsonl` rather than outline placeholders.
**Trigger**: claim matrix rewriter, rewrite claim-evidence matrix, evidence-first claim matrix, matrix index, 证据矩阵重写, 从证据包生成矩阵.
**Use when**: `outline/subsection_briefs.jsonl` + `outline/evidence_drafts.jsonl` are ready and you want a clean claim→evidence index for QA/writing.
**Skip if**: `outline/claim_evidence_matrix.md` is already refined and consistent with evidence packs.
**Network**: none.
**Guardrail**: NO PROSE; do not invent facts; only cite keys present in `citations/ref.bib`; if evidence is abstract/title-only, claims must be provisional.
WILLOSCAR/research-units-pipeline-skills 377
-
appendix-table-writer
Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.
**Trigger**: appendix tables, publishable tables, survey tables, reader tables, 附录表格, 可发表表格, 综述表格.
**Use when**: you have C4 artifacts (evidence packs + anchor sheet + citations) and want tables that look like a real survey (not internal logs).
**Skip if**: `outline/tables_appendix.md` already exists and is refined (>=2 tables; citation-backed; no placeholders; not index-y).
**Network**: none.
**Guardrail**: no invented facts; no pipeline jargon; no paragraph cells; use only keys present in `citations/ref.bib`.
WILLOSCAR/research-units-pipeline-skills 377
-
snapshot-writer
Write a 1-page literature snapshot (`output/SNAPSHOT.md`) from a small core set + a bullets-only outline.
**Trigger**: snapshot, literature snapshot, 速览, 48h snapshot, one-page snapshot, SNAPSHOT.md.
**Use when**: 你要在 24-48h 内交付一个“可读的研究速览”（bullet-first，含关键引用），而不是完整 survey。
**Skip if**: 你已经进入 evidence-first survey 写作（有 `outline/evidence_drafts.jsonl` / `citations/ref.bib` / `output/DRAFT.md`），应改用 `subsection-writer`/`prose-writer`。
**Network**: none.
**Guardrail**: 不发明论文/引用；引用只来自 `papers/core_set.csv`（或同 workspace 的候选池）；不写长段落（避免“像综述生成器”）。
WILLOSCAR/research-units-pipeline-skills 377
-
synthesis-writer
Synthesize evidence into a structured narrative (`output/SYNTHESIS.md`) grounded in `papers/extraction_table.csv`, including limitations and bias considerations.
**Trigger**: synthesis, evidence synthesis, systematic review writing, 综合写作, SYNTHESIS.md.
**Use when**: systematic review 完成 screening+extraction（含 bias 评估）后进入写作阶段（C4）。
**Skip if**: 还没有 `papers/extraction_table.csv`（或 protocol/screening 尚未完成）。
**Network**: none.
**Guardrail**: 以 extraction table 为证据底座；明确局限性与偏倚；不要在无数据支撑时扩写结论。
WILLOSCAR/research-units-pipeline-skills 377
-
citation-injector
Apply a `citation-diversifier` budget report by injecting *in-scope* citations into an existing draft (NO NEW FACTS), so the run passes the global unique-citation gate without citation dumps.
**Trigger**: citation injector, apply citation budget, inject citations, add citations safely, 引用注入, 按预算加引用, 引用增密.
**Use when**: `output/CITATION_BUDGET_REPORT.md` exists and you need to raise *global* unique citations (or reduce over-reuse) before `draft-polisher` / `pipeline-auditor`.
**Skip if**: you need more papers/citations upstream (fix C1/C2 mapping first), or `citations/ref.bib` is missing.
**Network**: none.
**Guardrail**: NO NEW FACTS; do not invent citations; only inject keys present in `citations/ref.bib`; keep injected citations within each H3’s allowed scope (via the budget report); avoid citation-dump paragraphs (embed cites per work).
WILLOSCAR/research-units-pipeline-skills 377
-
keyword-expansion
Expand and refine search keywords (synonyms, acronyms, exclusions) and update `queries.md`.
**Trigger**: keyword expansion, synonyms, exclusions, queries.md, 关键词扩展, 同义词, 排除词.
**Use when**: 检索覆盖不足/噪声过大，或主题别名很多，需要系统化扩展与收敛检索词。
**Skip if**: `queries.md` 已经能稳定检出覆盖面（无需扩大范围导致后续成本爆炸）。
**Network**: none.
**Guardrail**: 保持可控的 query 数量；明确 exclusions；避免“无限扩展”。
WILLOSCAR/research-units-pipeline-skills 377
-
post-merge-voice-gate
Post-merge paper-voice gate: detect planner-talk / axis-label artifacts introduced during merge (especially from `outline/transitions.md`), then route fixes back to the earliest source.
**Trigger**: post-merge voice gate, merge voice gate, transition leakage, planner talk, 合并后口吻门, 过渡句污染.
**Use when**: `section-merger` has produced `output/DRAFT.md` and you want to ensure merge-injected text won't drag the draft into generator voice before polishing.
**Skip if**: you are still pre-merge (no `output/DRAFT.md`) or you plan to rework structure upstream first.
**Network**: none.
**Guardrail**: analysis-only; do not edit `output/DRAFT.md`; do not invent facts/citations; write only the report + routing.
WILLOSCAR/research-units-pipeline-skills 377
-
hash-calculator
Calculate cryptographic hashes (MD5, SHA1, SHA256, SHA512) for text and files. Compare hashes, verify integrity, and batch process directories.
dkyazzentwatwa/chatgpt-skills 41
-
mcp-builder
Guide for building MCP (Model Context Protocol) servers that integrate external APIs/services with LLMs. Covers Python (FastMCP) and TypeScript (MCP SDK) implementations.
dkyazzentwatwa/chatgpt-skills 41
-
data-quality-auditor
Assess data quality with checks for missing values, duplicates, type issues, and inconsistencies. Use for data validation, ETL pipelines, or dataset documentation.
dkyazzentwatwa/chatgpt-skills 41
-
statistical-analyzer
Perform statistical hypothesis testing, regression analysis, ANOVA, and t-tests with plain-English interpretations and visualizations.
dkyazzentwatwa/chatgpt-skills 41
-
data-anonymizer
Detect and mask PII (names, emails, phones, SSN, addresses) in text and CSV files. Multiple masking strategies with reversible tokenization option.
dkyazzentwatwa/chatgpt-skills 41