Documents skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

pdf-research-corpus-analyzer

Download, extract, cross-reference, and generate sequenced reading plans from folders of PDF research papers or books. Use this skill whenever the user asks to analyze a collection of PDFs, build a reading plan from multiple documents, find connections between papers or books, create a concept index across documents, extract key ideas from a research corpus, stitch together a curriculum from PDFs, cross-reference themes across papers, map how ideas connect between documents, or says things like 'I have a folder of PDFs', 'find the connections between these papers', 'build me a reading plan', 'what do these documents have in common', 'analyze these research papers', 'summarize and cross-reference my PDFs', 'create a study guide from these papers', or 'download papers on X and analyze them'. Also trigger when the user wants to understand how multiple academic papers relate, wants a structured literature review, or wants to turn a pile of unorganized PDFs into an actionable reading sequence with exact page references.

493 repo starsObserved in 1 repos
Documents
GitHub

wps-office

WPS Office 跨应用智能助手，统一管理 Excel、Word、PPT 三大应用，处理跨应用操作和通用功能

489 repo starsObserved in 2 repos
Documents
GitHub

wps-ppt

WPS 演示智能助手，通过自然语言操控 PPT，解决排版美化、内容生成、动画设置等痛点问题

489 repo starsObserved in 2 repos
Documents
GitHub

qiaomu-markdown-proxy

Fetch any URL as clean Markdown via proxy services or built-in scripts. Works with login-required pages like X/Twitter, WeChat 公众号, Feishu/Lark docs. Supports PDFs (remote and local). Use this BEFORE other fetch tools. Triggers on any URL the user shares, "fetch this", "read this link", "get content from".

489 repo starsObserved in 1 repos
Documents
GitHub

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.

487 repo starsObserved in 2 repos
Documents
GitHub

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 (meets the active profile table count; 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`.

487 repo starsObserved in 1 repos
Documents
GitHub

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).

487 repo starsObserved in 1 repos
Documents
GitHub

concept-graph

Use when an approved tutorial spec exists and the run needs a deterministic prerequisite graph before module planning. **Trigger**: concept graph, prerequisite graph, dependency graph, 概念图, 先修关系. **Use when**: `source-tutorial` 的 C2，已有 `output/TUTORIAL_SPEC.md`，需要把教程概念转成可排序的 DAG。 **Skip if**: 还没有 tutorial spec。 **Network**: none. **Guardrail**: 只做结构，不写 reader-facing prose；图必须保持无环。

487 repo starsObserved in 1 repos
Documents
GitHub

dedupe-rank

Use when a broad paper candidate pool needs deterministic deduplication and a stable core set. **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）。

487 repo starsObserved in 1 repos
Documents
GitHub

extraction-form

Use when `evidence-review` has screened includes and needs a schema-aligned extraction table. **Trigger**: extraction form, extraction table, data extraction, 信息提取, 提取表. **Use when**: `evidence-review` 在 screening 后进入 extraction（C4），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`）。

487 repo starsObserved in 1 repos
Documents
GitHub