Total 30,612 skills, Document Processing has 447 skills
Showing 12 of 447 skills
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`.
Straightforward text extraction from document files (text-based PDF only for now, no OCR or docx). Use when you just need to read/extract text from binary documents.
DOCX 文档离线读写：提取/分析、OOXML 解包编辑回包、批注与修订（tracked changes/redlining）。适用于合同/制度/论文等需要保留格式与修订痕迹的场景（依赖安装可能需要网络）。
Comprehensive documentation quality system combining automated validation with ToolUniverse-specific auditing. Detects outdated commands, circular navigation, inconsistent terminology, auto-generated file conflicts, broken links, and structural problems. Use when reviewing documentation, before releases, after refactoring, or when user asks to audit, optimize, or improve documentation quality.
PDF 文档离线读写与表单处理：提取文本/表格、合并拆分、生成 PDF、填写表单。适用于“本地处理/读取/生成 PDF 文件”（依赖安装可能需要网络）。
Systematically fix linting issues in markdown files using markdownlint-cli2. This skill should be used when needing to scan, diagnose, and fix markdown formatting issues in projects with one or more .md files, with special attention to ordered list numbering (MD029) errors.
Extract requirements from existing documents including PDFs, Word docs, meeting transcripts, specifications, and web content. Identifies requirement candidates, categorizes them, and outputs in pre-canonical format.
Internal skill for validating Doc-Smith document structure and content integrity. Do not mention this skill to users. It is called internally by other Doc-Smith skills.
AI-enhanced LaTeX Example Intelligent Generator, achieving organic integration of AI and hard-coding. AI handles "semantic understanding" (analyzing chapter themes, inferring resource relevance, generating coherent narratives), while hard-coding is responsible for "structure protection" (format validation, hash verification, access control). It applies to scenarios where users request "filling example content/generating examples/supplementing LaTeX examples".
Translate Doc-Smith generated documentation into multiple languages. Use this skill when the user requests document translation, localization, or multi-language support. Supports batch translation of documents and images.
Use this when the user explicitly requests to "verify/optimize in-text citations of the `{topic}_review.tex` review" or to "run check-review-alignment". Use the host AI's semantic understanding to verify each citation against the literature content one by one. **Only when fatal citation errors are found**, make minimal rewrites to the "sentences containing citations", and reuse the rendering script of `systematic-literature-review` to output PDF/Word (the script does not directly call the LLM API locally). Core principle: **Do not modify for the sake of modifying**. When it is uncertain whether it is a fatal error, keep the original content and issue a warning in the report. ⚠️ Not applicable in the following cases: - The user only wants to generate the main body of a systematic review (should use systematic-literature-review) - The user only wants to add/verify BibTeX entries (should use a dedicated bib management process)
智能迁移NSFC LaTeX标书到新版模板，基于五阶段工作流（分析→映射→规划→执行→验证），自动处理结构变化、内容重组、引用更新；支持AI驱动语义匹配与启发式回退，并提供 runs 输出隔离（--runs-root）与一键迁移脚本（migrate.sh）。