Docs & Writing
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
-
photonics-dhl Skill Tex2docxLaTeX (ctexart) → DOCX 格式保持转换。三步流程: 1. python-docx 生成匹配 ctexart 样式的 reference.docx 模板 2. pandoc + reference.docx 执行转换(公式→OMML、图片嵌入) 3. python-docx 后处理(中文字体、图注识别、表格线型、图片尺寸) 触发场景: - 用户需要将 LaTeX 文件转为 Word 文档并保持格式 - 用户说"转 docx"、"输出 Word 版本"、"转成 Word" - 中期报告、论文等需要提交 DOCX 格式时 依赖:python-docx、pandoc 3.x
-
photonics-dhl Skill Referee Review审稿人专用技能。当用户提到以下任何场景时必须自动触发: - "审稿"、"审稿意见"、"审稿信"、"写审稿意见"、"帮我看这篇论文作为审稿人" - "review this paper"、"referee report"、"peer review" - "评价这篇稿件"、"给这篇论文写审稿意见"、"作为审稿人" - 收到期刊审稿邀请、需要提交审稿报告 7阶段系统化审稿流程(初评→逐节→统计→可复现→图表→研究诚信→写作质量)。 生成中英双语标准审稿信,含物理/光学实验特有审查项。 注意:本 skill 是"审别人的论文",不是自审(paper-review)也不是写作诊断(academic-craft)。
Audited -
photonics-dhl Skill Mid Term ReportMid Term Report
-
photonics-dhl Skill Word Form Filler填写 Word (.docx) 表格表单,格式零破坏。完整流程: 1. 用 python-docx 深度解析文档结构(段落/表格/合并单元格/表单域) 2. 定位可填写区域(区分指引行 vs. 内容行) 3. 保留原始格式(rPr/pPr)写入内容 4. 备份原文件 → 写入 → 验证 → Humanizer 润色 触发场景: - 明确填写类:"帮我填表"、"填写申请表"、"填写 Word 表单"、"填这个 docx" - 修改内容类:"修改这个表格"、"在这个 docx 里填入"、"更新 Word 表格内容" - 批量操作类:"批量填表"、"把这些信息填到表格里"、"生成填写好的 Word 文档" - 文件路径指向 .docx 且语境为填写/修改/填入内容 - 提到"表格"、"表单"、"申请表"且目标文件是 Word 格式 - 任何需要在 .docx 表格中写入内容且保持格式的场景 依赖:python-docx(pip install python-docx)
-
photonics-dhl Skill Scientific SlidesBuild slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.
Audited -
photonics-dhl Skill PDFPDF Skill
-
photonics-dhl Skill DOCXDOCX Skill
-
photonics-dhl Skill PPTXPPTX Skill
-
waseemnasir2k26 Bundle QASystematically QA test a web application. Use when asked to "qa", "QA", "test this site", "find bugs", "dogfood", or review quality. Four modes: diff-aware (automatic on feature branches — analyzes git diff, identifies affected pages, tests them), full (systematic exploration), quick (30-second smoke test), regression (compare against baseline). Produces structured report with health score, screenshots, and repro steps.
-
haohao-end Bundle Notion Research DocumentationResearch & Documentation
-
hantechnology Bundle Documentation SdkPlanned adjacent, non-primary: Deliver API and SDK-facing documentation guidance for design-first contracts, generated references, examples, and release-adjacent doc updates without widening into generic product docs.
-
layneformalized225 Bundle Exa Code SearchCode search using Exa. Finds real code snippets, API docs, and examples from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help.
-
philrobinluo Bundle Lls Word Memory Coach用中文帮助记忆英语单词:结合语境翻译、发音与自然拼读、可信构词、谐音或画面联想,并用主动回忆检查。适用于“这个单词怎么记”“帮我记单词”“用多种方法记住这些词”等请求;只要求翻译时不强加记忆训练。
-
philrobinluo Bundle Lls Article Screenshot为教程、产品复盘和操作说明规划并采集能证明关键步骤的真实界面截图。用于决定截图证据点、清理演示环境、在 macOS 选择区域/窗口/全屏模式、规范命名、生成 Markdown 引用和交付前隐私复核时;必须先写每张图要证明的事实,优先最小范围截图,不用装饰性图片冒充执行证据。
-
philrobinluo Bundle Lls Ppt Briefing CoachUse this skill when the user needs a guided PPT需求澄清、PPT策划访谈、PPT生成指令整理、汇报/培训/路演/答辩/提案类演示文稿前期策划. It asks one stage at a time across scenario, audience, content, outline, visual style, materials, and special requirements, then outputs a complete markdown PPT generation brief.
-
philrobinluo Bundle Lls Document Print Restorer把仍可辨认的纸质文件照片保守增强、规范排版成 A4 PDF,并保留输入哈希、处理参数、预览和人工核对记录。用于表格、票据、手写页或旧文档偏灰、轻微模糊、方向错误、边距不适合打印时;只改善可见内容,不猜测或重造缺失文字、数字、签名、公章和法律证据。
-
philrobinluo Bundle Lls Slide Storyline Planner把汇报、路演、教学或方案材料整理成一条听众能跟上的演示故事线。用于确定主结论、听众认知变化、章节逻辑、关键证据、逐页结论标题和删减顺序时;只负责内容叙事与页面任务,不替代完整 PPT 制作流程,必须先明确演示场景和期望决策,不从模板、配色或页数直接开始。
-
advaitpaliwal Skill PreviewPreview Markdown, LaTeX, PDF, or code artifacts when preview commands are visible, or fall back to shell/browser tools. Use when the user wants to review a written artifact, export a report, or view a rendered document.
-
advaitpaliwal Skill PDF ExploreRead, extract, and cross-check content across scientific PDFs. Use when a task needs methods, figures, tables, citations, accessions, or claims from multiple places in one or more papers.
Audited -
advaitpaliwal Skill Deep ResearchRun a thorough, source-heavy investigation on any topic. Use when the user asks for deep research, a comprehensive analysis, an in-depth report, or a multi-source investigation. Produces a cited research brief with provenance tracking.
Audited -
advaitpaliwal Skill Paper WritingTurn research findings into a polished paper-style draft with sections, equations, and citations. Use when the user asks to write a paper, draft a report, write up findings, or produce a technical document from collected research.
Audited -
guoliang1114-boop Skill PDF ManagementPDF file management toolkit. Use when the user needs to (1) merge multiple PDFs into one, (2) split a PDF into multiple files, (3) extract specific pages from a PDF, (4) read PDF text content, (5) add watermark to PDF. Supports advanced PDF operations beyond simple reading.
-
guoliang1114-boop Bundle AI Strategy ReportGenerate comprehensive AI strategy reports (15+ slides) in PowerPoint format. Analyzes company's digital readiness, identifies high-value AI use cases, creates implementation roadmaps, and provides ROI projections. Designed for consulting firm quality deliverables.
-
guoliang1114-boop Bundle Consulting Proposal AdvisorCreate client-ready consulting proposals, PPT outlines, PPTX decks, business cases, SOWs, roadmaps, and executive recommendations.
-
guoliang1114-boop Skill Tp Documentation Preparation转让定价文档准备:主体文档、本地文档、国别报告,基于OECD BEPS第13项行动计划及中国国家税务总局公告2016年第42号
-
isvlasov Skill CodifySweep the project's LEARNINGS.md inbox and turn accumulated entries into durable skill, rule, or documentation changes. Run when ready to process learnings — not mid-task.
-
isvlasov Bundle Working With PdfsHandles PDF operations (reading, creating, modifying). Use when extracting text from PDFs, converting markdown to PDF, merging or splitting PDFs, compressing, rotating pages, handling metadata, or when Claude Code's native PDF reading fails.
-
isvlasov Skill Assessing QualityConducts quality reviews of non-code artefacts. Use when reviewing or critiquing Skills, agents, workflows, documentation, or written materials, assessing quality against standards, or providing structured feedback.
-
isvlasov Skill Communicating In WritingGuides written communication — emails, reports, presentations, documents, website copy, newsletters, books. Use when writing or improving writing, adapting to an audience, or shaping document structure. Not for oral delivery or tool-specific formatting (slides, PDFs).
-
kriscard Bundle DocsReader-job technical documentation: READMEs, API docs, architecture docs, how-tos, RFCs, design docs, and ADRs. Use when writing, revising, or reviewing docs for other developers.
-
kriscard Bundle TalkConference talk builder for technical CFP submissions, speaking proposals, timed talk outlines, and slide flows. Use when the user asks for a conference talk, CFP abstract, talk proposal, or to turn a project/article into a speaking proposal.
-
kriscard Skill TutorialCheckpointed tutorial writer for step-by-step technical teaching: visible end state, dependency-ordered steps, working checkpoints, and mechanism explanations. Use when the user asks to create, draft, revise, or outline a tutorial, step-by-step guide, onboarding guide, or documentation that teaches a skill.
-
luckyrjain Bundle Test WriterThin orchestration router for test-writing requests that do not resolve to one specialist up front. Classifies the request into one or more complementary test levels, builds an ordered test_plan, then dispatches unit-test-creator, integration-test-creator, contract-test-creator, e2e-test-creator, and/or api-test-creator as required. Preserves each specialist's gates and report verbatim. A single explicitly named level still routes directly to that specialist. Keywords: write tests, generate tests, add test coverage, backfill tests, test this MR/PR/diff.
-
luckyrjain Bundle Bug DiagnosisDiagnose a non-incident bug, test failure, or performance regression: confirm a minimal repro, form candidate root causes and actively try to falsify each one with evidence, report the confirmed root cause. Use when a bug or regression needs its root cause found before it can be fixed, outside a live production incident. Keywords: diagnose this bug, why is this failing, root cause of this test failure, performance regression diagnosis, reproduce this bug. Not for a live production incident with a time window (incident-rca), or applying the fix once the cause is known (loop-task-implementer).
-
luckyrjain Bundle Weekly Squad DigestScheduled digest combining migration-program-manager's and cost-optimization-sprint-planner's own rollup JSON outputs into one squad-grouped report — never re-runs either aggregator, never re-derives squad/status/priority. Keywords: weekly squad digest, combined rollup, org-wide status roundup. Not for a fresh migration or cost rollup (migration-program-manager / cost-optimization-sprint-planner directly) or a plain ownership lookup (squad-map).
-
xonevn-ai Bundle Scenario AnalyzerBuild 18-month investment scenarios from news headlines. The skill orchestrates two subagents: scenario-analyst runs the primary analysis (Base/Bull/Bear cases, 1st/2nd/3rd-order sector impacts, positive/negative stock picks), and strategy-reviewer provides a critical second opinion (missed sectors, bias detection, probability sanity-check, alternative scenarios). Produces a single integrated Markdown report under reports/. Use when the user wants to think through how a news event will play out over ~18 months. Example: /scenario-analyzer "Fed raises rates by 50bp". Triggers: news headline analysis, scenario analysis, 18-month outlook, medium-term investment strategy.
Frequently asked questions
What are Docs & Writing agent skills?
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
Which Docs & Writing skills are most installed?
Popular Docs & Writing skills on SkillMD right now include tex2docx, referee-review, mid-term-report. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Docs & Writing skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.