Docs & Writing

llnl Bundle

Extracts features from volumetric, mask, and skeleton .npy files and generates a visual report with specific 3D perspectives.

logseq Skill

Use when working with Logseq graphs through the Logseq plugin, especially creating tasks, editing properties, organizing pages or blocks, searching, or capturing notes. Ensures ChatGPT uses Logseq DB graph semantics instead of legacy file-graph markdown conventions.

longsizhuo Bundle

帮助新手把 BossZhiPin_Job_Search 这个 BOSS 直聘自动打招呼脚本跑起来。覆盖两种用户路径——(A) 直接下载桌面 App（.app / .dmg / .exe）的非开发者，常见症状："Gatekeeper 拦"、"双击没反应"、".app 闪退"、"GUI 里配 API key"、"界面中英文怎么切"、"用不明白想让 AI 看看状态（「问 AI 帮忙」按钮）"；以及 (B) clone 源码 + uv 跑命令行的开发者，常见症状："uv 命令找不到"、"扫码扫不上"、"Chrome 起来空白"、"卡在哪一步"。当用户提到 BossZhiPin_Job_Search、BOSS 直聘脚本、自动招呼语、my_cover.pdf、chrome_profile、DEEPSEEK_API_KEY、Tauri、DMG 安装、PyTauri 等本项目特有概念，或者明显在按 README 走但被某一步卡住时，主动使用此 skill。即使用户没有明说"帮我装"，只要场景对得上就用。

lora-sys Bundle

科研助手技能，支持文献检索、学术脉络梳理、论文写作润色、技术路线图生成等全流程科研任务。当用户提及以下场景时触发：(1) 查找/检索文献、找论文、找参考；(2) 梳理学术脉络、概念演进、后续改进；(3) 论文润色、中英互译、改写降重、语法检查；(4) 写摘要、Cover letter、取标题；(5) 参考文献格式检查、APA校正；(6) 绘制技术路线图、生成Drawio图；(7) 科研配图、降AIGC；(8) 上传PDF/图片后解读；(9) 图表生成、数据可视化；(10) 任何SCI论文写作相关任务。

lottshin Bundle

Search, download, and manage academic papers from CNKI (知网), OpenAlex, Semantic Scholar, arXiv, NSSD, DBLP, and BASE; enriches metadata via Crossref and resolves OA links via Unpaywall. Generates citations (GB/T 7714, APA, MLA, Chicago, BibTeX, RIS), writes literature reviews, suggests inline references, analyzes citation networks, and generates research trend reports. Use when the user asks to 搜索/检索/查找 文献/论文, 下载论文/全文, 写文献综述, 引用建议/插入文献, 选题分析/研究选题/研究问题, 格式化参考文献, 参考文献, 引文追踪/引用网络/谁引用了, 研究趋势/热点分析, 文献对比/对比矩阵, 阅读笔记, 学术表达优化/论文改写/提升原创性, 查重/降重/降低重复率/重复率, 知网/CNKI, 批量导出/计量分析, or 导出BibTeX/RIS. DO NOT USE for general web search, non-academic content, or code documentation lookup.

louisedesadeleer Bundle

Source b-roll for a video edit — classify each moment, scope the search, return vetted candidates, place on the word. Use when the user says "find b-roll", "/find-broll", "source clips for this edit", or wants footage/memes/screenshots to lay over a talking-head video.

louisedesadeleer Bundle

Find compelling moments in a video — funny dialogue OR repeated impact actions like axe chops, hits, throws, drumbeats — cut them as standalone clips, optionally reformat 16:9 ↔ 9:16, time-warp pans for tighter reveals, and burn opus-style word-by-word captions. Use when the user mentions "clipify," "cut clips from this video," "make shorts from this," "find funny moments," "action montage," "cut on each chop/hit/punch," "reframe to 9:16," "vertical clips," or pastes a video file path and wants social-ready cuts.

louisedesadeleer Bundle

Tighten a long recording aggressively — remove silences, fillers, hedges, false starts, and repetitions while preserving laughs and comedic pauses. Cuts are driven by Montreal Forced Aligner (MFA) word boundaries (auto-installs on first run), not raw Whisper timestamps. Use when the user pastes a video and says "cut this", "tighten this video", "remove silences", "strip ums", "clean this up", or any variant of "make this video shorter without losing the good parts".

louisedesadeleer Bundle

Save the opening hook and first frame from a TikTok link, or sync new videos from a private TikTok collection, into a local Markdown or Obsidian swipe file. Use when someone asks to save a TikTok hook, sync their hook collection, configure their hook destination, or schedule collection syncing.

lovstudio Bundle

Analyze articles for AI-generated content indicators and rewrite to pass WeChat's 3.27 non-human automated content creation detection. Checks for template phrases, transition word density, sentence uniformity, paragraph pattern repetition, and other signals that WeChat uses to flag AI content. Outputs a risk report and an optional humanized rewrite. Use when the user wants to check if an article looks AI-generated, make an article more human-like, bypass WeChat AI detection, or humanize AI-written content. Also trigger when the user mentions "去AI痕迹", "人性化润色", "微信AI检测", "anti-ai-check", "humanize article", "公众号发文检查".

lowellran Bundle

全局自适应 10 倍速 AI 辅助高效学习导师。具备全球化全语种母语自适应能力（根据用户交互语言无缝自动对齐系统语言、讲授内容、指令反馈、档案文档与考核机制）。支持主题/文档/视频/链接等输入源，自动建立 5 级学习阶梯与 20 小时精选计划（10 次，每次 2 小时）。具备状态机驱动单点教学、暗黑硬核考官（拒绝 AI 讨好味与 0 分死刑机制、学员原话手术刀解剖、导师级降维打击满分解法示范）、12 岁费曼反向审判、外部状态解耦（防漂移与机器状态头 100% 确定性断点续学）、原生工具静默落盘 12 份标准 Markdown 档案体系，并支持 /skip、/jump（带依赖安全气囊）等快捷交互指令。

lucaswangzcx Bundle

Read academic papers from a provided PDF, URL, text, DOI, title, or citation and produce a teaching-first structured interpretation report, usually saved to a user-specified directory as a PDF with a Markdown source copy. Use when the user wants to genuinely understand, learn, summarize, deconstruct, critique, reproduce, compare, apply, or write a report about a scholarly article; especially for Chinese requests such as 读懂论文, 论文精读, 论文学习报告, 三遍阅读法, 逐段精读, 解构论文, 生成论文解读报告, 输出到指定目录, 输出PDF, PDF报告, 分析论文贡献/方法/实验/局限/可复现性.

luchi2333 Bundle

用于一线职工创新课题的端到端 TRIZ 研究：把现场问题转化为带证据标记的问题模型，对经典 39×39 矛盾矩阵做确定性查询，完成可复现的标准/产品/专利/文献查新、可追溯候选方案、安全与验证闸门、效益测算和技术方案报告。End-to-end TRIZ research for frontline worker innovation: evidence-labelled problem modelling, deterministic Altshuller 39x39 matrix lookup, reproducible research, gated concepts, benefit estimates and a technical-solution report. 自包含：不得要求用户另装 deep-research、矩阵插件或多智能体框架。Do not use as a patentability/FTO legal opinion or to claim field performance without measured evidence.

lululu811 Bundle

**Financial Report Downloader**: Auto-search and download A-share/HK stock financial report PDFs from Xueqiu (stockn.xueqiu.com) or 同花顺 (notice.10jqka.com.cn). - MANDATORY TRIGGERS: download report, 下载财报, 下载年报, 下载中报, annual report download, financial report PDF, 雪球财报, 同花顺财报

lupynow Bundle

简历制作、审改与真实性审计。当用户要写简历、改简历、优化简历、诊断简历、为投递某岗位定制简历，或让你"看看我的简历"时使用。也适用于：从零开始造简历、贴出岗位 JD 问怎么改、基于简历预测面试追问点、把周报或项目文档整理成简历素材、简历翻译。即使用户只说"简历"两个字，或者丢来一个 .docx 文件，也应该用这个 skill。Use this skill whenever the user mentions resume, CV, 简历, 求职, 投递, or shares a resume file — even casually. 泛泛的面试题练习、自我介绍润色、求职邮件撰写不属于本 skill，除非用户明确要求结合简历来做。

shirenchuang Bundle

Kuaifa (快发) — publish Markdown articles to WeChat Official Accounts via the kuaifa CLI. Use this skill whenever the user wants to publish an article to WeChat, publish image messages, manage kuaifa configuration or templates, or mentions '快发', 'kuaifa', 'publish to WeChat', '发布公众号', '微信发布', '发文章'. Also trigger when the user has a Markdown file and wants to distribute it to WeChat, or asks about WeChat article formatting and themes.

shmulc8 Bundle

Coach the user step-by-step through writing a conference talk proposal (CFP / Call for Papers) that content committees actually accept. Use this whenever the user is writing or brainstorming a talk proposal, an abstract or title for a tech talk, a speaker submission, or asks how to get accepted to speak at a conference — even if they just say "help me submit to [conference]" or "I have a talk idea" and don't use the word CFP. Also trigger when the user wants feedback on a draft abstract/title, is stuck for a talk idea, or wants to tailor an existing talk for a specific conference. This skill guides ideation, structure, and polish; it does NOT ghost-write a finished proposal from a cold start.

shrektan Skill

Convert Markdown text or Markdown artifacts into professionally formatted .docx files using the formaldoc npm package. Use this skill whenever the user wants to export, download, or save Markdown content as a Word document (.docx), or asks to "generate a docx", "export to Word", "turn this into a Word file", "download as docx", or "save as document". Also trigger when the user has a Markdown artifact and asks for a formatted document version. Always prefer this skill over manual docx generation when Markdown source is available. Available templates: - cn-gov Chinese official document, GB/T 9704 style - cn-general Chinese general-purpose document - cn-academic Chinese academic paper - cn-report Chinese business or work report - en-standard Standard — Times New Roman + Arial - en-business Business — Calibri + Arial, modern - en-academic Academic — APA style, double-spaced - en-legal Legal — Contracts, legal docs

sihanyanliu-sys Bundle

Track public tech companies' AI investment through their official job-posting APIs (Greenhouse/Lever/Ashby) and turn hiring data into investment research signals. Use this skill whenever the user wants to collect or update hiring data, run the hiring signal report, add/remove/replace companies in the watchlist (股票池), analyze a company's AI hiring momentum, set up recurring collection, reconcile hiring signals with earnings data, or asks about 招聘信号 / AI 投入跟踪 / 招聘数据分析 — even if they don't name the skill. Also use it when a financial analyst asks how a tech company's expansion or AI strategy shows up in its hiring.

silkyland Bundle

Auto-generates a beautiful user manual with REAL screenshots captured by executable scripts: censuses the app's user flows from routes and navigation, builds a Playwright (Python) capture harness for web (the primary focus; mobile via Maestro is an optional path), seeds safe demo data so no real user data appears in images, writes the manual chapter-per-flow with a numbered step per screenshot, and renders it beautifully (MkDocs Material site, Markdown, or PDF). The capture scripts are committed, so the manual regenerates when the UI changes instead of rotting. Use when the user asks to generate a user manual, user guide, documentation with screenshots, onboarding docs, or mentions love-me-love-my-docs or /love-me-love-my-docs.

silkyland Bundle

Turns a vague bug report into a minimal, runnable reproduction BEFORE any fix is attempted: sweeps evidence (logs, stack traces, git history around first-seen, DB state), ranks hypotheses by evidence, builds the smallest failing automated test (or repro script) that demonstrates the bug on demand, minimizes it until every remaining step is load-bearing, handles intermittent/flaky bugs by forcing determinism and documenting the reproduction rate, and delivers a repro dossier that hands the fixer a ready-made regression test. Never fixes — reproduces. Use when the user reports a bug, says something breaks sometimes or only in production, asks to investigate, debug, or find the root cause of an issue, or mentions reproduce-my-bug or /reproduce-my-bug.

silviazeng Bundle

分寸 (fencun) — knowing what your position lets you say, and who else will read it. Run before drafting anything another person will read on the user's behalf: interview slides or talking points, a deck or memo for a company, a message to a hiring manager or an executive, a LinkedIn profile, post, or article, an industry write-up or field guide, a competitive comparison, a cover letter, an outreach DM. Use it whenever a draft names a real company, product, or person, or will be seen by a manager, colleague, customer, or the public, even if the user only asks for slides, a summary, an analysis, or a post and says nothing about tone. 适用于任何将由他人阅读的文字：面试材料、提交给公司的方案、致上级的邮件、LinkedIn、行业分析。It checks the piece has a thesis, then establishes the seat the user writes from and what happens when the document travels. It prevents the default failure of writing as a detached analyst who grades the reader's own products, tells their company what to do, and ranks third parties as winners and losers the user may later face.

siriusfzh Skill

NovaForge 通用知识笔记模板 — 将任意学科/项目的知识体系整理为结构化笔记。LaTeX+Typst+Markdown三版本，支持章节笔记（7步结构）、期末复习（真题分类+留白练习）、考研（7步+考研真题）、考公（行测/申论/面试）、科研（文献+笔记+方法）、项目（架构+进度+复盘）六种模式，适配考研/考公/专业课/科研/项目/竞赛。

smartaicoach Bundle

Use whenever an OmniGraffle document or .graffle, .gtemplate, or .gstencil file is involved, including reading, inspecting, extracting, creating, editing, repairing, rendering, validating, or converting SVG, PDF, Visio, and other supported formats to or from OmniGraffle.

smixs Bundle

Operate Didox.uz (Uzbekistan e-document exchange) end to end: turn a Word draft into a clean PDF, file any document type (акт, договор, ЭСФ счёт-фактура, акт сверки, доверенность, письмо) to a counterparty, accept or reject incoming documents, cancel sent ones, check signing status, look up companies and VAT status by ИНН/TIN, sign with the local E-IMZO key. Use when the user says didox / дидокс / didoks / дидокс.уз in any spelling or layout, or asks to выставить, подать or отправить акт/договор/СФ контрагенту, принять или отклонить входящий документ, проверить подписал ли контрагент, найти документ, пробить компанию по ИНН, подписать ЭЦП, hujjat yuborish — even if they don't say "Didox". Do NOT use for Russian EDO operators (Diadoc, СБИС).

smoldrago Bundle

Create clean, readable diagrams using Kroki with a use-case-first selector. Use when the user wants repository-local diagrams for architecture, runtime topology, request flows, dependency graphs, schemas, planning structures, or tree-like repository layouts from code, docs, or natural-language descriptions. Prefer this skill when the user wants versionable diagram source and the right engine chosen for the job. Do not use it for generic UI mockups, freeform graphic design, image editing, screenshots, slide design, or non-diagram data visualization.

sdfkr22 Bundle

Analyzes the current Claude Code session — conversation history AND changed code files — to detect potential bugs, technical debt, regressions, and performance issues, then creates structured GitHub issues for each one after user approval. Always use this skill when the user says "find bugs", "open issues", "create github issues", "bug report", "what bugs did we introduce", "session bugs", "hunt bugs", "report issues to github", or anything implying they want to capture problems from the current session as GitHub issues. Also trigger proactively when the user is wrapping up a session and there were visible errors, workarounds, or "fix later" comments during the session.

seasonedcc Skill

Generate code examples and usage patterns for the make-typed-env library. Use when writing examples, documentation, demos, answering questions about the make-typed-env API, or helping users set up type-safe environment variables with Standard Schema, Zod, Valibot, ArkType, or string-ts key transformations.

sebaslogen Skill

Run KoverGate coverage gate and fix coverage gaps after writing or modifying tests

seokhoonj Skill

Send a result, report, or file from the conversation as email. Holds no logic of its own -- it calls the mailmail package's send(), and always shows the recipients, subject, and attachments for approval before sending. Trigger phrases: send mail, email this, mail this, send this by email, email the report, 메일 보내줘, 메일로 보내, 메일 발송, 이거 메일로, 부장님께 보내줘, 상무님께 보내줘.

serenakeyitan Bundle

Create, curate, and maintain high-quality awesome lists on GitHub. Use when the user wants to build a curated resource list, organize tools by category or role, create a GitHub-based directory, or maintain an existing awesome list. Handles the full lifecycle: research and discover tools, organize by use-case workflows, deduplicate, format as clean markdown tables, add GitHub badges, and publish.

sheepmao Bundle

Use when converting Word documents (.doc/.docx) to clean Markdown with images extracted to a separate folder for readability and AI compatibility

stephenlzc Bundle

Compare two versions of a .docx document and produce a single Word file in tracked-changes (revision / tracking) mode, as if a human had edited the old file into the new one with Track Changes turned on. Use whenever the user has two versions of a DOCX (e.g., successive drafts of a paper, report, or contract — often AI-generated or AI-assisted revisions) and wants to see the differences as native Word revisions (insertions/deletions) that can be accepted/rejected in Word. Triggers: "对比两个版本的 docx", "tracked changes", "tracking mode", "修订模式对比", "compare two Word documents", "diff two drafts", "生成修订对比文件". Do NOT use for: creating new documents from scratch (use docx skill), single-file editing with revisions (use docx WIR engine), or PDF-only comparisons.

stephenturner Bundle

Fast research question validity check using Consensus. Runs 4-5 targeted searches to assess whether a proposed research question is novel, saturated, or somewhere in between — with evidence. Returns a structured Word document (.docx): novelty signal, evidence density, what the literature shows, gap quotes, and a recommended next step. Trigger when the user asks: "Is this research question novel?", "Has this been done before?", "Is there a gap in the literature on X?", "Is [X] already saturated?", "Validate my research question", "Check for prior work on X", "Is this worth pursuing?", or any phrasing where the user wants a go/no-go answer before committing to a full review or grant application. Do NOT trigger for full literature reviews (use literature-review-helper), grant opportunities (use consensus-grant-finder), or simple one-off paper searches.

sultanalsafran Bundle

Create, edit, repair, and validate Arabic-first or Arabic-English PowerPoint decks with native editable PPTX text, paragraph-level RTL, correct mixed Arabic/Latin/number behavior, native bullets, Arabic language metadata, and PowerPoint-first QA. Use together with the Presentations skill whenever a deck contains Arabic, requires RTL or bilingual slides, must remain editable as .pptx, or renders Arabic differently in PowerPoint, Keynote, Google Slides, or Codex preview.

sumonehk Bundle

AI 制作的竖屏剧 / AI 漫剧（非真人拍摄）的全流程编剧工作流，从立项选题、剧本圣经设计、分集场次执行稿到 Markdown 交付包，含状态门禁与制作增强整理。当用户提到抖音 / TikTok 短剧、AI 漫剧、立项选题、锁题、世界观 / 人物 / 场景道具、故事梗概 / 大纲 / 节拍、分集大纲、场次执行稿、剧本圣经、复盘、交付清单、production-enhanced，或要为这类项目创建 / 续写 / 改编 / 复盘 / 交付时使用。不适用于真人拍摄短剧、分镜、视频提示词、配音脚本或音效表生成。