12,236 skills found · Page 182 of 408
FreedomIntelligence / bio-local-blastRun BLAST searches locally using NCBI BLAST+ command-line tools.
FreedomIntelligence / bio-long-read-sequencing-clair3-variantsDeep learning-based variant calling from long reads using Clair3 for SNPs and small indels
FreedomIntelligence / bio-long-read-sequencing-isoseq-analysisAnalyze PacBio Iso-Seq data for full-length isoform discovery and quantification
FreedomIntelligence / armored-cart-design-agentThe Armored CAR-T Design Agent provides AI-assisted design of next-generation armored CAR-T cells engineered to express cytokines, chemokines, or other enhancing factors.
FreedomIntelligence / aav-vector-design-agentThe AAV Vector Design Agent provides AI-driven design of adeno-associated virus vectors for gene therapy applications. It covers capsid selection and engineering, promoter/enhancer design, transgene optimization, and manufacturing considerations.
FreedomIntelligence / bgpt-paper-searchSearch scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions.
FreedomIntelligence / bio-experimental-design-power-analysisPower = probability of detecting a true effect. Underpowered studies waste resources; overpowered studies are inefficient.
FreedomIntelligence / bio-experimental-design-sample-sizeWhen resources are limited, prioritize: 1. Biological replicates over technical replicates 2. More samples over deeper sequencing (after ~20M reads for RNA-seq) 3. Balanced designs (equal n per group)
FreedomIntelligence / bio-clinical-databases-dbsnp-queriesQuery dbSNP for rsID lookups, variant annotations, and cross-references to other databases
FreedomIntelligence / bio-crispr-screens-base-editing-analysisAnalyzes base editing and prime editing outcomes including editing efficiency, bystander edits, and indel frequencies
FreedomIntelligence / bio-experimental-design-multiple-testingTesting 20,000 genes at p < 0.05 yields ~1,000 false positives by chance. Correction is essential.
FreedomIntelligence / bio-format-conversionConvert between sequence file formats (FASTA, FASTQ, GenBank, EMBL) using Biopython Bio.SeqIO
FreedomIntelligence / bio-alignment-files-bam-statisticsGenerate alignment statistics using samtools and pysam.
FreedomIntelligence / bio-batch-processingProcess multiple sequence files in batch using Biopython
FreedomIntelligence / bio-duplicate-handlingMark and remove PCR/optical duplicates using samtools.
FreedomIntelligence / bio-fastq-qualityWork with FASTQ quality scores using Biopython
FreedomIntelligence / bio-experimental-design-batch-designBatch effects are unavoidable. Good design makes them correctable.
Agentchengfeng / chengfeng-check-updates剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。
Agentchengfeng / chengfeng-cut剪辑中文口播原素材：逐词转录、词典修字出修字表、五轮扫描找口误与重复、汇总表与重复句子表、打开 Studio 让用户复核、复盘沉淀用户偏好与词典。只产出一份已复核的删词账本，不切媒体、不做字幕、不做分镜动画。用户说剪口播、处理口误、生成口播基础素材、继续剪口播，或确认卡回传 action=return_cut_review 时使用。不要用于执行物理剪切、导出剪后视频、单独安装、单独打开工作台或口播分镜成片。
Agentchengfeng / chengfeng-subtitle给剪好的口播做字幕：直接用已有的逐词稿加账本算出剪后时间（不必导出、不必重新转录）、用词典和作者文稿改写听错的专名、按句子分屏、在 Studio 里逐屏复核。用户说做字幕、加字幕、改字幕、重新分屏、字幕不对时使用。不要用于删词剪辑、物理剪切、分镜动画或成片渲染。
Agentchengfeng / chengfeng-visual给剪好的口播配画面：在录屏上盖 HTML 层（圈重点标注 / 小黑整屏动画 / 推近），层绑字幕屏、由播放器逐帧驱动、直接在预览里看。用户说做分镜、配画面、加动画、圈重点、B-roll、做 storyboard 时使用。不要用于删词剪辑、字幕、物理剪切或成片渲染。
Agentchengfeng / ian-xiaohei-svg-motionCreate Ian Xiaohei-style HTML/SVG motion illustrations for Chinese articles, scripts, storyboard scenes, workflow explanations, concept metaphors, and short video visual aids
Agentchengfeng / chengfeng-report-bug整理、脱敏并上报 chengfeng-videocut 的 GitHub Bug。用户说上报 Bug、反馈剪口播问题、提交 GitHub Issue、这个问题告诉开发者，或要求继续提交已预览的 Bug 草稿时使用。不要用于功能建议、普通排错、代码提交或未获用户确认的自动上报。
Agentchengfeng / chengfeng-export把剪好的口播烧成一个成片文件：账本切片段、推近、字幕、HTML 画面层，一次全部烧进 mp4。用户说导出、出成片、烧字幕、渲染、导出视频、生成最终文件时使用。不要用于生成删词候选、写字幕、做画面动画。
Tiger3807861189 / j-spaceOperate a selective workspace for complex reasoning, long tasks, repository engineering, coordinated agents, and authorized security analysis
xstongxue / create-skillGuides users through creating effective Agent Skills for Cursor
xstongxue / office-file-process处理 Office 文档的一站式 skill：Word(.doc/.docx/.dotx)、Excel(.xls/.xlsx/.xlsm/.csv)、PowerPoint(.ppt/.pptx/.potx) 的创建、读取、编辑、提取、转换、校验。触发：『读取 word 文档』『提取 excel 内容』『看 ppt 讲了什么』、.doc 老格式打不开、生成/编辑 Word 报告/合同/模板、制作幻灯片/deck/演示文稿、写带公式的电子表格。读取优先 pandoc/markitdown 等官方工具，环境没有则走 Windows Office COM 自动化（含中文文件名、PowerShell 编…
xstongxue / pptgen-drawio根据论文或汇报内容生成多页 Draw.io 格式 PPT，支持论文答辩与通用汇报两种模式，自动导出为 .pptx。当用户提到论文答辩 PPT、答辩幻灯片、通用 PPT、汇报 PPT、根据模板生成 PPT、drawio2pptx 时使用。
xstongxue / wechat-article-writer公众号/自媒体全流程。根据用户表述自动匹配：撰写文章、封面图、正文插图、风格提取。支持多种写作风格。当用户提到写公众号、技术博客、公众号封面、正文插图、步骤图、演示图、流程示意、分析写作风格、克隆文风、模仿爆款、提取风格时使用。详见 reference 目录。
xstongxue / project-docs对任意代码项目生成一套面向新人的循序渐进文档集，输出到 docs/ 目录。含架构、设计思想、语言特性、代码导读、运行时模型、构建、对接、调试、设计规范共 9 篇，支持全部生成 / 只写几篇 / 更新已有文档。当用户提到"生成项目文档"、"新人文档"、"上手文档"、"架构文档"、"代码导读"、"项目理解"、"深入理解项目"、"onboarding 文档"、"给新同事看的文档"时使用。要按用户给的格式写论文章节、项目梳理、重点问题、简历项目描述的，用 codegen-doc。
