Claude Skills by LeoLin990405

口述史"整理稿"生成系统（Pass 1 去口语化）。将录音转写稿通过"方针师→整理者→质量门" 多角色协作，按口述史方法论转换为忠实、可读、可供受访人审阅签字的整理稿，并配套 人工复核包。专为长文（10 万字级）设计：分块 + 全局术语锚定 + 跨块一致性。 搭配 companion skill `oral-history-quality-guard` 做交付前忠实度审计。 触发词：口述史整理、转写稿去口语化、整理访谈记录、口述文本处理、oral history、 整理稿、"按口述史要求处理录音转文字"。书面化（Pass 2）见 workflows/pass2-bookify.md。

oral-history-master 的配套质量门：交付前对整理稿做**对抗式忠实度审计**。 对照原始转写逐句核查：是否捏造、是否伪造确定性、是否圆场矛盾、是否抹掉方言/个性、 ⚠ 是否该标尽标、专名是否全篇统一。产出 QA 报告与逐块 PASS / NEEDS FIX 判定。 在交付任何口述史整理稿前必须运行。触发词：口述史质检、忠实度审计、整理稿质量门、 oral history QA、检查整理稿、quality guard。

R language data analysis and visualization skill. Use when user asks to (1) run R scripts or code, (2) install/update R packages, (3) perform data analysis with R, (4) create visualizations with ggplot2/plotly, (5) statistical analysis, (6) data manipulation with tidyverse/dplyr/data.table. Triggers on keywords like "R语言", "R脚本", "ggplot", "tidyverse", "数据分析", "可视化".

R bioinformatics packages. Use for genomic data analysis, RNA-seq, phylogenetics, and Bioconductor workflows.

R Bioconductor ecosystem for bioinformatics. Use for genomics, proteomics, and bioinformatics analysis.

R Biostrings package for biological sequences. Use for DNA, RNA, and protein sequence manipulation.

R GenomicRanges package for genomic intervals. Use for representing and manipulating genomic coordinates.

R genomics with GenomicRanges, Biostrings. Use for genomic intervals, sequences, and annotations.

R pheatmap package for heatmaps. Use for creating publication-quality heatmaps with clustering.

R seqinr package for biological sequence analysis. Use for reading, writing, and analyzing biological sequences.

R phylogenetics with ape, ggtree. Use for phylogenetic trees and evolutionary analysis.

R ape package for phylogenetic analysis. Use for reading, writing, and analyzing phylogenetic trees.

R phangorn package for phylogenetic analysis. Use for phylogenetic reconstruction and analysis.

R DESeq2 package for RNA-seq analysis. Use for differential expression analysis with negative binomial models.

R RNA-seq analysis with DESeq2, edgeR. Use for differential expression and gene set enrichment.

R edgeR package for RNA-seq analysis. Use for differential expression with negative binomial models.

R limma package for microarray and RNA-seq. Use for linear models in differential expression.

R data manipulation, formats, and database packages. Use for data wrangling with dplyr/data.table, reading files (CSV, Excel, JSON, Arrow), and database connections (SQL, MongoDB, Redis).

R DBI package for database interface. Use for connecting to and querying databases with a common interface.

R RPostgres package for PostgreSQL databases. Use for PostgreSQL connections with modern DBI interface.

R RSQLite package for SQLite databases. Use for embedded SQLite database connections.

R database packages for SQL and NoSQL. Use for DBI connections, SQL queries, dbplyr, SQLite, PostgreSQL, MySQL, MongoDB, Redis.

R dbplyr package for database backends. Use for dplyr verbs on database tables with lazy evaluation.

R elastic package for Elasticsearch. Use for connecting to Elasticsearch and performing search operations.

R mongolite package for MongoDB. Use for connecting to MongoDB databases and performing CRUD operations.

R odbc package for ODBC database connections. Use for connecting to any ODBC-compatible database.

R data format packages for reading/writing files. Use for CSV (readr, vroom), Excel (readxl, writexl), JSON (jsonlite), Parquet (arrow), and fast serialization (fst, qs).

R arrow package for Apache Arrow. Use for reading/writing Parquet, Feather, and working with large datasets.

R feather package for fast binary data format. Use for fast reading/writing of data frames between R and Python.

R fst package for fast serialization of data frames. Use for ultra-fast reading/writing of data frames with compression.

R haven package for SPSS, Stata, SAS files. Use for reading/writing .sav, .dta, .sas7bdat files with labels.

R jsonlite package for JSON parsing. Use for reading, writing, and converting JSON data.

R qs package for quick serialization of R objects. Use for fast saving/loading of any R object with high compression.

R readr package for reading rectangular data. Use for fast CSV, TSV, and fixed-width file reading.

R readxl package for reading Excel files. Use for importing .xls and .xlsx files.

R rio package for data import/export. Use for reading/writing any file format with a single function.

R vroom package for fast reading of delimited files. Use for reading large CSV/TSV files with lazy loading.

R writexl package for writing Excel files. Use for creating .xlsx files without Java dependency.

R yaml package for YAML parsing. Use for reading/writing YAML configuration files.

R DataExplorer package for EDA. Use for automated exploratory data analysis and reporting.

R data manipulation with dplyr, data.table, tidyr. Use for filtering, selecting, mutating, grouping, summarizing, reshaping data frames.

R broom package for tidying model outputs. Use for converting statistical model results to tidy data frames.

R data.table package for fast data manipulation. Use for high-performance data operations with concise syntax.

R dplyr package for data manipulation. Use for filter, select, mutate, summarize, group_by, joins, and data transformation.

R fuzzyjoin package for fuzzy matching joins. Use for joining tables by inexact matching on strings, numbers, or distances.

R janitor package for data cleaning. Use for cleaning dirty data and creating tabulations.

R lubridate package for date-time manipulation. Use for parsing, extracting, and arithmetic with dates and times.

R purrr package for functional programming. Use for map, reduce, iteration, and list manipulation.

R reshape2 package for data reshaping. Use for melting and casting data between wide and long formats.

R stringi package for string processing. Use for fast, consistent string manipulation with ICU library.