text-as-data-cn
Executes quantitative text analysis pipelines for Chinese corpus data like policy and media documents.
Install
mkdir -p .claude/skills/text-as-data-cn && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11623" && unzip -o skill.zip -d .claude/skills/text-as-data-cn && rm skill.zipInstalls to .claude/skills/text-as-data-cn
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
中文文本即数据/计算社会科学操作技能（可执行）：把政策文本、媒体语料、舆情、议案等大规模中文文本落成"语料构建→预处理/分词→表示→分析→验证→回写"流水线。核心 scripts/textstat.py（仅标准库）做词频/TF-IDF/关键词/共现网络，分词用 jieba（可选前端）；主题模型(LDA/STM)、词向量等重型分析指引到 gensim/sklearn/R。强调 Grimmer & Stewart "自动化文本方法必须验证"。Use when the user does 文本分析、文本即数据、计算社会科学、政策文本分析、舆情分析、词频、TF-IDF、关键词提取、共现网络、语义网络、主题模型、LDA、情感分析、词典法、文本标度。Trigger on 文本即数据、text as data、计算社会科学、政策文本、舆情、词频、TF-IDF、关键词、共现网络、语义网络、主题模型、LDA、STM、情感分析、词向量、文本挖掘。属于 empirical-research 编排层的计算/文本分支。Key capabilities
- →Build corpus by defining population and sampling frame.
- →Preprocess text by segmenting, removing stopwords, and unifying character sets.
- →Represent text using word frequency, TF-IDF, or document-word matrices.
- →Analyze text using descriptive statistics, keyword extraction, or topic models.
- →Validate automated text methods against human-coded gold standards.
- →Write back results into figures, narratives, and reproducible numbers.
How it works
The skill processes large-scale Chinese text through a pipeline of corpus building, preprocessing, representation, analysis, validation, and result writing.
Inputs & outputs
When to use text-as-data-cn
- →Analyzing policy documents
- →Sentiment analysis of public opinion
- →Topic modeling for large document sets
- →Extracting keyword networks
About text-as-data-cn
Builds pipelines from raw text to analysis (TF-IDF, topic modeling, sentiment). Emphasizes empirical verification of methods as per Grimmer & Stewart standards.
中文文本即数据/计算社会科学操作技能（可执行）：把政策文本、媒体语料、舆情、议案等大规模中文文本落成"语料构建→预处理/分词→表示→分析→验证→回写"流水线。核心 scripts/textstat.py（仅标准库）做词频/TF-IDF/关键词/共现网络，分词用 jieba（可选前端）；主题模型(LDA/STM)、词向量等重型分析指引到 gensim/sklearn/R。强调 Grimmer & Stewart "自动化文本方法必须验证"。Use when the user does 文本分析、文本即数据、计算社会科学、政策文本分析、舆情分析、词频、TF-IDF、关键词提取、共现网络、语义网络、
When not to use it
- →When assuming automated text methods are correct without verification.
- →When using unverified Chinese word segmentation tools or sentiment dictionaries.
- →When interpreting co-occurrence networks as causal relationships.
Limitations
- →Automated text methods are 'wrong language models' and their performance on new corpora cannot be assumed.
- →Chinese word segmentation tools, sentiment dictionaries, Wordfish, and word vectors are not verified by this skill.
- →Co-occurrence networks should not be interpreted as causal relationships.
How it compares
This skill emphasizes empirical verification of automated text methods against human-coded gold standards, ensuring methodological rigor beyond simple tool application.
Compared to similar skills
text-as-data-cn side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| text-as-data-cn (this skill) | 0 | 2mo | Review | Advanced |
| exploratory-data-analysis | 15 | 2mo | Review | Intermediate |
| model-compare | 7 | 7mo | Review | Advanced |
| astropy | 6 | 7mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
exploratory-data-analysis
K-Dense-AI
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.
model-compare
rawwerks
Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall). Use when evaluating generated models against gold references, diffing CAD revisions, or computing similarity metrics for ML training. Triggers on: model diff, compare models, IoU, intersection over union, model similarity, CAD comparison, STEP diff, 3D evaluation, gold reference, generated model, precision recall 3D.
astropy
davila7
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
statistical-analysis
anthropics
Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.
datacommons-client
davila7
Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities.
analyzing-market-sentiment
jeremylongshore
Analyze cryptocurrency market sentiment using Fear & Greed Index, news analysis, and market momentum. Use when gauging overall market mood, checking if markets are fearful or greedy, or analyzing sentiment for specific coins. Trigger with phrases like "analyze crypto sentiment", "check market mood", "is the market fearful", "sentiment for Bitcoin", or "Fear and Greed index".