Back to search
social-data-analysis
SkillGitHubIncomplete
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/nealcaren--social-data-analysis)HTML
<a href="/listings/nealcaren--social-data-analysis"><img src="/api/listings/nealcaren--social-data-analysis/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
# Add this marketplace to Claude Code /plugin marketplace add nealcaren/social-data-analysis # Install only the plugins you need /plugin install r-analyst@social-data-analysis /plugin install stata-analyst@social-data-analysis /plugin install interview-analyst@social-data-analysis /plugin install abductive-analyst@social-data-analysis /plugin install text-analyst@social-data-analysis /plugin install prompt-optimizer@social-data-analysis /plugin install dag-development@social-data-analysis /plugin install lit-search@social-data-analysis /plugin install lit-synthesis@social-data-analysis /plugin install reading-agent@social-data-analysis /plugin install zotero-rag@social-data-analysis /plugin install verifier@social-data-analysis /plugin install bibliography-builder@social-data-analysis /plugin install peer-reviewer@social-data-analysis /plugin install project-scaffold@social-data-analysis /plugin install research-coordinator@social-data-analysis
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 300 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- {
- "name": "social-data-analysis",
- "owner": {
- "name": "Neal Caren",
- "email": "neal.caren@unc.edu"
- },
- "metadata": {
- "description": "Claude Code skills for collecting and analyzing social science data: quantitative, qualitative, and text analysis, causal design, literature search and synthesis, and research-project support."
- },
- "plugins": [
- {
- "name": "r-analyst",
- "source": "./plugins/r-analyst",
- "description": "R statistical analysis for publication-ready sociology research. Phased workflow for DiD, IV, matching, panel methods, and more with pauses for user review.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "R",
- "statistics",
- "econometrics",
- "sociology",
- "research"
- ],
- "strict": true
- },
- {
- "name": "stata-analyst",
- "source": "./plugins/stata-analyst",
- "description": "Stata statistical analysis for publication-ready sociology research. Phased workflow for DiD, IV, matching, panel methods, and more with pauses for user review.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "Stata",
- "statistics",
- "econometrics",
- "sociology",
- "research"
- ],
- "strict": true
- },
- {
- "name": "interview-analyst",
- "source": "./plugins/interview-analyst",
- "description": "Pragmatic qualitative analysis for interview data. Supports theory-informed or data-first approaches with systematic coding, quality indicators, and publication-ready synthesis.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "qualitative",
- "interviews",
- "coding",
- "sociology",
- "research"
- ],
- "strict": true
- },
- {
- "name": "dag-development",
- "source": "./plugins/dag-development",
- "description": "Develop causal diagrams (DAGs) from social-science research questions and literature, then render publication-ready figures using Mermaid, R, or Python.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "causal-diagrams",
- "DAG",
- "development",
- "methods",
- "sociology"
- ],
- "strict": true
- },
- {
- "name": "abductive-analyst",
- "source": "./plugins/abductive-analyst",
- "description": "Abductive analysis (Timmermans & Tavory) for theory-generating qualitative research. Theory-first approach with anomaly detection, theoretical casing, and rhetorical abduction for publication.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "qualitative",
- "abduction",
- "theory",
- "sociology",
- "research"
- ],
- "strict": true
- },
- {
- "name": "text-analyst",
- "source": "./plugins/text-analyst",
- "description": "Computational text analysis using R or Python. Topic models (LDA, STM, BERTopic), sentiment analysis, classification, and embeddings with systematic validation.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "text-analysis",
- "NLP",
- "topic-models",
- "sociology",
- "research"
- ],
- "strict": true
- },
- {
- "name": "lit-search",
- "source": "./plugins/lit-search",
- "description": "Build systematic literature databases using OpenAlex API. Phased workflow for search, screening, snowballing, annotation, and synthesis with structured user interaction.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "literature-search",
- "OpenAlex",
- "bibliography",
- "systematic-review",
- "research"
- ],
- "strict": true
- },
- {
- "name": "prompt-optimizer",
- "source": "./plugins/prompt-optimizer",
- "description": "Systematically optimize LLM prompts for text classification tasks using reflective evolution. Guides researchers through iterative prompt development with evaluation-driven improvement. Use when users want to classify text (sentiment, topic, stance, frame, etc.) and need the best prompt for batch API processing. Supports Python and R.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "text-classification",
- "LLM",
- "prompts",
- "evaluation",
- "research"
- ],
- "strict": true
- },
- {
- "name": "lit-synthesis",
- "source": "./plugins/lit-synthesis",
- "description": "Deep reading and synthesis of literature corpus. Theoretical mapping, thematic clustering, and debate identification using local library of markdown-converted papers.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "literature-review",
- "synthesis",
- "theory",
- "sociology",
- "research"
- ],
- "strict": true
- },
- {
- "name": "reading-agent",
- "source": "./plugins/reading-agent",
- "description": "Create structured reading notes for academic papers. Converts PDFs to markdown and extracts bibliographic info, core arguments, theoretical frameworks, findings, and key quotes. Supports single-paper deep reading or batch processing with haiku agents.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "reading-notes",
- "PDF",
- "literature",
- "annotation",
- "research"
- ],
- "strict": true
- },
- {
- "name": "zotero-rag",
- "source": "./plugins/zotero-rag",
- "description": "Semantic search across your project's local library (library/markdown/). Index papers, search by meaning, find similar passages, and get expanded context. Replaces the deprecated Zotero RAG integration.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "RAG",
- "semantic-search",
- "literature",
- "library",
- "research"
- ],
- "strict": true
- },
- {
- "name": "verifier",
- "source": "./plugins/verifier",
- "description": "Verify that claims and direct quotes in research manuscripts are present in source materials. Systematically checks interview transcripts, datasets, or cited literature using fast search with haiku agent fallback for intensive reading.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "verification",
- "quotes",
- "fact-checking",
- "qualitative",
- "research"
- ],
- "strict": true
- },
- {
- "name": "project-scaffold",
- "source": "./plugins/project-scaffold",
- "description": "Initialize research project structure with standardized directories and metadata files. Creates project.yaml (configuration) and progress.yaml (state tracking) that other skills use for canonical paths and workflow coordination. Supports qualitative, quantitative, and mixed methods projects. Use when starting a new project or adopting an existing one.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "project-setup",
- "workflow",
- "organization",
- "sociology",
- "research"
- ],
- "strict": true
- },
- {
- "name": "research-coordinator",
- "source": "./plugins/research-coordinator",
- "description": "Orchestrate the research workflow—qualitative, quantitative, or mixed methods—from literature review through data analysis to verified analysis outputs (memos, tables, figures, synthesis notes). Supports non-linear, iterative work with state tracking at the sub-phase level.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "workflow",
- "orchestration",
- "project-management",
- "sociology",
- "research"
- ],
- "strict": true
- },
- {
- "name": "bibliography-builder",
- "source": "./plugins/bibliography-builder",
- "description": "Build bibliographies from manuscript citations by extracting in-text citations, matching them against a references.bib file, identifying issues, and generating a formatted reference list.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "bibliography",
- "citations",
- "BibTeX",
- "pandoc",
- "research"
- ],
- "strict": true
- },
- {
- "name": "peer-reviewer",
- "source": "./plugins/peer-reviewer",
- "description": "Simulate peer review by constructing reviewer personas from project references. Identifies relevant perspectives, retrieves full texts, builds reviewer profiles, and generates focused reviews on theory/methods and findings.",
- "version": "1.0.0",
- "author": {
- "name": "Neal Caren"
- },
- "license": "MIT",
- "keywords": [
- "peer-review",
- "feedback",
- "manuscripts",
- "sociology",
- "research"
- ],
- "strict": true
- }
- ]
- }
README.md · README · 269 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- # Sociology Analysis Agents for Claude Code
- A Claude Code plugin marketplace with skills for collecting and analyzing data in sociology and related social sciences. These skills guide you through systematic, publication-ready research workflows, each with mandatory pauses between phases for user review.
- ## Installation
- ```bash
- # Add this marketplace to Claude Code
- /plugin marketplace add nealcaren/social-data-analysis
- # Install only the plugins you need
- /plugin install r-analyst@social-data-analysis
- /plugin install stata-analyst@social-data-analysis
- /plugin install interview-analyst@social-data-analysis
- /plugin install abductive-analyst@social-data-analysis
- /plugin install text-analyst@social-data-analysis
- /plugin install prompt-optimizer@social-data-analysis
- /plugin install dag-development@social-data-analysis
- /plugin install lit-search@social-data-analysis
- /plugin install lit-synthesis@social-data-analysis
- /plugin install reading-agent@social-data-analysis
- /plugin install zotero-rag@social-data-analysis
- /plugin install verifier@social-data-analysis
- /plugin install bibliography-builder@social-data-analysis
- /plugin install peer-reviewer@social-data-analysis
- /plugin install project-scaffold@social-data-analysis
- /plugin install research-coordinator@social-data-analysis
- ```
- ## Available Plugins
- Each plugin provides a single focused skill. Install only what you need:
- | Skill | Invocation | Description |
- |-------|------------|-------------|
- | **R Statistical Analyst** | `/r-analyst` | Phased quantitative analysis workflow using R (DiD, IV, matching, etc.) |
- | **Stata Statistical Analyst** | `/stata-analyst` | Phased quantitative analysis workflow using Stata |
- | **Interview Analyst** | `/interview-analyst` | Pragmatic qualitative analysis for interview data |
- | **Abductive Analyst** | `/abductive-analyst` | Abductive analysis (Timmermans & Tavory) for theory-generating qualitative research |
- | **Text Analyst** | `/text-analyst` | Computational text analysis with R and Python (topic models, sentiment, classification) |
- | **Prompt Optimizer** | `/prompt-optimizer` | Develop and evaluate LLM prompts for text classification |
- | **DAG Development** | `/dag-development` | Develop causal diagrams and render publication-ready figures (Mermaid, R, Python) |
- | **Lit Search** | `/lit-search` | Build systematic literature databases via OpenAlex |
- | **Lit Synthesis** | `/lit-synthesis` | Map theories, themes, and debates across a corpus of papers |
- | **Reading Agent** | `/reading-agent` | Convert PDFs and write structured reading notes |
- | **Library RAG** | `/zotero-rag` | Semantic search over a local library of papers |
- | **Verifier** | `/verifier` | Check quotes and claims against transcripts, data, and sources |
- | **Bibliography Builder** | `/bibliography-builder` | Match in-text citations to references.bib and build reference lists |
- | **Peer Reviewer** | `/peer-reviewer` | Simulated peer review from reviewer personas built from your references |
- | **Project Scaffold** | `/project-scaffold` | Set up project folders, project.yaml, and progress.yaml |
- | **Research Coordinator** | `/research-coordinator` | Orchestrate the analysis workflow across these skills |
- Each skill uses a **phased workflow** with mandatory pauses between phases for user review and decision-making.
- > **Scope**: This marketplace covers data collection and analysis. It does not include manuscript drafting or editing skills.
- ## Workflow Overview
- ### Quantitative Analysis (R/Stata)
- ```
- Phase 0: Research Design → Establish identification strategy
- ↓ [User Review]
- Phase 1: Data Familiarization → Descriptives, quality checks
- ↓ [User Review]
- Phase 2: Model Specification → Pre-specify models before estimation
- ↓ [User Review]
- Phase 3: Main Analysis → Run models, interpret results
- ↓ [User Review]
- Phase 4: Robustness → Sensitivity analysis, placebo tests
- ↓ [User Review]
- Phase 5: Output → Publication-ready tables, figures, narrative
- ```
- ### Qualitative Analysis (Interviews)
- ```
- Phase 0: Theory Preparation → Sensitizing concepts (optional)
- ↓ [User Review]
- Phase 1: Immersion → Read transcripts, create memos
- ↓ [User Review]
- Phase 2: Coding → Develop codebook, apply codes
- ↓ [User Review]
- Phase 3: Interpretation → Identify patterns, develop explanations
- ↓ [User Review]
- Phase 4: Quality Check → Assess against 5 quality indicators
- ↓ [User Review]
- Phase 5: Synthesis → Integrate into a coherent argument
- ```
- ### Abductive Analysis (Timmermans & Tavory)
- ```
- Phase 0: Theoretical Preparation → Build theoretical sensitivity
- ↓ [User Review]
- Phase 1: Familiarization → Open coding, flag surprises
- ↓ [User Review]
- Phase 2: Theoretical Casing → Apply multiple theoretical lenses
- ↓ [User Review]
- Phase 3: Anomaly Analysis → Identify contradictions and puzzles
- ↓ [User Review]
- Phase 4: Memo Writing → Develop tentative theory
- ↓ [User Review]
- Phase 5: Integration → Test theory against full dataset
- ↓ [User Review]
- Phase 6: Writing Up → Rhetorical abduction for publication
- ```
- ### Computational Text Analysis (R/Python)
- ```
- Phase 0: Research Design → Method selection, language choice (R or Python)
- ↓ [User Review]
- Phase 1: Corpus Preparation → Load, clean, explore text data
- ↓ [User Review]
- Phase 2: Specification → Document preprocessing, specify parameters
- ↓ [User Review]
- Phase 3: Analysis → Run topic models, classifiers, sentiment
- ↓ [User Review]
- Phase 4: Validation → Human validation, diagnostics, robustness
- ↓ [User Review]
- Phase 5: Output → Publication-ready tables, figures, replication
- ```
- ### Literature Search (OpenAlex)
- ```
- Phase 0: Scope Definition → Topic, search terms, criteria
- ↓ [User Review]
- Phase 1: Initial Search → Query OpenAlex, build corpus
- ↓ [User Review]
- Phase 2: Screening → Filter with LLM assistance
- ↓ [User Review]
- Phase 3: Snowballing → Expand via citation networks
- ↓ [User Review]
- Phase 4: Full Text → Identify OA sources, download checklist
- ↓ [User Review]
- Phase 5: Annotation → Extract structured information
- ↓ [User Review]
- Phase 6: Synthesis → Generate database, identify gaps
- ```
- ## Repository Structure
- ```
- .claude-plugin/
- └── marketplace.json # Plugin marketplace definition (16 plugins)
- plugins/
- ├── r-analyst/
- │ └── skills/r-analyst/
- │ ├── SKILL.md # R orchestrator
- │ ├── phases/ # Phase agents
- │ └── techniques/ # R code reference guides
- │
- ├── stata-analyst/
- │ └── skills/stata-analyst/
- │ ├── SKILL.md # Stata orchestrator
- │ ├── phases/ # Phase agents
- │ └── techniques/ # Stata code reference guides
- │
- ├── interview-analyst/
- │ └── skills/interview-analyst/
- │ ├── SKILL.md # Interview orchestrator
- │ └── phases/ # Phase agents
- │
- ├── abductive-analyst/
- │ └── skills/abductive-analyst/
- │ ├── SKILL.md # Abductive analysis orchestrator
- │ └── phases/ # Phase agents (7 phases)
- │
- ├── text-analyst/
- │ └── skills/text-analyst/
- │ ├── SKILL.md # Text analysis orchestrator
- │ ├── phases/ # Phase agents
- │ ├── concepts/ # Method concepts (language-agnostic)
- │ ├── r-techniques/ # R text analysis code guides
- │ └── python-techniques/ # Python text analysis code guides
- │
- ├── dag-development/
- │ └── skills/dag-development/
- │ ├── SKILL.md # DAG development orchestrator
- │ └── phases/ # Phase agents
- │
- ├── lit-search/
- │ └── skills/lit-search/
- │ ├── SKILL.md # Literature search orchestrator
- │ ├── phases/ # Phase agents
- │ └── api/ # OpenAlex API reference
- │
- └── prompt-optimizer/, lit-synthesis/, reading-agent/, zotero-rag/, verifier/,
- bibliography-builder/, peer-reviewer/, project-scaffold/, research-coordinator/
- ```
- ## Key Features
- ### Quantitative Skills
- - **Identification-first**: Establish research design before estimation
- - **Pre-specification**: Document model choices before seeing results
- - **Robustness built-in**: Sensitivity analysis, placebo tests, wild bootstrap
- - **Nonlinear model interpretation**: AMEs, predicted probabilities, proper diagnostics
- - **Missing data handling**: Multiple imputation with adequate m
- - **Survey methodology**: Weighting, design effects, response rates
- - **Publication checklists**: Minimum, strong, and exemplary standards
- ### Qualitative Skills
- - **Theory-informed or data-first**: Choose your approach
- - **Systematic coding**: Codebook development with examples
- - **Quality indicators**: Cognitive empathy, heterogeneity, palpability, follow-up, self-awareness
- - **Evidence selection**: Luminous exemplars, not just typical quotes
- ### Abductive Analysis Skills
- - **Theory-first approach**: Build theoretical sensitivity before data engagement
- - **Map and compass theories**: Both substantive and grammatical frameworks
- - **Anomaly detection**: Systematic identification of contradictions and puzzles
- - **Theoretical casing**: View data through multiple theoretical lenses
- - **Rhetorical abduction**: Structure writing as what we knew → surprise → new theory
- ### Text Analysis Skills
- - **Dual-language support**: R for topic models/STM; Python for transformers/BERTopic
- - **Method selection guidance**: Match methods to research questions
- - **Validation required**: Human validation, coherence metrics, robustness checks
- - **Topic modeling**: LDA, STM (R), BERTopic (Python) with K selection guidance
- - **Sentiment analysis**: VADER, lexicon-based, and ML approaches
- - **Supervised classification**: Traditional ML and transformer fine-tuning
- - **Reproducibility**: Documented preprocessing, seeds, package versions
- ### Methods Skills
- - **DAG development**: Build causal diagrams from theory and render figures in Mermaid, R, or Python
- ### Literature Skills
- - **OpenAlex-powered**: Systematic search, screening, and snowballing
- - **Structured annotation**: Extract consistent information across a corpus
- - **Database output**: Reusable literature database with gap identification
- - **Synthesis**: Theoretical maps, thematic clusters, and debates from a local library of papers
- - **Reading notes and semantic search**: Structured notes from PDFs and RAG search across the library
- ### Research Support Skills
- - **Verification**: Check quotes and claims against transcripts and sources
- - **Bibliographies**: Match citations to `references.bib` and format with pandoc
- - **Simulated peer review**: Reviewer personas built from the project's references
- - **Project coordination**: Shared `project.yaml`/`progress.yaml` and a coordinator that routes between skills
- ## Requirements
- - [Claude Code CLI](https://claude.ai/code)
- - R (for R skills) or Stata (for Stata skills)
- - Interview transcripts (for interview skill)
- - R and/or Python (for text analysis skill)
- ## Contributing
- Contributions welcome! Please:
- 1. Fork the repo
- 2. Create a feature branch
- 3. Submit a pull request
- ## License
- MIT License - see LICENSE file
- ## Acknowledgments
- These skills draw on methodological guidance from:
- - Gerson & Damaske, *The Science and Art of Interviewing*
- - Small & Calarco, *Qualitative Literacy*
- - Long & Mustillo (2017), Mize (2019) on nonlinear model interpretation
- - Various *Social Forces* editorial guidelines
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.