Skip to content
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
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/nealcaren--social-data-analysis/badge.svg)](/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)

  1. {
  2. "name": "social-data-analysis",
  3. "owner": {
  4. "name": "Neal Caren",
  5. "email": "neal.caren@unc.edu"
  6. },
  7. "metadata": {
  8. "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."
  9. },
  10. "plugins": [
  11. {
  12. "name": "r-analyst",
  13. "source": "./plugins/r-analyst",
  14. "description": "R statistical analysis for publication-ready sociology research. Phased workflow for DiD, IV, matching, panel methods, and more with pauses for user review.",
  15. "version": "1.0.0",
  16. "author": {
  17. "name": "Neal Caren"
  18. },
  19. "license": "MIT",
  20. "keywords": [
  21. "R",
  22. "statistics",
  23. "econometrics",
  24. "sociology",
  25. "research"
  26. ],
  27. "strict": true
  28. },
  29. {
  30. "name": "stata-analyst",
  31. "source": "./plugins/stata-analyst",
  32. "description": "Stata statistical analysis for publication-ready sociology research. Phased workflow for DiD, IV, matching, panel methods, and more with pauses for user review.",
  33. "version": "1.0.0",
  34. "author": {
  35. "name": "Neal Caren"
  36. },
  37. "license": "MIT",
  38. "keywords": [
  39. "Stata",
  40. "statistics",
  41. "econometrics",
  42. "sociology",
  43. "research"
  44. ],
  45. "strict": true
  46. },
  47. {
  48. "name": "interview-analyst",
  49. "source": "./plugins/interview-analyst",
  50. "description": "Pragmatic qualitative analysis for interview data. Supports theory-informed or data-first approaches with systematic coding, quality indicators, and publication-ready synthesis.",
  51. "version": "1.0.0",
  52. "author": {
  53. "name": "Neal Caren"
  54. },
  55. "license": "MIT",
  56. "keywords": [
  57. "qualitative",
  58. "interviews",
  59. "coding",
  60. "sociology",
  61. "research"
  62. ],
  63. "strict": true
  64. },
  65. {
  66. "name": "dag-development",
  67. "source": "./plugins/dag-development",
  68. "description": "Develop causal diagrams (DAGs) from social-science research questions and literature, then render publication-ready figures using Mermaid, R, or Python.",
  69. "version": "1.0.0",
  70. "author": {
  71. "name": "Neal Caren"
  72. },
  73. "license": "MIT",
  74. "keywords": [
  75. "causal-diagrams",
  76. "DAG",
  77. "development",
  78. "methods",
  79. "sociology"
  80. ],
  81. "strict": true
  82. },
  83. {
  84. "name": "abductive-analyst",
  85. "source": "./plugins/abductive-analyst",
  86. "description": "Abductive analysis (Timmermans & Tavory) for theory-generating qualitative research. Theory-first approach with anomaly detection, theoretical casing, and rhetorical abduction for publication.",
  87. "version": "1.0.0",
  88. "author": {
  89. "name": "Neal Caren"
  90. },
  91. "license": "MIT",
  92. "keywords": [
  93. "qualitative",
  94. "abduction",
  95. "theory",
  96. "sociology",
  97. "research"
  98. ],
  99. "strict": true
  100. },
  101. {
  102. "name": "text-analyst",
  103. "source": "./plugins/text-analyst",
  104. "description": "Computational text analysis using R or Python. Topic models (LDA, STM, BERTopic), sentiment analysis, classification, and embeddings with systematic validation.",
  105. "version": "1.0.0",
  106. "author": {
  107. "name": "Neal Caren"
  108. },
  109. "license": "MIT",
  110. "keywords": [
  111. "text-analysis",
  112. "NLP",
  113. "topic-models",
  114. "sociology",
  115. "research"
  116. ],
  117. "strict": true
  118. },
  119. {
  120. "name": "lit-search",
  121. "source": "./plugins/lit-search",
  122. "description": "Build systematic literature databases using OpenAlex API. Phased workflow for search, screening, snowballing, annotation, and synthesis with structured user interaction.",
  123. "version": "1.0.0",
  124. "author": {
  125. "name": "Neal Caren"
  126. },
  127. "license": "MIT",
  128. "keywords": [
  129. "literature-search",
  130. "OpenAlex",
  131. "bibliography",
  132. "systematic-review",
  133. "research"
  134. ],
  135. "strict": true
  136. },
  137. {
  138. "name": "prompt-optimizer",
  139. "source": "./plugins/prompt-optimizer",
  140. "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.",
  141. "version": "1.0.0",
  142. "author": {
  143. "name": "Neal Caren"
  144. },
  145. "license": "MIT",
  146. "keywords": [
  147. "text-classification",
  148. "LLM",
  149. "prompts",
  150. "evaluation",
  151. "research"
  152. ],
  153. "strict": true
  154. },
  155. {
  156. "name": "lit-synthesis",
  157. "source": "./plugins/lit-synthesis",
  158. "description": "Deep reading and synthesis of literature corpus. Theoretical mapping, thematic clustering, and debate identification using local library of markdown-converted papers.",
  159. "version": "1.0.0",
  160. "author": {
  161. "name": "Neal Caren"
  162. },
  163. "license": "MIT",
  164. "keywords": [
  165. "literature-review",
  166. "synthesis",
  167. "theory",
  168. "sociology",
  169. "research"
  170. ],
  171. "strict": true
  172. },
  173. {
  174. "name": "reading-agent",
  175. "source": "./plugins/reading-agent",
  176. "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.",
  177. "version": "1.0.0",
  178. "author": {
  179. "name": "Neal Caren"
  180. },
  181. "license": "MIT",
  182. "keywords": [
  183. "reading-notes",
  184. "PDF",
  185. "literature",
  186. "annotation",
  187. "research"
  188. ],
  189. "strict": true
  190. },
  191. {
  192. "name": "zotero-rag",
  193. "source": "./plugins/zotero-rag",
  194. "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.",
  195. "version": "1.0.0",
  196. "author": {
  197. "name": "Neal Caren"
  198. },
  199. "license": "MIT",
  200. "keywords": [
  201. "RAG",
  202. "semantic-search",
  203. "literature",
  204. "library",
  205. "research"
  206. ],
  207. "strict": true
  208. },
  209. {
  210. "name": "verifier",
  211. "source": "./plugins/verifier",
  212. "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.",
  213. "version": "1.0.0",
  214. "author": {
  215. "name": "Neal Caren"
  216. },
  217. "license": "MIT",
  218. "keywords": [
  219. "verification",
  220. "quotes",
  221. "fact-checking",
  222. "qualitative",
  223. "research"
  224. ],
  225. "strict": true
  226. },
  227. {
  228. "name": "project-scaffold",
  229. "source": "./plugins/project-scaffold",
  230. "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.",
  231. "version": "1.0.0",
  232. "author": {
  233. "name": "Neal Caren"
  234. },
  235. "license": "MIT",
  236. "keywords": [
  237. "project-setup",
  238. "workflow",
  239. "organization",
  240. "sociology",
  241. "research"
  242. ],
  243. "strict": true
  244. },
  245. {
  246. "name": "research-coordinator",
  247. "source": "./plugins/research-coordinator",
  248. "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.",
  249. "version": "1.0.0",
  250. "author": {
  251. "name": "Neal Caren"
  252. },
  253. "license": "MIT",
  254. "keywords": [
  255. "workflow",
  256. "orchestration",
  257. "project-management",
  258. "sociology",
  259. "research"
  260. ],
  261. "strict": true
  262. },
  263. {
  264. "name": "bibliography-builder",
  265. "source": "./plugins/bibliography-builder",
  266. "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.",
  267. "version": "1.0.0",
  268. "author": {
  269. "name": "Neal Caren"
  270. },
  271. "license": "MIT",
  272. "keywords": [
  273. "bibliography",
  274. "citations",
  275. "BibTeX",
  276. "pandoc",
  277. "research"
  278. ],
  279. "strict": true
  280. },
  281. {
  282. "name": "peer-reviewer",
  283. "source": "./plugins/peer-reviewer",
  284. "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.",
  285. "version": "1.0.0",
  286. "author": {
  287. "name": "Neal Caren"
  288. },
  289. "license": "MIT",
  290. "keywords": [
  291. "peer-review",
  292. "feedback",
  293. "manuscripts",
  294. "sociology",
  295. "research"
  296. ],
  297. "strict": true
  298. }
  299. ]
  300. }
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)

  1. # Sociology Analysis Agents for Claude Code
  2. 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.
  3. ## Installation
  4. ```bash
  5. # Add this marketplace to Claude Code
  6. /plugin marketplace add nealcaren/social-data-analysis
  7. # Install only the plugins you need
  8. /plugin install r-analyst@social-data-analysis
  9. /plugin install stata-analyst@social-data-analysis
  10. /plugin install interview-analyst@social-data-analysis
  11. /plugin install abductive-analyst@social-data-analysis
  12. /plugin install text-analyst@social-data-analysis
  13. /plugin install prompt-optimizer@social-data-analysis
  14. /plugin install dag-development@social-data-analysis
  15. /plugin install lit-search@social-data-analysis
  16. /plugin install lit-synthesis@social-data-analysis
  17. /plugin install reading-agent@social-data-analysis
  18. /plugin install zotero-rag@social-data-analysis
  19. /plugin install verifier@social-data-analysis
  20. /plugin install bibliography-builder@social-data-analysis
  21. /plugin install peer-reviewer@social-data-analysis
  22. /plugin install project-scaffold@social-data-analysis
  23. /plugin install research-coordinator@social-data-analysis
  24. ```
  25. ## Available Plugins
  26. Each plugin provides a single focused skill. Install only what you need:
  27. | Skill | Invocation | Description |
  28. |-------|------------|-------------|
  29. | **R Statistical Analyst** | `/r-analyst` | Phased quantitative analysis workflow using R (DiD, IV, matching, etc.) |
  30. | **Stata Statistical Analyst** | `/stata-analyst` | Phased quantitative analysis workflow using Stata |
  31. | **Interview Analyst** | `/interview-analyst` | Pragmatic qualitative analysis for interview data |
  32. | **Abductive Analyst** | `/abductive-analyst` | Abductive analysis (Timmermans & Tavory) for theory-generating qualitative research |
  33. | **Text Analyst** | `/text-analyst` | Computational text analysis with R and Python (topic models, sentiment, classification) |
  34. | **Prompt Optimizer** | `/prompt-optimizer` | Develop and evaluate LLM prompts for text classification |
  35. | **DAG Development** | `/dag-development` | Develop causal diagrams and render publication-ready figures (Mermaid, R, Python) |
  36. | **Lit Search** | `/lit-search` | Build systematic literature databases via OpenAlex |
  37. | **Lit Synthesis** | `/lit-synthesis` | Map theories, themes, and debates across a corpus of papers |
  38. | **Reading Agent** | `/reading-agent` | Convert PDFs and write structured reading notes |
  39. | **Library RAG** | `/zotero-rag` | Semantic search over a local library of papers |
  40. | **Verifier** | `/verifier` | Check quotes and claims against transcripts, data, and sources |
  41. | **Bibliography Builder** | `/bibliography-builder` | Match in-text citations to references.bib and build reference lists |
  42. | **Peer Reviewer** | `/peer-reviewer` | Simulated peer review from reviewer personas built from your references |
  43. | **Project Scaffold** | `/project-scaffold` | Set up project folders, project.yaml, and progress.yaml |
  44. | **Research Coordinator** | `/research-coordinator` | Orchestrate the analysis workflow across these skills |
  45. Each skill uses a **phased workflow** with mandatory pauses between phases for user review and decision-making.
  46. > **Scope**: This marketplace covers data collection and analysis. It does not include manuscript drafting or editing skills.
  47. ## Workflow Overview
  48. ### Quantitative Analysis (R/Stata)
  49. ```
  50. Phase 0: Research Design → Establish identification strategy
  51. ↓ [User Review]
  52. Phase 1: Data Familiarization → Descriptives, quality checks
  53. ↓ [User Review]
  54. Phase 2: Model Specification → Pre-specify models before estimation
  55. ↓ [User Review]
  56. Phase 3: Main Analysis → Run models, interpret results
  57. ↓ [User Review]
  58. Phase 4: Robustness → Sensitivity analysis, placebo tests
  59. ↓ [User Review]
  60. Phase 5: Output → Publication-ready tables, figures, narrative
  61. ```
  62. ### Qualitative Analysis (Interviews)
  63. ```
  64. Phase 0: Theory Preparation → Sensitizing concepts (optional)
  65. ↓ [User Review]
  66. Phase 1: Immersion → Read transcripts, create memos
  67. ↓ [User Review]
  68. Phase 2: Coding → Develop codebook, apply codes
  69. ↓ [User Review]
  70. Phase 3: Interpretation → Identify patterns, develop explanations
  71. ↓ [User Review]
  72. Phase 4: Quality Check → Assess against 5 quality indicators
  73. ↓ [User Review]
  74. Phase 5: Synthesis → Integrate into a coherent argument
  75. ```
  76. ### Abductive Analysis (Timmermans & Tavory)
  77. ```
  78. Phase 0: Theoretical Preparation → Build theoretical sensitivity
  79. ↓ [User Review]
  80. Phase 1: Familiarization → Open coding, flag surprises
  81. ↓ [User Review]
  82. Phase 2: Theoretical Casing → Apply multiple theoretical lenses
  83. ↓ [User Review]
  84. Phase 3: Anomaly Analysis → Identify contradictions and puzzles
  85. ↓ [User Review]
  86. Phase 4: Memo Writing → Develop tentative theory
  87. ↓ [User Review]
  88. Phase 5: Integration → Test theory against full dataset
  89. ↓ [User Review]
  90. Phase 6: Writing Up → Rhetorical abduction for publication
  91. ```
  92. ### Computational Text Analysis (R/Python)
  93. ```
  94. Phase 0: Research Design → Method selection, language choice (R or Python)
  95. ↓ [User Review]
  96. Phase 1: Corpus Preparation → Load, clean, explore text data
  97. ↓ [User Review]
  98. Phase 2: Specification → Document preprocessing, specify parameters
  99. ↓ [User Review]
  100. Phase 3: Analysis → Run topic models, classifiers, sentiment
  101. ↓ [User Review]
  102. Phase 4: Validation → Human validation, diagnostics, robustness
  103. ↓ [User Review]
  104. Phase 5: Output → Publication-ready tables, figures, replication
  105. ```
  106. ### Literature Search (OpenAlex)
  107. ```
  108. Phase 0: Scope Definition → Topic, search terms, criteria
  109. ↓ [User Review]
  110. Phase 1: Initial Search → Query OpenAlex, build corpus
  111. ↓ [User Review]
  112. Phase 2: Screening → Filter with LLM assistance
  113. ↓ [User Review]
  114. Phase 3: Snowballing → Expand via citation networks
  115. ↓ [User Review]
  116. Phase 4: Full Text → Identify OA sources, download checklist
  117. ↓ [User Review]
  118. Phase 5: Annotation → Extract structured information
  119. ↓ [User Review]
  120. Phase 6: Synthesis → Generate database, identify gaps
  121. ```
  122. ## Repository Structure
  123. ```
  124. .claude-plugin/
  125. └── marketplace.json # Plugin marketplace definition (16 plugins)
  126. plugins/
  127. ├── r-analyst/
  128. │ └── skills/r-analyst/
  129. │ ├── SKILL.md # R orchestrator
  130. │ ├── phases/ # Phase agents
  131. │ └── techniques/ # R code reference guides
  132. │
  133. ├── stata-analyst/
  134. │ └── skills/stata-analyst/
  135. │ ├── SKILL.md # Stata orchestrator
  136. │ ├── phases/ # Phase agents
  137. │ └── techniques/ # Stata code reference guides
  138. │
  139. ├── interview-analyst/
  140. │ └── skills/interview-analyst/
  141. │ ├── SKILL.md # Interview orchestrator
  142. │ └── phases/ # Phase agents
  143. │
  144. ├── abductive-analyst/
  145. │ └── skills/abductive-analyst/
  146. │ ├── SKILL.md # Abductive analysis orchestrator
  147. │ └── phases/ # Phase agents (7 phases)
  148. │
  149. ├── text-analyst/
  150. │ └── skills/text-analyst/
  151. │ ├── SKILL.md # Text analysis orchestrator
  152. │ ├── phases/ # Phase agents
  153. │ ├── concepts/ # Method concepts (language-agnostic)
  154. │ ├── r-techniques/ # R text analysis code guides
  155. │ └── python-techniques/ # Python text analysis code guides
  156. │
  157. ├── dag-development/
  158. │ └── skills/dag-development/
  159. │ ├── SKILL.md # DAG development orchestrator
  160. │ └── phases/ # Phase agents
  161. │
  162. ├── lit-search/
  163. │ └── skills/lit-search/
  164. │ ├── SKILL.md # Literature search orchestrator
  165. │ ├── phases/ # Phase agents
  166. │ └── api/ # OpenAlex API reference
  167. │
  168. └── prompt-optimizer/, lit-synthesis/, reading-agent/, zotero-rag/, verifier/,
  169. bibliography-builder/, peer-reviewer/, project-scaffold/, research-coordinator/
  170. ```
  171. ## Key Features
  172. ### Quantitative Skills
  173. - **Identification-first**: Establish research design before estimation
  174. - **Pre-specification**: Document model choices before seeing results
  175. - **Robustness built-in**: Sensitivity analysis, placebo tests, wild bootstrap
  176. - **Nonlinear model interpretation**: AMEs, predicted probabilities, proper diagnostics
  177. - **Missing data handling**: Multiple imputation with adequate m
  178. - **Survey methodology**: Weighting, design effects, response rates
  179. - **Publication checklists**: Minimum, strong, and exemplary standards
  180. ### Qualitative Skills
  181. - **Theory-informed or data-first**: Choose your approach
  182. - **Systematic coding**: Codebook development with examples
  183. - **Quality indicators**: Cognitive empathy, heterogeneity, palpability, follow-up, self-awareness
  184. - **Evidence selection**: Luminous exemplars, not just typical quotes
  185. ### Abductive Analysis Skills
  186. - **Theory-first approach**: Build theoretical sensitivity before data engagement
  187. - **Map and compass theories**: Both substantive and grammatical frameworks
  188. - **Anomaly detection**: Systematic identification of contradictions and puzzles
  189. - **Theoretical casing**: View data through multiple theoretical lenses
  190. - **Rhetorical abduction**: Structure writing as what we knew → surprise → new theory
  191. ### Text Analysis Skills
  192. - **Dual-language support**: R for topic models/STM; Python for transformers/BERTopic
  193. - **Method selection guidance**: Match methods to research questions
  194. - **Validation required**: Human validation, coherence metrics, robustness checks
  195. - **Topic modeling**: LDA, STM (R), BERTopic (Python) with K selection guidance
  196. - **Sentiment analysis**: VADER, lexicon-based, and ML approaches
  197. - **Supervised classification**: Traditional ML and transformer fine-tuning
  198. - **Reproducibility**: Documented preprocessing, seeds, package versions
  199. ### Methods Skills
  200. - **DAG development**: Build causal diagrams from theory and render figures in Mermaid, R, or Python
  201. ### Literature Skills
  202. - **OpenAlex-powered**: Systematic search, screening, and snowballing
  203. - **Structured annotation**: Extract consistent information across a corpus
  204. - **Database output**: Reusable literature database with gap identification
  205. - **Synthesis**: Theoretical maps, thematic clusters, and debates from a local library of papers
  206. - **Reading notes and semantic search**: Structured notes from PDFs and RAG search across the library
  207. ### Research Support Skills
  208. - **Verification**: Check quotes and claims against transcripts and sources
  209. - **Bibliographies**: Match citations to `references.bib` and format with pandoc
  210. - **Simulated peer review**: Reviewer personas built from the project's references
  211. - **Project coordination**: Shared `project.yaml`/`progress.yaml` and a coordinator that routes between skills
  212. ## Requirements
  213. - [Claude Code CLI](https://claude.ai/code)
  214. - R (for R skills) or Stata (for Stata skills)
  215. - Interview transcripts (for interview skill)
  216. - R and/or Python (for text analysis skill)
  217. ## Contributing
  218. Contributions welcome! Please:
  219. 1. Fork the repo
  220. 2. Create a feature branch
  221. 3. Submit a pull request
  222. ## License
  223. MIT License - see LICENSE file
  224. ## Acknowledgments
  225. These skills draw on methodological guidance from:
  226. - Gerson & Damaske, *The Science and Art of Interviewing*
  227. - Small & Calarco, *Qualitative Literacy*
  228. - Long & Mustillo (2017), Mize (2019) on nonlinear model interpretation
  229. - Various *Social Forces* editorial guidelines

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.