Sociology Analysis Agents plugin
A marketplace of 16 Claude Code plugins for quantitative and qualitative sociology research, with pauses between phases.
- 96 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The skills run R, Stata and Python code, read data files and write results into the project
Install
- Works in
Manual install
/plugin marketplace add nealcaren/social-data-analysisThen `/plugin install r-analyst@social-data-analysis` and the other plugins from the list.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skills run R, Stata and Python code, read data files and write results into the project
This is third-party code. Review the repository files before installing.
What it does
The repository publishes a plugin marketplace for data collection and analysis in sociology and related fields. Each plugin holds one phased skill: for example, `r-analyst` and `stata-analyst` run quantitative analysis from research design to final models, `interview-analyst` and `abductive-analyst` work with interviews, and `text-analyst` builds topic models and text classifiers. Support plugins cover literature search through OpenAlex, theory synthesis, PDF reading notes, search over a local paper library, quote checking against transcripts, bibliography building, simulated peer review, a project scaffold and a coordinator. Between phases the skill must stop so the researcher can check the result and decide.
Who it is for. Sociologists, graduate students and researchers who work in R or Stata and want a checkable step-by-step process.
Good fit when
- A difference-in-differences, instrumental variable or matching estimate is needed and the design must be fixed before models run.
- Interview transcripts wait for coding and anomaly search in the abductive spirit.
- A systematic database of papers has to be built through OpenAlex and in-text citations matched with `references.bib`.
- Before submitting a paper you want a trial review by personas built from your references.
Not a fit when
- You need the manuscript drafted or edited: the set covers only data collection and analysis.
- You need a quick one-off calculation with no phases and review pauses.
- Data may not be shown to an external model service while the workflow assumes a cloud agent.
Example request
Run r-analyst: I want to estimate a program effect with difference-in-differences, start with the research design and stop for review.Limitations
Each plugin is installed separately with `/plugin install`, so you pick the ones you need from the list of 16. Quantitative skills assume R or Stata and text skills R and Python, and those environments must be present. Mandatory pauses between phases slow the work but leave decisions with the researcher. Manuscript drafting and editing skills are not included. The agent reads sensitive interview data locally, but the text enters the model context, and that question belongs to the study ethics protocol.
How to disable. Run `/plugin uninstall` for each installed plugin or remove the marketplace from Claude Code. Project files and analysis outputs stay on disk.
FAQ
How many plugins does the marketplace hold?
Sixteen, one skill each, from `r-analyst` and `stata-analyst` to `research-coordinator`. Install only the ones you need.
What does `verifier` do?
It checks quotes and claims against transcripts, data and sources so no unverified spots remain in the text.
How are quantitative phases organized?
Phase 0 fixes the design, then come data familiarization, model specification, the main analysis and onward. Each phase ends with a review pause.
Does the set help write the paper?
No, the README explicitly excludes drafting and editing skills. The set covers data collection, analysis, literature and verification.
What does `project-scaffold` do?
It creates project folders and the `project.yaml` and `progress.yaml` files the coordinator uses to track progress.
Discussion
No questions or reviews yet.
Related
PluginsAuto-Empirical Research Skills
Auto-Empirical Research Skills (AERS)
A plugin marketplace for empirical social science research: causal inference, econometrics and manuscript prep for top journals
StatsClaw assembles nine Claude Code agents to build statistical packages from a paper or formulas with isolated pipelines.
43 skills for Claude Code along the research cycle: surveys, experiments, topic models, reporting and manuscript review
Life Sciences: Anthropic's marketplace for Claude Code
Life Sciences Marketplace
Anthropic's official plugin marketplace for biology and medicine: PubMed, BioRender, Synapse, ChEMBL, ClinicalTrials.gov and data analysis skills
Step-by-step causal inference: 14 skills pick a method, check assumptions, write R or Python code and stress-test the result.
17 skills for economists: research ideas, literature review, Stata and R, LaTeX models, tables and Beamer slides
README in short
A catalog of Claude Code plugins for the social sciences: a table of 16 skills, the phase diagram for quantitative analysis and the install command for each plugin.