Generate a comprehensive conjoint analysis report with utilities, charts, and segment analysis
Analyze EDSL Results by UUID or file path
Answer a question about a generated analysis report
Design, execute, and analyze a conjoint analysis study
Create an EDSL AgentList from descriptions, web searches, or files
Generate a comprehensive, self-contained analysis report for a conjoint (choice-based) study with executive summary, methodology, part-worth utilities, segment analysis, and limitations
Analyze EDSL Results objects - load by UUID or file path, export survey documentation, and generate analysis reports
Answer questions about a generated analysis report - reads report artifacts, performs additional analysis if needed, and saves the answer with metadata
Design, execute, and analyze conjoint analysis studies - guides through attribute/level definition, experimental design, EDSL survey generation, and part-worth utility estimation
Create AgentLists from web searches, descriptions, local files, or programmatic generation
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin marketplace for AI-powered survey research using EDSL (Expected Parrot's Domain Specific Language).
/plugin marketplace add expectedparrot/ep-skills
/plugin install edsl-research@ep-skills
/plugin marketplace add ~/tools/ep/ep-skills
/plugin install edsl-research@ep-skills
Complete AI-powered survey research workflow with 11 skills covering experiment design, survey creation, agent generation, result analysis, and publication.
Research question → /design-experiment → /create-study → /analyze-results → /answer-question → /publish-study
| Skill | Description |
|---|---|
/design-experiment | Design a detailed experimental plan from a research question -- includes literature review, randomization plan, survey design, power analysis, and sample size recommendation |
/create-study | Generate a multi-file study project with Survey, ScenarioList, AgentList, and a Makefile from a free text description |
/create-survey | Create EDSL Surveys from questions, QSF files, or programmatically with branching logic |
/create-agent-list | Create AgentLists from web searches, descriptions, local files, or programmatic generation |
/analyze-results | Load EDSL Results objects by UUID or file path, export survey documentation, and generate analysis reports |
/answer-question | Answer questions about a generated analysis report with additional analysis if needed |
/publish-study | Publish a completed study to GitHub with the analysis report as README.md |
/search-objects | Search, browse, and pull EDSL objects from the Expected Parrot cloud |
| Skill | Covers |
|---|---|
edsl-survey-reference | Question types, Jinja2 templating, skip/nav rules, memory modes, helpers, visualization |
edsl-agent-reference | AgentList operations, trait manipulation, templates, codebooks, instructions |
edsl-persistence-reference | Save/load locally, push/pull to Expected Parrot cloud, git versioning |
pip install edsl)EXPECTED_PARROT_API_KEY env var)Built by Expected Parrot for conducting AI-powered survey research with EDSL.
npx claudepluginhub expectedparrot/ep-skills --plugin edsl-researchClaude Code skills for experimental social science and computational text analysis: conjoint design, diagnostics, and data cleaning, survey design, list experiments, cross-national design, topic modeling, LLM text classification, VLM-based OCR pipelines, post-OCR cleanup, paper pre-submission review, hypothesis building, narrative building, pre-registration, and methods reporting. Invoke as /skill-name or let Claude auto-trigger based on context.
Orchestrate manuscript revision by routing feedback to specialized writing skills
PhD-level research capabilities: literature review, multi-source investigation, critical analysis, hypothesis-driven exploration, quantitative/qualitative methods, and lateral thinking
Autonomous research orchestration: agents for hypothesis-driven investigation, experiment running, fresh-eyes review, and batch evaluation.
Oh My Paper research harness: memory system, Codex delegation, and pipeline commands for academic research projects.
Computational-science methodology for Claude Code: research framing, pre-registration, reproducible analysis, anomaly investigation, and red-team review