text-analyst

```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 interview-writeup@social-data-analysis

/plugin install dag-development@social-data-analysis

/plugin install abductive-analyst@social-data-analysis

/plugin install text-analyst@social-data-analysis

/plugin install lecture-designer@social-data-analysis

/plugin install lit-review@social-data-analysis

```

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 |

| Interview Write-Up | /interview-writeup | Write-up support for interview methods and findings |

| DAG Development | /dag-development | Develop causal diagrams and render publication-ready figures (Mermaid, R, Python) |

| 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) |

| Lecture Designer | /lecture-designer | Transform textbook chapters into engaging lectures with Quarto slides |

| Lit Review | /lit-review | Build literature databases via OpenAlex |

Each skill uses a phased workflow with mandatory pauses between phases for user review and decision-making.

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 → Write publication-ready sections

```

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

```

Lecture Design

```

Phase 0: Context & Outcomes → Define measurable learning outcomes

↓ [Instructor Review]

Phase 1: Content Audit → Narrative arc (ABT), chunk map, hook design

↓ [Instructor Review]

Phase 2: Active Learning → Polls, ConcepTests, peer instruction

↓ [Instructor Review]

Phase 3: Slide Development → Quarto reveal.js with speaker notes

↓ [Instructor Review]

Phase 4: Review → Timing audit, backup plans, instructor guide

```

```

.claude-plugin/

└── marketplace.json # Plugin marketplace definition (9 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

│

├── interview-writeup/

│ └── skills/interview-writeup/

│ ├── SKILL.md # Interview write-up orchestrator

│ └── phases/ # Phase agents

│

├── dag-development/

│ └── skills/dag-development/

│ ├── SKILL.md # DAG development 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

│

└── lecture-designer/

└── skills/lecture-designer/

├── SKILL.md # Lecture design orchestrator

├── phases/ # Phase agents

├── pedagogy/ # Teaching methodology (overview)

└── quarto/ # Quarto reveal.js reference

└── lit-review/

└── skills/lit-review/

├── SKILL.md # Literature review orchestrator

├── phases/ # Phase agents

└── api/ # OpenAlex API reference

```

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
• Methods transparency: Det