{
  "markdown": "# Insight Badger\n\nSurvey-specialised data insights for non-technical professionals. Drop a survey response CSV from any platform — Qualtrics, SurveyMonkey, Google Forms, Typeform, Microsoft Forms, custom — and get meaningful, actionable analysis. No spreadsheet formulas, no SPSS, no coding.\n\n## What it does\n\nInsight Badger reads your survey export, automatically classifies each column by question type (Likert, NPS, single-choice, multi-select, open-text, demographic), reconstructs matrix and multi-select questions, and applies the right method per type. Results are presented in plain language with a polished HTML report.\n\n## Skills\n\n### `/dig-deep` — Autonomous Survey Analysis\n\n**No questions asked.** Hand over a survey CSV and Insight Badger explores it autonomously:\n\n- Detects question types per column (Likert 5/7, NPS 0–10, CSAT, single-choice, multi-select, open-text, numeric, demographic, datetime)\n- Reconstructs matrix questions (`Q3_1…Q3_n`) and multi-select batteries (`Q5_optA…optN`)\n- Computes the right metric per type — top-2-box / bottom-2-box / net-agree for Likert, NPS score with promoter/passive/detractor split, response distribution for single-choice\n- Identifies a likely KPI question (NPS, recommend, overall satisfaction) and runs driver analysis\n- Builds attitudinal segments from Likert items and names them as personas\n- Themes open-text responses with exemplar quotes per theme\n- Cross-tabs the KPI by detected demographics and flags significant gaps\n- Delivers 3–5 key takeaways and recommended follow-up questions\n\n**Trigger phrases**: \"dig deep\", \"analyse this survey\", \"what's interesting in this survey\", \"explore this survey\", \"find insights\"\n\n### `/dig-for` — Guided Survey Investigation\n\n**You have a question — Insight Badger sharpens it and answers it.** When you want to investigate a specific aspect of the survey, this skill asks a few survey-aware clarifying questions and runs a focused analysis.\n\nCommon patterns it handles:\n\n- \"What's driving our NPS?\" → driver analysis on Likert items predicting NPS\n- \"Compare power users vs. light users\" → cross-tabs + significance tests\n- \"Why did satisfaction drop in Q3?\" → trend + driver decomposition (longitudinal surveys)\n- \"How do our enterprise customers feel about pricing?\" → scoped subgroup analysis\n- \"What do people complain about in open-text?\" → themed open-text analysis with quotes\n\n**Trigger phrases**: \"dig for\", \"what's driving NPS\", \"compare segments\", \"why did X change\", \"break down Y by Z\"\n\n## Output\n\nBoth skills produce:\n\n1. **Conversation summary** — a concise plain-language answer right in the chat, leading with the headline finding (NPS score, top driver, biggest segment gap).\n2. **HTML report** — a polished, self-contained file with interactive charts and detailed findings, saved to your output folder.\n\nThe HTML report is organised into five tabs:\n\n- **Insights** — KPI summary, headline findings, driver chart, top segment differences, key takeaways\n- **Questions** — one card per question with the right visualisation per type (Likert bar with top-2-box callout, donut for single-choice, NPS gauge, themed quote cards for open-text)\n- **Segments** — attitudinal segments with persona profiles and demographic composition\n- **Data** — health check per column (traffic-light rating), skip-logic interpretation, response quality flags (straight-lining, speeders, completion rate)\n- **Info** — report metadata, column reference (codebook), techniques applied, raw data sample\n\n## Survey-Aware Methods\n\nInsight Badger draws from a survey-research toolkit:\n\n- **Question-type detection** — header patterns, value ranges, response text matching\n- **Matrix and multi-select reconstruction** — group `Q3_1…Q3_n` as one item battery, `Q5_optA…optN` as one multi-response question\n- **Codebook ingestion** — optional second file (CSV/JSON) mapping column → question text + response options; inferred from headers if absent\n- **Likert metrics** — top-2-box, bottom-2-box, net-agree, mean score (with caveats), distribution shape\n- **NPS / CSAT / CES** — promoter/passive/detractor split, NPS score, CSAT %, with confidence intervals\n- **Construct reliability** — Cronbach's alpha for matrix question batteries\n- **Driver analysis** — relative weights / dominance analysis predicting KPI from Likert composites\n- **Attitudinal segmentation** — K-Means / GMM on Likert items with auto-named personas\n- **Open-text NLP** — TF-IDF + clustering for themes, VADER sentiment, exemplar quotes per theme\n- **Cross-tabs** — KPI by demographic with chi-squared / z-test for proportions\n- **Skip-logic awareness** — distinguishes \"not asked\" from \"didn't answer\"\n- **Response quality flags** — straight-lining detection, speeder/laggard flagging, completion rate\n- **Significance testing** — chi-squared, z-test for proportions, t-test, ANOVA — with effect sizes\n\n## Typical Workflow\n\n**Option A — Explore freely:**\nDrop a survey CSV and say \"dig deep\" or \"analyse this survey\". Insight Badger profiles the questionnaire, identifies the KPI, runs drivers and segments, themes the open-text, and delivers a full HTML report.\n\n**Option B — Investigate a question:**\nSay \"dig for what's driving our NPS\" or \"compare enterprise vs. SMB on satisfaction\" along with your CSV. Insight Badger asks one or two clarifying questions, then runs a focused analysis.\n\n**Optional codebook:**\nFor sharper results, provide a codebook alongside your CSV — a JSON or CSV file mapping each column to its question text and response options. Insight Badger works without one (inferring from headers and values), but a codebook eliminates ambiguity.\n\n## Requirements\n\n- Python 3.x with: pandas, numpy, scikit-learn, scipy, matplotlib, seaborn, vaderSentiment (for open-text sentiment)\n- Survey response CSV from any platform (Qualtrics, SurveyMonkey, Google Forms, Typeform, Microsoft Forms, custom exports)\n\n## Setup\n\nNo configuration needed. Install the plugin and start using `/dig-deep` or `/dig-for`.\n",
  "bytes": 5993,
  "sha": "ff9bf6e98b91fa0fb9596501e6d9dd2291ac43114f2ed29c2f86a3936187d248",
  "repo_slug": "ozturkumut/insightbadger-plugin",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_ozturkumut_insightbadger_plugin_insight__97c947f7/readme"
}