survey-analyst — Claude Code skill: survey analysis and reports
survey-analyst turns a raw survey export into a cleaned Excel workbook and a Word findings report, cross-tabs and charts included.
Apache-2.0 ★ 12,746 updated 2026-10-29
npx skills add genspark-ai/genoffice --skill survey-analyst -a claude-codeWhat survey-analyst does
Give the skill your responses (an exported table, a CSV, pasted text) together with the questionnaire. It maps question types, sample size and demographic columns before touching an answer, then returns a five-sheet workbook named “<Survey> Analysis” and a Word report of 4 to 8 pages.
Cleaning follows rules it writes down: rushed completions, straight-lined answers and logical contradictions get dropped, each rule with a count in the cleaning log. Multiple-choice items become 0/1 columns, scales are flipped to one direction, open answers land in 5–8 themes with quotes. Per-question figures come from COUNTIF and AVERAGE formulas rather than typed values.
Cross-tabs run on whichever demographic variables you choose; gaps of 10 percentage points or more stand out, and any group under 30 respondents is marked as too small to lean on. Question wording is the catch: without it the option codes produce frequencies and nothing more. Phone, name and company columns are stripped before the workbook is built.
What it helps with
- clean a messy survey export and log every exclusion
- count frequencies and means for each question
- compare satisfaction across respondent groups
- sort open-ended answers into themes with quotes
- deliver one Excel workbook and one Word report
Example prompts for the agent
- Go through this survey export and put together a findings report
- Break the satisfaction survey down by respondent group
- Clean the responses from the CSV and show per-question frequencies
How to install survey-analyst
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill survey-analyst -a claude-code2Manually: put the files in place
~/.claude/skills/survey-analyst/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/survey-analyst/
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill survey-analyst -a codex2Manually: put the files in place
.agents/skills/survey-analyst/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill survey-analyst -a cursor2Manually: put the files in place
.cursor/skills/survey-analyst/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install genspark-ai/genoffice skills/recommended/survey-analyst2Manually: put the files in place
.github/skills/survey-analyst/SKILL.md1Skills CLI (Vercel)
npx skills add genspark-ai/genoffice --skill survey-analyst -a gemini-cli2Platform CLI
gemini skills install https://github.com/genspark-ai/genoffice --path skills/recommended/survey-analystManually: put the files in place
.devin/skills/survey-analyst/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about survey-analyst
How do I install survey-analyst in Claude Code?
Run npx skills add genspark-ai/genoffice --skill survey-analyst -a claude-code. The skill file lands at ~/.claude/skills/survey-analyst/SKILL.md.
What does survey-analyst do?
It reads the questionnaire and raw responses, cleans the sample, computes descriptive stats and cross-tabs, and groups open-ended answers. You get an Excel workbook plus a Word report with the key findings.
Which sheets does the Excel workbook have?
Five: cleaned data with an exclusion flag, cleaning log, per-question stats, cross-tabs, open-ended themes. Charts for key questions sit alongside them.
Source text
SKILL.md · Apache-2.0
--- name: survey-analyst description: Clean raw survey responses, run cross-tabulations and charts, and produce an analysis workbook plus a findings report, delivered as an Excel workbook and a Word document category: data scenarios: Survey analysis | Satisfaction research | User research quickPrompts: Analyse this survey export and write a findings report | Cross-tabulate this satisfaction survey by respondent group metadata: version: 1.0.0 --- You are a survey analyst. The user gives you raw survey responses (exported table, CSV or pasted text) and the questionnaire; you deliver a cleaned analysis workbook and a findings report. ## Workflow 1. Read the survey structure first: question types (single choice / multiple choice / scale / matrix / open-ended), sample size, demographic variables (gender / age / region / user type). Ask for the question wording when it is missing, otherwise option codes cannot be interpreted; also ask about the research purpose and the 2-3 questions the user most wants answered. 2. Clean: drop responses with too-short completion time, straight-lining (the same option throughout) or logical contradictions (such as rating a purchase experience without having purchased), recording the exclusion rules and counts; split multiple-choice questions into 0/1 columns; align scale direction (reverse-scored items flipped); remove empty open-ended answers. 3. Descriptive statistics: frequency and share per question; mean and Top-2 / Bottom-2 share for scale questions. 4. Cross-tabulation: cross-tabs by the user's chosen demographic variables, highlighting share differences of 10 percentage points or more or clearly different means; groups under 30 respondents are marked "small sample, indicative only". 5. Open-ended questions: group into 5-8 themes with counts, quoting 1-2 verbatim responses per theme as evidence. 6. Build the workbook as an Excel workbook with the spreadsheet tools available here, titled "<Survey> Analysis"; then build the report as a Word document with the document tools available here, titled "<Survey> Findings Report". ## Workbook structure - Sheet "Cleaned data": the cleaned detail plus an exclusion flag column. - Sheet "Cleaning log": Rule / Excluded / Remaining sample. - Sheet "Per-question stats": frequency, share and mean per question, computed with formulas (COUNTIF / AVERAGE), never typed. - Sheet "Cross-tabs": pivot-style cross-tables, groups as rows, options as columns. - Sheet "Open-ended": Theme / Count / Example quote. - Charts for key questions: bar for single choice, stacked bar for scales, clustered column for group comparisons. ## Report structure - Research overview (purpose / sample / timing / valid responses) -> Key findings (3-5, each = observation + figure + explanation). - Question-by-question analysis (ordered by research purpose, not question number) -> Group differences -> Open-ended insights -> Recommendations -> Appendix (questionnaire, cleaning rules). ## Rules - State the denominator of every share (all valid respondents or those who answered the question); note that multiple-choice shares can sum past 100%. - Draw no conclusions from differences on insufficient samples; make no untested causal claims, and phrase as "may be related to". - Columns with personal data (phone, name, company) stay out of the analysis workbook; drop them during cleaning and note it in the log. - Without question wording, option codes get frequencies only, no interpretation. - The Top-2 basis for satisfaction scales (such as 4-5 on a 5-point scale) is stated in the header and kept consistent across questions. - After delivering, note in the reply the limits of sample representativeness and which conclusions are correlational rather than causal. ## Output One Excel analysis workbook (five sheets) plus one Word report (4-8 pages). The reply holds only the representativeness limits and the correlation-versus-causation reminder.
© genspark-ai · Apache-2.0 · genspark-ai/genoffice