research-skills
QuestionPunk research skills: survey design, pricing research, feedback analysis and interview method skills.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/questionpunk--research-skills)HTML
<a href="/listings/questionpunk--research-skills"><img src="/api/listings/questionpunk--research-skills/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
All skills, into the agent you use:
npx skills add questionpunk/research-skills
One skill:
npx skills add questionpunk/research-skills --skill van-westendorp-analysis
Claude Code plugin marketplace:
/plugin marketplace add questionpunk/research-skills /plugin install research-skills@research-skills
The marketplace also has one plugin per method group: `survey-design`, `pricing-research`, `feedback-analysis` and `interviews`.
By hand: copy any folder under `skills/` into your agent's skills folder (`.claude/skills/`, `.github/skills/` or `.agents/skills/`). Skills with a script need Python 3.9 or later and nothing else.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 111 lines
- {
- "name": "research-skills",
- "description": "QuestionPunk research skills: survey design, pricing research, feedback analysis and interview method skills.",
- "owner": {
- "name": "QuestionPunk",
- "url": "https://www.questionpunk.com"
- },
- "metadata": {
- "version": "0.2.2"
- },
- "plugins": [
- {
- "name": "research-skills",
- "source": "./",
- "strict": false,
- "description": "Every skill in the pack.",
- "category": "research",
- "skills": [
- "./skills/survey-bias-check",
- "./skills/survey-from-decision",
- "./skills/qsf-convert",
- "./skills/open-ended-coding",
- "./skills/nps-analysis",
- "./skills/pmf-survey",
- "./skills/van-westendorp-analysis",
- "./skills/maxdiff-design",
- "./skills/maxdiff-analysis",
- "./skills/survey-sample-size",
- "./skills/ai-interview-guide",
- "./skills/survey-data-cleaning",
- "./skills/csat-ces-analysis",
- "./skills/survey-crosstabs",
- "./skills/likert-analysis",
- "./skills/kano-analysis",
- "./skills/conjoint-design",
- "./skills/conjoint-analysis",
- "./skills/ux-scale-scoring",
- "./skills/gabor-granger-analysis",
- "./skills/survey-weighting",
- "./skills/screener-writer"
- ]
- },
- {
- "name": "survey-design",
- "source": "./",
- "strict": false,
- "description": "Design, check, size and recruit for questionnaires before they go out.",
- "category": "research",
- "skills": [
- "./skills/survey-bias-check",
- "./skills/survey-from-decision",
- "./skills/qsf-convert",
- "./skills/survey-sample-size",
- "./skills/screener-writer"
- ]
- },
- {
- "name": "pricing-research",
- "source": "./",
- "strict": false,
- "description": "Van Westendorp, Gabor-Granger, MaxDiff and conjoint: design and analysis.",
- "category": "research",
- "skills": [
- "./skills/van-westendorp-analysis",
- "./skills/maxdiff-design",
- "./skills/maxdiff-analysis",
- "./skills/conjoint-design",
- "./skills/conjoint-analysis",
- "./skills/gabor-granger-analysis"
- ]
- },
- {
- "name": "feedback-analysis",
- "source": "./",
- "strict": false,
- "description": "Clean, weight, code and analyze survey answers: NPS, CSAT/CES, PMF, Likert, Kano, UX scales, crosstabs, open ends.",
- "category": "research",
- "skills": [
- "./skills/open-ended-coding",
- "./skills/nps-analysis",
- "./skills/pmf-survey",
- "./skills/survey-data-cleaning",
- "./skills/csat-ces-analysis",
- "./skills/survey-crosstabs",
- "./skills/likert-analysis",
- "./skills/kano-analysis",
- "./skills/ux-scale-scoring",
- "./skills/survey-weighting"
- ]
- },
- {
- "name": "interviews",
- "source": "./",
- "strict": false,
- "description": "Interview guides for AI-moderated customer and user interviews.",
- "category": "research",
- "skills": [
- "./skills/ai-interview-guide"
- ]
- },
- {
- "name": "questionpunk",
- "source": {
- "source": "github",
- "repo": "questionpunk/claude-plugin"
- },
- "description": "Optional: connect the QuestionPunk MCP server to field studies and read results.",
- "category": "research"
- }
- ]
- }
README.md · README · 106 lines
- # Research skills
- Agent skills for survey and research methods: design a questionnaire and check it for bias, size the
- sample, run Van Westendorp and MaxDiff, code open-ended answers, read NPS and PMF surveys, and turn a
- discussion guide into an AI-moderated interview. They work in Claude Code, Claude.ai, Codex, Cursor, GitHub
- Copilot and other agents that read `SKILL.md`.
- Every skill works on your own files with no account. Where a study needs fielding, the last step shows how
- to run it with QuestionPunk's MCP server; that step is optional.
- > **Status: 0.2.0, early release.** 22 skills. The scripts are tested (1,197 tests, Python 3.9 to 3.12) and
- > their numbers were re-derived independently, including published worked examples. [Open an
- > issue](../../issues) when something looks wrong.
- ## Install
- All skills, into the agent you use:
- ```text
- npx skills add questionpunk/research-skills
- ```
- One skill:
- ```text
- npx skills add questionpunk/research-skills --skill van-westendorp-analysis
- ```
- Claude Code plugin marketplace:
- ```text
- /plugin marketplace add questionpunk/research-skills
- /plugin install research-skills@research-skills
- ```
- The marketplace also has one plugin per method group: `survey-design`, `pricing-research`,
- `feedback-analysis` and `interviews`.
- By hand: copy any folder under `skills/` into your agent's skills folder (`.claude/skills/`,
- `.github/skills/` or `.agents/skills/`). Skills with a script need Python 3.9 or later and nothing else.
- ## Skills
- <!-- skills-table:start (generated by tools/build.mjs from catalog.json; do not edit) -->
- | Skill | Plugin | Version | What it does |
- |---|---|---|---|
- | [`nps-analysis`](skills/nps-analysis/SKILL.md) | feedback-analysis | 0.2.0 | Computes Net Promoter Score (NPS) with its confidence interval (margin of error) from raw 0-10 scores or promoter, passive and detractor counts, tests differences between segments, periods or against a target, and splits comments by promoter, passive and detractor so the reasons can be coded and counted. |
- | [`open-ended-coding`](skills/open-ended-coding/SKILL.md) | feedback-analysis | 0.2.0 | Builds a codebook from open-ended survey answers, applies it to every row of a CSV with a definition for every code, counts themes with honest denominators, pulls verbatim quotes with row ids, and checks coder agreement (Cohen's kappa, Krippendorff's alpha) on a double-coded sample, human or LLM. |
- | [`pmf-survey`](skills/pmf-survey/SKILL.md) | feedback-analysis | 0.2.0 | Designs, scores and segments a Sean Ellis product-market-fit survey (the 40% "very disappointed" test): exact questions, who to sample, the score with a confidence interval and a stated N/A rule, segment scores, and the Superhuman (Rahul Vohra) engine for finding must-have users, what they value and what holds the rest back. |
- | [`survey-data-cleaning`](skills/survey-data-cleaning/SKILL.md) | feedback-analysis | 0.2.0 | Screens a survey export for response quality: flags speeders, straight-liners, duplicates, failed attention checks, gibberish or copy-pasted open answers, inconsistent answers and platform bot or fraud flags. Writes a flags file and a cleaning log, removes rows only by a rule the user approves, and never changes the original. |
- | [`csat-ces-analysis`](skills/csat-ces-analysis/SKILL.md) | feedback-analysis | 0.1.0 | Computes CSAT and Customer Effort Score (CES) from ratings or counts: the top-2-box share with a Wilson interval and the mean, CES on the 7-point agree or ease scale or the original 1-5 effort scale (lower is better), with the convention printed so numbers reconcile with Zendesk or Qualtrics; tests differences between agents, channels, segments or periods and against a target; and splits comments by satisfied, neutral and dissatisfied. |
- | [`kano-analysis`](skills/kano-analysis/SKILL.md) | feedback-analysis | 0.1.2 | Designs and analyzes Kano surveys: writes the functional and dysfunctional question pair for each feature, classifies every answer with Kano's evaluation table (attractive, one-dimensional, must-be, indifferent, reverse, questionable), assigns each feature its category with Fong's test for a clear winner, and computes Better/Worse coefficients with intervals for a quadrant chart. |
- | [`likert-analysis`](skills/likert-analysis/SKILL.md) | feedback-analysis | 0.1.0 | Analyzes Likert and other rating-scale items from a CSV: full distributions, top-2 and bottom-2 box with Wilson intervals, medians and means with guidance on which to lead with, a diverging stacked bar table, reverse-coded item detection, Cronbach's alpha with a Feldt interval and alpha-if-item-deleted, and group comparisons (Mann-Whitney per item, box differences, Welch t on the scale score). |
- | [`survey-crosstabs`](skills/survey-crosstabs/SKILL.md) | feedback-analysis | 0.1.1 | Builds crosstabs (banner tables) from a survey CSV: column percentages with bases, significance letters from column-proportion tests with Holm or Benjamini-Hochberg correction, chi-square, intervals, weighted bases with Kish effective n, and an anonymity rule that hides groups and cells under k respondents. |
- | [`survey-weighting`](skills/survey-weighting/SKILL.md) | feedback-analysis | 0.1.0 | Weights a survey sample to known population totals by raking (iterative proportional fitting) or cell weighting: reads target margins, rakes to a stated tolerance, trims extreme weights and re-rakes, and reports the design effect, Kish effective sample size, weight distribution and weighted estimates, writing a new file and never overwriting the data. Also reports the design effect of existing weights. |
- | [`ux-scale-scoring`](skills/ux-scale-scoring/SKILL.md) | feedback-analysis | 0.1.1 | Scores standard usability questionnaires from a CSV: SUS (0-100, standard or all-positive wording, with checks for miscoded data), UMUX-Lite (raw, read on the SUS grades, plus the historical SUS-equivalent), SEQ and raw NASA-TLX, with confidence intervals, the SUS curved grade, percentile and adjective from published benchmarks, and tests of two designs (independent or paired) or against a target such as 68. |
- | [`ai-interview-guide`](skills/ai-interview-guide/SKILL.md) | interviews | 0.2.0 | Turns research goals or an existing discussion guide or interview script into a brief an AI moderator can run for customer or user research: goal, must-ask questions, probes and probe depth, skip rules, topics to avoid, a consent screen with AI disclosure and a short opener, length, and a paste-ready interviewer prompt, with leading questions rewritten. |
- | [`maxdiff-analysis`](skills/maxdiff-analysis/SKILL.md) | pricing-research | 0.2.0 | Scores MaxDiff (best-worst scaling, BWS) results from a CSV: counting scores and an aggregate multinomial logit, giving utilities and preference shares with bootstrap intervals, model fit and segment comparisons. |
- | [`maxdiff-design`](skills/maxdiff-design/SKILL.md) | pricing-research | 0.2.0 | Builds or checks a balanced MaxDiff (best-worst scaling) experimental design: items per set, sets per respondent and versions, exact BIBDs from cyclic, affine-plane and complete constructions or a balanced search otherwise, with checks on item frequency, pair frequency, position balance and connectivity, plus respondent-facing question wording. |
- | [`van-westendorp-analysis`](skills/van-westendorp-analysis/SKILL.md) | pricing-research | 0.2.1 | Computes a Van Westendorp price sensitivity meter (PSM) from a CSV of survey answers: optimal (OPP) and indifference (IPP/IDP) price points, PMC, PME and the acceptable price range, plus the optional Newton-Miller-Smith purchase-intent extension. Flags inconsistent respondents and prints the convention used, so results can be compared with R, Conjointly or Sawtooth. |
- | [`conjoint-analysis`](skills/conjoint-analysis/SKILL.md) | pricing-research | 0.1.0 | Analyzes choice-based conjoint results from a CSV of tasks and choices: an aggregate multinomial logit with respondent-clustered standard errors, part-worth utilities, attribute importances, willingness to pay when price is an attribute, AMCEs and marginal means for fully randomized designs, segment comparisons, and a share-of-preference simulator, with bootstrap intervals. |
- | [`conjoint-design`](skills/conjoint-design/SKILL.md) | pricing-research | 0.1.0 | Designs a choice-based conjoint (CBC) study: attributes and levels that don't overlap, prohibited combinations, tasks, concepts per task and a none option, a randomized design with level balance and minimal overlap (or fully randomized for AMCEs) generated by script, checks of level frequency, attribute association and relative D-efficiency, and a sample size from the Johnson-Orme rule. |
- | [`gabor-granger-analysis`](skills/gabor-granger-analysis/SKILL.md) | pricing-research | 0.1.2 | Estimates a demand curve and the revenue- or profit-maximizing price from Gabor-Granger purchase-likelihood answers: take rate at each tested price with confidence intervals, a monotonicity check per respondent, a monotone demand curve, arc price elasticity, revenue and profit curves with a bootstrap check on the optimal price, and optional user-supplied weights for stated-intent overclaim. Reads full, adaptive or monadic price ladders. |
- | [`qsf-convert`](skills/qsf-convert/SKILL.md) | survey-design | 0.2.0 | Converts a survey written in Markdown (or pasted from a doc or form) into a Qualtrics import file: a .qsf with blocks, question types, skip and display logic, or Advanced Format TXT when there is no logic. Also turns an exported .qsf into editable Markdown or a codebook with a list of what could not be carried, and checks a .qsf for broken references. |
- | [`survey-bias-check`](skills/survey-bias-check/SKILL.md) | survey-design | 0.2.1 | Reviews a survey or questionnaire for question wording and design problems: leading, loaded, double-barreled, assumptive and hypothetical questions, double negatives, unbalanced scales, overlapping or gapped answer ranges, missing "none" or "other" options, recall periods, agree/disagree grids and length, with a rewrite for each problem question. |
- | [`survey-from-decision`](skills/survey-from-decision/SKILL.md) | survey-design | 0.2.1 | Designs a survey backward from the decision it informs: decision rule, hypotheses, each question with its reason, the analysis plan with empty result tables, target sample and estimated length. |
- | [`survey-sample-size`](skills/survey-sample-size/SKILL.md) | survey-design | 0.2.1 | Calculates survey sample size: how many responses are needed for a margin of error and confidence level, a power analysis to compare two groups (minimum detectable difference), NPS margins and comparisons, minimum subgroup sizes, MaxDiff and conjoint rules of thumb, invitations from a response rate, and how many interviews reach saturation. |
- | [`screener-writer`](skills/screener-writer/SKILL.md) | survey-design | 0.1.0 | Turns a target participant profile into a recruiting screener: behavioral qualifying questions with decoy options so the right answer can't be guessed, terminate and quota logic, an articulation question for interviews, and a script check that every route that qualifies passes a question for each profile criterion, every option routes, no question or option reveals the target, and quotas can fill. |
- <!-- skills-table:end -->
- ## How they chain
- 1. Decide: `survey-from-decision`
- 2. Write and check: `survey-bias-check`; recruit with `screener-writer`
- 3. Design the method: `maxdiff-design`, `conjoint-design`, `kano-analysis` (question pairs), `ai-interview-guide`
- 4. Size: `survey-sample-size`
- 5. Field
- 6. Clean: `survey-data-cleaning`; weight: `survey-weighting`
- 7. Code open ends: `open-ended-coding`
- 8. Analyze: `survey-crosstabs`, `likert-analysis`, `nps-analysis`, `csat-ces-analysis`, `pmf-survey`,
- `ux-scale-scoring`, `kano-analysis`, `van-westendorp-analysis`, `gabor-granger-analysis`, `maxdiff-analysis`,
- `conjoint-analysis`
- ## Run it on QuestionPunk (optional)
- Skills that can field a study end with a short "Field it" section. It names the QuestionPunk MCP tools the
- step would use (endpoint `https://app.questionpunk.com/api/v1`, OAuth sign-in). The agent asks before
- creating, changing or publishing anything.
- ## How the scripts are tested
- Skills that compute something ship a small Python script (3.9+, standard library only, no network) with
- fixtures whose expected results were worked out independently. Each skill's `references/sources.md` cites
- every formula and threshold. To check every skill and run its tests:
- ```text
- node tools/validate.mjs --tests
- ```
- ## Contributing
- See [CONTRIBUTING.md](CONTRIBUTING.md). One skill per pull request; every formula needs a source.
- ## License
- MIT, see [LICENSE](LICENSE). Made by [QuestionPunk](https://www.questionpunk.com).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.