# cookiy-ai/user-research-skill

Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, synthetic users, quant surveys, participant recruitment.

Repository: https://github.com/cookiy-ai/user-research-skill
Canonical: https://ross.abutalabs.com/products/user-research-skill
Homepage: https://cookiy.ai
Language: Shell
License: MIT
License Family: permissive
Topics: ai-agent, ai-skill, claude-code, cli, codex, cursor, openclaw, skill, skills, user-research, ux-research, quantitative-research
Last push: 2026-08-19T11:20:36+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 48, longevity 10
- inputs: {"age_days": 145, "days_push": 14, "days_rel": 139, "gap_med": null, "n_releases_24m": 1}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1508, forks 58 (observed 2026-08-28T04:04:55.216774+00:00)

## What it is
An open-source AI agent skill (installed as a CLI) that lets AI coding agents like Claude Code, Codex, Cursor, and OpenClaw plan, run, and synthesize user research — including AI-moderated interviews, synthetic users, and quantitative surveys. It connects to the Cookiy AI platform for end-to-end studies with real or synthetic participants and participant recruitment.

## Use cases
- run user interviews from my AI coding agent
- recruit research participants for a UX study
- generate an interview guide and research plan
- synthesize interview transcripts into a research report
- run a quantitative survey with conditional logic
- simulate synthetic users for product feedback
- do ux research without leaving the terminal

## When to choose
- you already work inside Claude Code, Codex, Cursor, or another agent and want research capabilities in that workflow
- you want end-to-end studies (recruit, interview, survey, synthesize) with real or synthetic participants
- you want an MIT-licensed, scriptable research skill rather than a closed SaaS-only tool

## When to avoid
- you need a polished standalone GUI for research rather than an agent/CLI workflow
- you require full data control or air-gapped operation, since studies run through the Cookiy AI hosted platform
- you need statistically rigorous academic survey tooling with fine-grained sampling controls

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, cli, nlp, chatbot, data-science, analytics
- domain: artificial-intelligence, large-language-models, developer-tools, hr
- platform: cli, cross-platform, python
- tags: ai-skill, user-research, ux-research, claude-code, cursor, codex, synthetic-users, interviews, surveys, participant-recruitment, qualitative-research, quantitative-research, ai-agents, nodejs

## Member repositories
- cookiy-ai/user-research-skill (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:55.216774+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:32:31.948318+00:00, confidence not recorded.
  - readme: https://github.com/cookiy-ai/user-research-skill (fetched 2026-08-28T04:04:55.216774+00:00, sha 0379cc6146e8)
  - homepage: https://cookiy.ai (fetched 2026-08-29T11:36:45.339527+00:00, sha 46b7900ff21f)
  - site_page: https://cookiy.ai/about (fetched 2026-08-29T11:36:45.342504+00:00, sha bf680672113c)
- Data as of 2026-08-30T08:39:29.467469+00:00.