Cookiy

Install

Config snippet generator goes here (5 client tabs)

README

# Cookiy Skill

Turn Claude Code, Codex, Cursor, VS Code / GitHub Copilot, Windsurf, Cline, OpenClaw, Manus, and other MCP clients into AI user-research operators that can create studies, run interviews, recruit participants, and deliver report links from plain-English prompts.

This repository now has two layers:

- a protected production surface for the current public `cookiy` skill and MCP install flow
- an additive open library of prompts, references, templates, and examples for user research

The install and indexing surface stays stable while the library grows around it.

The public installer package now acts as a bootstrap CLI:

1. on supported clients, it installs a local Cookiy skill copy
2. then it configures MCP
3. on unsupported clients, it falls back to MCP-only setup

## How installation relates to the two skills

- **`cookiy` (MCP-backed)**: `npx cookiy-mcp`, Homebrew `cookiy`, and marketplace/plugin installs primarily configure **Cookiy MCP** and sync a local copy of **`skills/cookiy`**. Use this path for **live** studies, AI interviews, recruitment, and report links on Cookiy.
- **`pm-research` (local open library)**: **`skills/pm-research`**, **`prompts/`**, **`references/`**, **`examples/`**, and optional **`scripts/`** are **plain Markdown and Python** in this repo. They **do not** call Cookiy APIs or require MCP. Use them by **cloning or opening this repository** in your agent workspace and following **`skills/pm-research/SKILL.md`**. Some installers only copy **`skills/cookiy`**; if **`pm-research`** is missing in your client, clone the repo or copy that folder into your workspace.

## What You Get In This Repo Today

This repo already includes concrete user-research materials, not just install docs. The **canonical file list** for the open library is in **`### Current files in the open library`** below; the table here is a high-level map.

| Material type | What is included now | What it is for |
|---|---|---|
| Installable runtime skill | `cookiy` skill + MCP install surface | Connect an agent to Cookiy and run the live study/interview/recruit/report workflow |
| Additive PM / UXR skill (no MCP) | `skills/pm-research/` + `prompts/`, `references/`, `examples/`, optional `scripts/` | End-to-end PM/UXR craft (plan, guide, synthesize, recruit, read out) using local files only |
| Public installer package | `packages/cookiy-mcp/` | Source for the `cookiy-mcp` bootstrap CLI and Homebrew build artifacts |
| Study-brief and survey prompts | `prompts/study-briefs/discovery-study.md`, `prompts/study-briefs/survey-design.md` | Stronger study briefs and survey instruments with bias checks |
| Interview-guide prompts | `problem-exploration`, `jtbd-switch-interview`, `probing-techniques`, `usability-test-script` under `prompts/interview-guides/` | Exploratory, JTBD/switch, probe menus, and moderated usability sessions |
| Synthesis prompts | `evidence-first-synthesis`, `qualitative-coding`, `affinity-mapping`, `opportunity-solution-tree` under `prompts/synthesis/` | Evidence-first synthesis, coding, affinity clustering, opportunity-solution trees |
| Stakeholder readout prompts | `executive-summary`, `data-story-narrative` under `prompts/stakeholder-readouts/` | Exec summaries and data-story narratives for mixed evidence |
| Recruitment prompts | `outreach-script`, `screening-call` under `prompts/recruitment/` | Outreach copy and screening calls |
| Research method references | `references/methods/` (selector, thematic analysis, JTBD card, survey statistics basics, continuous discovery loop) | Short method cards and heuristics |
| Reusable templates | `references/templates/` (research plan, insight card, discussion guide, recruit screener, findings deck) | Reusable planning, fieldwork, and readout structures |
| Book-ingestion guidance | `references/books/README.md` | Turn books into agent-usable notes without uploading copyrighted content |
| Worked examples | `examples/` (study briefs, readouts, interview guides, synthesis, recruitment) | Synthetic examples of “good enough” artifacts |
| Optional local scripts | `scripts/transcript_to_codes.py`, `scripts/survey_sampler.py` | CSV helper for coding rows; rough two-proportion sample-size estimate |
| Repo governance docs | `docs/PLATFORM_COMPATIBILITY.md`, `docs/CONTENT_POLICY.md`, `docs/THIRD_PARTY_ATTRIBUTIONS.md`, `docs/ROADMAP.md` | Compatibility, copyright boundaries, attribution, roadmap |
| Security and license | `SECURITY.md`, `LICENSE` | Installer behavior and license |

## Materials By Use Case

If you are here for a specific kind of material, start here:

- To plan a study:
  - `prompts/study-briefs/discovery-study.md`
  - `references/templates/research-plan-template.md`
  - `examples/study-briefs/saas-onboarding-friction.md`
- To design a survey or quantitative UX:
  - `prompts/study-briefs/survey-design.md`
  - `references/methods/survey-statistics-basics.md`
  - `scripts/survey_sampler.py` (planning aid only)
- To explore JTBD / switc