{"id":"a43fbf1a-4ea9-4b64-90ee-b737b2127629","slug":"user-intuition-skills","kind":"skill","name":"skills","summary":"Run real qualitative research from your AI agent: AI-moderated interviews with real people, from brief to cited findings. Plan studies with no account, design screeners, recruit from a vetted 4M+ cons","owner":"user-intuition","repoUrl":"https://github.com/user-intuition/skills","license":"MIT","licenseTier":"permissive","trust":"community","stars":0,"match":null,"fewStars":true,"format":"skill","createdAt":"2026-08-17T18:38:41.000Z","addedAt":"2026-10-29T15:04:04.311Z","logoUrl":"https://avatars.githubusercontent.com/u/317991492?v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["design-media","developer-tools","communication"],"tags":["claude-code","codex","concept-testing","consumer-insights","consumer-research","cursor","market-research","qualitative-research"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-29T23:43:21.746Z","sample":false,"url":"https://conduits.dev/tools/user-intuition-skills","language":"JavaScript","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# Run real qualitative research from your AI agent\n\nAsk your agent to run a concept test with 20 frozen-dinner buyers. It drafts the study, shows you the plan and the cost, and once you confirm, it fields AI-moderated interviews (typically 20–30 minutes) and returns findings with verbatim quotes.\nInterviews ladder 5–7 levels deep, from what people did to why it matters to them. Participants come from a vetted 4M+ consumer panel or from your own customers, by voice, chat or video in 80+ languages.\nNo account yet? Ask for help with any research question: the `user-research` skill plans the study or synthesizes research you already have, then fields it with real people when you're ready.\n\nThese are Agent Skills for running qualitative research with [User Intuition](https://www.userintuition.ai): create interview studies, design screeners, field panel recruits, and turn transcripts into stakeholder-ready findings. The plugin bundles the hosted [User Intuition MCP server](https://docs.userintuition.ai/mcp-server/overview) for the *tools* and the skills for the *play*: the workflow, guardrails, and order of operations that make research runs reproducible.\n\n**Works with:** Claude Code (plugin), Claude Desktop and claude.ai (connector and skill ZIPs), ChatGPT (connector), Codex, Cursor, and any agent that reads Agent Skills.\n\n**Guides:** [Set up User Intuition in Claude](https://www.userintuition.ai/reference-guides/claude-mcp-customer-research-setup/) · [Skills docs](https://docs.userintuition.ai/skills/overview) · [How quality is controlled](https://www.userintuition.ai/quality/) · [Pricing](https://www.userintuition.ai/pricing/)\n\n## Example run\n\nThis is the shape of a run. The prompt is illustrative; the findings come from the public [Walmart shopper study](https://www.userintuition.ai/preview/).\n\n1. **Prompt.** \"Find out where Walmart shoppers get stuck on a trip, and whether it changes whether they come back.\"\n2. **Saved plan.** The agent drafts the study from the brief (audience, screener, discussion guide) and shows you the saved plan before anything is fielded.\n3. **Estimate.** For a panel study it gets a quote and stops. Nothing launches, and nothing is spent, until you approve the plan and the quote. The cost depends on audience and size; see [pricing](https://www.userintuition.ai/pricing/).\n4. **Findings excerpt.** From 43 interviewed shoppers, each finding linked back to what participants said:\n   - 34 of 43 hit at least one obstacle on their trip.\n   - 36 of 43 will shop there again.\n   - The shelf carried 20 of 51 friction moments.\n   - 19 of 43 named the shelf as the moment that shaped the trip.\n\n## Install\n\nEvery surface uses the same hosted MCP server (`https://mcp.userintuition.ai/mcp`, browser sign-in) and the same skill files. After installing, ask your agent: **\"Help me get started with User Intuition.\"** The `setup` skill checks the connection and routes you to the right workflow.\n\n| Agent | Skills | MCP connection |\n|-------|--------|----------------|\n| **Claude Code** | `/plugin marketplace add user-intuition/skills`, then `/plugin install user-intuition-research@user-intuition` | Bundled with the plugin. Run `/mcp`, select `user-intuition`, and sign in. |\n| **Claude Desktop / claude.ai** | Download a skill ZIP from [Releases](https://github.com/user-intuition/skills/releases) and upload it in Settings → Capabilities → Skills. One ZIP per skill; the bundle ZIP holds all of them. | Settings → Connectors → add a custom connector with `https://mcp.userintuition.ai/mcp`. |\n| **Codex** | `npx skills add user-intuition/skills -a codex` | `codex mcp add user-intuition --url https://mcp.userintuition.ai/mcp`, then `codex mcp login user-intuition`. |\n| **Cursor** | Install the plugin defined in [`.cursor-plugin/plugin.json`](.cursor-plugin/plugin.json), or `npx skills add user-intuition/skills -a cursor` | Bundled with the plugin, or add `https://mcp.userintuition.ai/mcp` under Settings → MCP. Sign in when prompted. |\n| **ChatGPT** | Skills ship inside the User Intuition app. | Settings → Apps & Connectors → User Intuition, then sign in. |\n| **Any other agent** | `npx skills add user-intuition/skills` (pick your agent when asked, or pass `-a <agent>`) | Add `https://mcp.userintuition.ai/mcp` as a remote MCP server in your client. |\n\nInstall a single skill with `npx skills add user-intuition/skills -s create-study-from-brief`. To build the Desktop ZIPs yourself, run `node scripts/build-desktop-zip.mjs` (output in `dist/`).\n\n### Raw files\n\nEach skill is a standalone Markdown file under `plugins/user-intuition-research/skills/<name>/SKILL.md`. You can also tell your agent:\n\n> Fetch https://raw.githubusercontent.com/user-intuition/skills/main/catalog.json, select the workflow needed for the task, and fetch its raw `SKILL.md`. Install it in the skill directory supported by your agent client.\n\n## Connect your account\n\nThe Claude plugin includes the hosted MCP connection:\n\n```text\nhttps://mcp.userintuition.ai/mcp\n```\n\nAfter installing the plugin, open `/mcp`, select `user-intuition`, and complete the browser-based OAuth flow. Claude stores and refreshes the resulting token securely.\n\nIf you prefer a local stdio connection instead of the bundled hosted connection, disable the plugin-provided MCP and use:\n\n```bash\nclaude mcp add userintuition -- npx -y @userintuition-ai/mcp@latest\n```\n\nwith `USERINTUITION_API_KEY` set (get a key from your [dashboard](https://app.userintuition.ai)).\n\n## The skills\n\n| Skill | Outcome |\n|-------|---------|\n| `setup` | Check the connection, ask what you want to learn, and route to the right workflow |\n| `user-research` | Plan a study or synthesize research you already have, no account needed; then field it with real people |\n| `interview-category-shoppers` | Interview category or brand shoppers recruited from the consumer panel by what they buy |\n| `interview-brand-switchers` | Hear why shoppers switched brands or traded down, recruited from the consumer panel |\n| `map-shopper-journey` | Map the path to purchase, from trip trigger to shelf or page to first use |\n| `run-usage-and-attitudes` | Usage and attitudes: occasions, habits, needs, and brand repertoire |\n| `interview-recent-buyers` | Interview people who just bought, from Shopify or any store's orders |\n| `interview-lapsed-customers` | Find customers who stopped buying and hear why |\n| `interview-cancellations` | Interview subscribers soon after they cancel, from Stripe or any billing data |\n| `run-win-loss` | Interview buyers on closed won and lost deals from HubSpot or any CRM |\n| `investigate-drop-off` | Interview the people behind a funnel drop-off from your analytics tool |\n| `create-study-from-brief` | Turn a research brief into a launch-ready interview study |\n| `design-screeners` | Recruit exactly the right respondents — panel and custom screeners, done safely |\n| `field-a-panel` | Recruit N respondents from the panel, with cost approved before any spend |\n| `invite-your-own-participants` | Interview your own customers — invites, share links, and rewards |\n| `run-a-concept-test` | Put a concept, prototype, or landing page in front of participants |\n| `monitor-fielding` | Daily digest of every fielding study — progress, quality, stalls |\n| `analyze-completed-study` | From transcripts to stakeholder-ready findings, with real quotes only |\n| `curate-interview-quality` | Review low-quality interviews and delete only the exact interviews the user confirms |\n| `retrieve-study-results` | Read an existing report and follow source references without regeneration |\n| `search-research` | Find authorized prior evidence and inspect coverage and sources |\n\nThe original eight fielding and analysis workflows retain their validated MCP behavior. Retrieval and search use current tool/schema discovery; illustrative B2/C1 adapters still require release verification. Check any named tool yourself:\n\n```bash\nnpx -y @userintuition-ai/mcp describe create_study\n```\n\n## Machine discovery\n\n[Catalog](https://raw.githubusercontent.com/user-intuition/skills/main/catalog.json): names, descriptions, raw file URLs, documentation URLs, and SHA-256 digests. Each skill is independently fetchable; loading the catalog does not require loading every workflow.\n\n## Contributing\n\nMaintainer workflow (catalog, tests, docs and website export) is in [CONTRIBUTING.md](CONTRIBUTING.md). Release notes are in [CHANGELOG.md](CHANGELOG.md).\n\n## Docs\n\n- [Skills overview](https://docs.userintuition.ai/skills/overview)\n- [Skills library](https://docs.userintuition.ai/skills/library) (browsable version of these files)\n- [MCP server reference](https://docs.userintuition.ai/mcp-server/overview)\n\n## License\n\nMIT\n"}