Update to qlaris

{
  "description": "MANDATORY router — whenever the user message contains \"with qlaris\" (any casing, with or without a colon or arguments, e.g. \"with qlaris: <goal>\", \"with qlaris: how do I …\", or \"with qlaris:\" alone), you MUST load and follow this skill BEFORE responding; never answer a \"with qlaris\" request from memory. Also use when the user asks how to do anything with qlaris — creating personas or running research (surveys, UX tests, interviews). The command menu and router for everything qlaris.",
  "included_files": [],
  "name": "help-with-qlaris",
  "skill_md_contents": "---\nname: help-with-qlaris\ndescription: MANDATORY router — whenever the user message contains \"with qlaris\" (any casing, with or without a colon or arguments, e.g. \"with qlaris: <goal>\", \"with qlaris: how do I …\", or \"with qlaris:\" alone), you MUST load and follow this skill BEFORE responding; never answer a \"with qlaris\" request from memory. Also use when the user asks how to do anything with qlaris — creating personas or running research (surveys, UX tests, interviews). The command menu and router for everything qlaris.\n---\n\n# With qlaris\n\n## Behavior — how to handle a request\n\n- **`with qlaris: <a goal>`** → do it. For research, pick the audience, run the study, and deliver\n  the findings — asking first when the goal is large or unclear. Use any detail the user added\n  (audience, sub-questions, approach, exact output); leave the rest open and decide sensibly.\n- **`with qlaris: how do I …`** → explain and point to the right tool or skill — run nothing.\n- **`with qlaris:`** (nothing after) → print the **Cheat sheet** below **verbatim**.\n\nMatch the user's language, check cost with a `dryRun` before anything large, and only report results\nonce they are final. For \"how do I\" questions, don't execute write/action tools; read-only `list_*` /\n`get_*` are always fine.\n\n---\n\n## Cheat sheet (print verbatim for a blank `with qlaris:`)\n\n**CHEAT SHEET · COMMANDS**\n\n# with qlaris\n\nEverything starts with **`with qlaris:`** — say what you want and qlaris does it, or points you to\nthe right skill. Add as much or as little detail as you like: audience, sub-questions, approach,\nexact output. Leave things out and qlaris fills the gaps sensibly or asks first.\n\n### the basics — Three ways to ask\n| say | what happens |\n|---|---|\n| `with qlaris: <research goal and specifications>` | qlaris does it. For research it picks the audience, runs the study and delivers the findings — asking first when the goal is large or unclear. You can also add any detail about the audience, research or similar, or leave it open and let qlaris decide. |\n| `with qlaris: how do I …` | qlaris explains and points to the right tool or skill — nothing is run. |\n| `with qlaris:` | Shows this cheat sheet. |\n\nqlaris matches your language, checks cost with a dry run before anything large, and only reports\nresults once they are final.\n\n### personas — Build and reuse audiences\n| say | what happens |\n|---|---|\n| `with qlaris: create a persona <description>` | Build a research persona from a short description. |\n| `with qlaris: list my personas` | Show existing personas to reuse. |\n\n### research — Say your question, qlaris handles the rest\n| say | what happens |\n|---|---|\n| `with qlaris: <your research question>` | qlaris chooses the audience, runs the study and compiles the findings. |\n| `with qlaris: run a survey <survey specifications>` | Quantitative survey on a digital-twin panel. |\n| `with qlaris: run a UX test <UX test specifications>` | Twins navigate a URL and report their experience. |\n| `with qlaris: run an interview <interview specifications>` | One-to-one interview study: a decision, 2–5 research questions, a discussion guide, one audience (or up to five to compare), 3–50 interviews and a report. Free draft first; you approve before anything is paid. |\n\nWant control? State any preference as text — audience, specific personas, exact questions, method,\nsample size — and it is used instead of chosen for you.\n\nTwo ways to phrase the same command:\n- **Quick:** \"with qlaris: Find out if Americans prefer chocolate or vanilla ice cream when going to the cinema.\"\n- **Steered:** \"with qlaris: Should a new US cinema chain mainly sell ice cream, and which flavor? Focus on the western USA, under 45. Detailed report, qualitative through quantitative. Ask clarifying questions first.\"\n\n### tips — Getting good results\n- Say the decision, not just a topic. \"Should we charge for X?\" beats \"ask about pricing\".\n- Be as specific or as hands-off as you like. Name the audience and questions, or leave them to qlaris.\n- Personas read best as short narratives. Don't over-define — open traits keep the panel real.\n\n---\n\n## Under the hood (for routing)\n\n- **Personas:** `create_persona({ country, description, directPrompt })` (pass the narrative to both\n  `description` and `directPrompt`); reuse via `list_personas` / `get_persona`.\n- **Survey:** `run_survey` — target via `personaId` / `filters` / `segmentSlug` / `groups`; question\n  types via `list_question_types`; `dryRun` for cost; poll `get_survey_status` → `get_survey_results`.\n- **UX test:** `run_user_test` (needs `url` + `task`; host a design first with `serve_prototype`);\n  poll `get_user_test_status` → `get_user_test_results`.\n- **Interview (1:1 study):** `draft_interview_study` (FREE — ask the decision; omit `researchQuestions`\n  and `guide` and qlaris proposes and drafts them; confirm the audience; show `proposals`, `coverage`,\n  `validity`, `costBar`; put `questionsForUser[]` to the user; follow `nextSteps[]`; apply edits to\n  `draft.study`; follow `draft.procedure`) → `run_interview_study` with `{ study: draft.study, requestId }`\n  (`study.pilot: true` when the sample is ≥ 6 and the user wants to read three first) → poll\n  `get_interview_study` at `suggestedPollIntervalSeconds` → `report.markdown` rendered AS RETURNED,\n  every finding with its validity label. Transcripts: `get_interview_study` with a `participantId`.\n  Cancel / regenerate / launch the remainder: `cancel_interview_study` / `regenerate_interview_report` / `launch_interview_study_remainder`.\n- **Rule:** for \"how do I …\" questions, explain and point — don't run write/action tools. For a\n  stated research goal, run it. Read-only `list_*` / `get_*` are always fine.\n"
}