Update to Vera

{
  "name": "legal-tax-answer-planner",
  "description": "Use automatically before Vera answers any accepted substantive legal, tax, or compliance question or prepares source-backed professional drafting that needs an answer contract and generation instructions for direct Codex work or a ChatGPT Deep Research handoff. The user never needs to request prompt optimization. Do not use this skill as a substitute for a missing operational return, declaration, filing, or form workflow.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 291
    }
  ],
  "skill_md_contents": "---\nname: legal-tax-answer-planner\ndescription: Use automatically before Vera answers any accepted substantive legal, tax, or compliance question or prepares source-backed professional drafting that needs an answer contract and generation instructions for direct Codex work or a ChatGPT Deep Research handoff. The user never needs to request prompt optimization. Do not use this skill as a substitute for a missing operational return, declaration, filing, or form workflow.\n---\n\n<!-- VERA_OPENAI_ONBOARDING_BEGIN -->\nOnboarding is optional. Continue ordinary professional work immediately,\nincluding direct specialist invocation, without checking or completing a local\nonboarding profile. Missing, unfinished, inaccessible or corrupt onboarding state,\nor unavailable voice/window controls, must never block ordinary work. Do not\nautomatically start, resume or repeatedly offer onboarding.\nOnly for a user-requested tutorial or a native teaching handoff, read\n`../vera/references/local-onboarding.md`. A verified paired lesson worker\nexecutes only its bound lesson and token; never bypass tutorial validation.\nTutorial profiles, progress, examples and feedback remain local; never send a\nchange request, stamp a tutorial receipt or call hosted interviews for a tutorial.\nCurrent user requests take precedence over saved preferences.\n<!-- VERA_OPENAI_ONBOARDING_END -->\n\n# Plan The Answer\n\nAfter substantive use of this workflow, read and follow the `Plugin Improvement Feedback` section in `../vera/SKILL.md`.\n\nResolve `../../modules/prompt-optimizer` from this skill directory when it\nexists; otherwise resolve `../../../prompt-optimizer` in the repository. Read\nthat module's `skills/legal-tax-answer-planner/SKILL.md` completely and follow it. Treat\nthe resolved module root as the plugin working directory for all commands.\n\n## Optional ChatGPT Deep Research handoff\n\nBefore providing this handoff, identify the exact optimized_prompt.md and the\nseparate ChatGPT account or workspace chosen by the user. The full prompt,\nincluding material client names, case facts, dates and amounts, enters ChatGPT\nmodel processing when the user pastes it there. It is not covered by the\noriginating Codex or Cowork account arrangement. Obtain the route choice if it\nis not already explicit. The user checks the destination account's plan,\ntraining controls and retention before professional use or when terms change;\nVera cannot inspect or enforce them. No helper uploads the prompt or\nanonymizes it. Vera records this optional destination in the prompt-optimizer\nexternal-boundary manifest; its runtime profiles describe only the originating\nCodex and Cowork sessions. For direct drafting, continue in the selected runtime.\n\nFor the complete `quesito-legale-fiscale` journey, resolve the shared validator\nmodule at `../../modules/deep-research-validator` from this skill directory, or\n`../../../deep-research-validator` in repository source. Read its\n`skills/legal-tax-answer-review/references/research-choice.md` and follow it\nafter preparing the question and before finalizing the generation route and\nsemantic review. Reuse a choice already made for this answer. This does not\nturn a preparation-only request into a full research assignment.\n"
}