Update to FLORA

{
  "name": "flora-batch-consistent",
  "description": "Apply one FLORA technique across many items so every result shares a single consistent style — a product list or spreadsheet into PDP shots, a folder of sketches into renders, a set of photos relit the same way. Use when the user supplies a list, file, or set of images and wants the same treatment on each. Always total the cost and get confirmation before running. Do not use for a single item.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 414
    }
  ],
  "skill_md_contents": "---\nname: flora-batch-consistent\ndescription: Apply one FLORA technique across many items so every result shares a single consistent style — a product list or spreadsheet into PDP shots, a folder of sketches into renders, a set of photos relit the same way. Use when the user supplies a list, file, or set of images and wants the same treatment on each. Always total the cost and get confirmation before running. Do not use for a single item.\n---\n\n# Batch a FLORA technique across many items\n\nConsistency here comes from running **one technique** over every item, not from\nrepeating a prompt and hoping. Pick the technique once; vary only the inputs.\n\n**Input:** a list of items (rows, URLs, attached files) and the treatment wanted.\n**Output:** one output URL per item, a total cost, and a list of any failures.\n\n## Steps\n\n1. **Build the item list.** Read the spreadsheet, list, or attachments into an\n   explicit set. Show the user the parsed list and the count before going further —\n   a misparsed column is cheaper to catch now than after spending.\n\n2. **Resolve one technique** with `flora_list_techniques` and `flora_get_technique`.\n   One technique for the whole batch. If items need different treatments, that is\n   two batches, and say so.\n\n3. **Total the cost and stop.** Multiply `run_cost` by the item count and state it\n   plainly: *\"24 items x $0.117 = $2.81. Proceed?\"* **Wait for a yes.** Do this\n   even when the per-item cost looks trivial — the batch is where spend compounds.\n\n4. **Run them,** a few at a time rather than all at once. Poll each with\n   `flora_get_run`.\n\n5. **Report.** One row per item: source, output URL, cost. Then the total.\n\n## Rules\n\n- **Keep going when one item fails.** Collect failures and report them at the end\n  as a list. Never abort a paid batch partway and leave the user guessing what ran.\n- **Never re-run a completed item** to \"fix\" a batch. Each retry bills again.\n- **Attached files already have URLs** on `files.openai.com` or `cdn.openai.com`,\n  both allowlisted — pass them straight through. Never base64-encode anything.\n- **You cannot see any output.** Report URLs and let the user judge them.\n- If the user asks for more items than the confirmed count, re-total and re-confirm.\n"
}