Update to OloLand DD

{
  "description": "Use when the user asks to run the OloLand ololand-dd-deal-search workflow. Search documents in a deal's data room — full-text + semantic search across uploaded PDFs, financials, legal docs — plus literal/structural document navigation (list, read, grep, sections, tables, notes).",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 454
    }
  ],
  "name": "ololand-dd-deal-search",
  "skill_md_contents": "---\nname: ololand-dd-deal-search\ndescription: \"Use when the user asks to run the OloLand ololand-dd-deal-search workflow.\\\n  \\ Search documents in a deal's data room \\u2014 full-text + semantic search across\\\n  \\ uploaded PDFs, financials, legal docs \\u2014 plus literal/structural document\\\n  \\ navigation (list, read, grep, sections, tables, notes).\"\n---\n\n\n# Workflow for ololand-dd-deal-search\n\nFollow the OloLand command instructions below when the user asks for `ololand-dd-deal-search` or the equivalent workflow.\n\n# Deal Document Search\n\nSearch across all documents in a deal's data room using hybrid search (dense + sparse + rerank).\n\n## Usage\n\n```\nololand-dd-deal-search <deal_id> <query>\n```\n\n## Arguments\n\n- `deal_id` (required) — The deal to search within.\n- `query` (required) — Natural language search query.\n\n## Execution\n\n1. Call `search_deal_documents` with the deal_id and query.\n2. Present results with:\n   - Document name and page number\n   - Relevant excerpt (highlighted match)\n   - Relevance score\n3. If the query implies a financial figure, cross-reference with `get_financial_snapshot` to check consistency.\n\n## Examples\n\n- `ololand-dd-deal-search deal123 customer concentration risk`\n- `ololand-dd-deal-search deal123 revenue recognition policy`\n- `ololand-dd-deal-search deal123 change of control provisions`\n- `ololand-dd-deal-search deal123 EBITDA adjustments and add-backs`\n\n## Document navigation primitives\n\nSemantic search (above) answers \"what's relevant to this meaning.\" These\ntools answer \"I know (or can find) exactly where this is\" — literal path- and\nstructure-based access to the same data-room text, complementing\n`search_deal_documents` (semantic) and `grep_filing` (SEC-filing chunks).\n\n- **List** — `list_deal_files(deal_id)` returns every document's\n  data-room path, `file_id`, category, size, and modified time. Call this\n  before `read_deal_file` / `grep_deal_files` to see what exists.\n- **Read** — `read_deal_file(path, deal_id, offset, limit)`\n  reads a known document's full text by data-room path, paginated by line\n  (frontmatter stripped, `file_id` carried for citation).\n- **Grep** — `grep_deal_files(pattern, deal_id, glob,\n  case_sensitive, max_results)` is literal/regex pattern matching over the\n  markdown mirror — use this instead of `search_deal_documents` when the user\n  needs an exact string or regex match, not a meaning-based hit. `glob` scopes\n  to a folder/type, e.g. `financials/*`.\n- **Read a structural section** — `read_section(deal_id,\n  file_id, section)` reads a named section end-to-end (e.g. \"Item 7. MD&A\",\n  \"Note 11\", \"Risk Factors\", \"Consolidated Balance Sheet\"). Section matching\n  is case-insensitive substring; requires `file_id` from `list_deal_files`.\n  Documents without structural sections return the full document instead\n  (`matched_field=\"document\"`); a near-miss on a structured document returns\n  `available_sections` to retry against.\n- **Read a structured table** — `read_table(deal_id, file_id,\n  table_label)` returns a document-graph `TableNode` as typed rows × columns\n  with cell-level span IDs — not chunked text, so the row/column structure\n  survives. Returns an error if the graph has no matching table; there is no\n  chunk-based fallback for this one, deliberately, since chunking would\n  destroy exactly the structure this tool exists to preserve.\n- **Read a financial-statement note** — `read_note(deal_id,\n  file_id, note_number)` reads a numbered note in full, including its\n  outgoing `cross_references` — follow a Note 11 → Note 8 → Note 18 chain with\n  repeated calls, or `list_cross_references` for the whole graph at once.\n\nUse these when the user names a specific document, section, table, or note —\nreach for `search_deal_documents` when they're asking a question and don't\nknow exactly where the answer lives.\n\n\n## OpenAI execution requirements\n\nUse the connected MCP server's current tool schemas. Do not invent tool arguments, job-status endpoints, inputs, or outputs. If a referenced tool is unavailable, explain the limitation and request the needed connection or data. Invoke writes only when the user has requested the corresponding action. Do not initiate purchases or payments. An unrun, unsupported, or unavailable procedure is a gap, never a passing result.\n\n\nOpenAI cannot execute local lifecycle hooks. Use the packaged explicit setup/review workflow when requested. Server-side MCP auditing remains authoritative; preserve evidence blockers and human-only approval gates.\n\nClaim-correction submission is unsupported in this OpenAI upload because the current handler records surface=cowork. Do not invoke submit_agent_claim_correction from OpenAI. Explain the limitation and retain proposed correction text for human review without claiming submission. See unsupported-workflows.json for the excluded canonical workflow.\n"
}