Update to OloLand DD

{
  "description": "Use when the user asks to run the OloLand ololand-dd-verify workflow. Verify every number and citation in an artifact (CIM paragraph, IC memo, risk narrative, DCF write-up) against a deal's source documents and deterministic engine runs. Works on OloLand-produced artifacts (four atomic-claim verifiers + citation audit + cross-document reconciliation) AND on externally-drafted artifacts — e.g. a memo written in your assistant — via per-claim corpus grading. The 'defend every number, cite every source' button.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 431
    }
  ],
  "name": "ololand-dd-verify",
  "skill_md_contents": "---\nname: ololand-dd-verify\ndescription: \"Use when the user asks to run the OloLand ololand-dd-verify workflow.\\\n  \\ Verify every number and citation in an artifact (CIM paragraph, IC memo, risk\\\n  \\ narrative, DCF write-up) against a deal's source documents and deterministic engine\\\n  \\ runs. Works on OloLand-produced artifacts (four atomic-claim verifiers + citation\\\n  \\ audit + cross-document reconciliation) AND on externally-drafted artifacts \\u2014\\\n  \\ e.g. a memo written in your assistant \\u2014 via per-claim corpus grading. The\\\n  \\ 'defend every number, cite every source' button.\"\n---\n\n\n# Workflow for ololand-dd-verify\n\nFollow the OloLand command instructions below when the user asks for `ololand-dd-verify` or the equivalent workflow.\n\n# ololand-dd-verify\n\nYou are running OloLand's verifier stack against an artifact and a deal. This is the user-facing surface for the four atomic-claim verifiers that back the \"verifiable outputs\" guarantee.\n\n## Required inputs\n\nAsk the user for these if missing:\n\n1. **deal_id** — the OloLand deal whose source documents back the verification.\n2. **text** — the artifact text to verify. Accept any of:\n   - A paragraph or section pasted inline.\n   - A path to a local file (read it with your file tool, then pass the contents).\n   - The output of a previous OloLand command (e.g., the IC memo body, a CIM section, a risk narrative).\n\nOptional:\n- **include_dcf_arithmetic** (default `true`) — also replay the DCF identity checks against the deal's stored `DCFRun`. Set to `false` if the artifact does not reference a DCF.\n- **audit_markers** (default `true` when the artifact contains `[N]` markers) — also run `check_citation_coverage` to audit the `[N]` markers.\n\n## Action\n\n1. Call `run_atomic_verifiers` with `deal_id`, `text`, and `include_dcf_arithmetic`.\n2. If the artifact contains any `[N]` markers, also call `check_citation_coverage` with the same `deal_id` and `text`. (Detect with a quick regex on the text — `\\[\\d+\\]` excluding `[EK:N]`.)\n3. If the user signals this is an IC memo or final report (i.e., wants a full audit, not just a spot-check), also call `reconcile_documents` with `deal_id`. This walks the CPA > tax > management > AI source hierarchy across the deal's stored financial observations.\n\n## Externally-drafted artifacts (e.g. written in your assistant)\n\nThe verifiers above are tuned for OloLand-produced text. When the user pastes an artifact **drafted outside OloLand** — a memo written in your assistant, a draft from another tool, a partner's marked-up paragraph — grade it per-claim against the deal's ingested data room instead:\n\n1. Call `grade_external_artifact` with `artifact_text`, `deal_id`, and `mode` (`strict` default; `lenient` for early drafts). Optionally pass a `rubric` string to steer what \"supported\" means.\n2. For **each** figure and claim, the tool retrieves evidence per-claim from the deal's corpus (hybrid search) and returns a `PASS` / `FAIL` / `UNVERIFIED` verdict — it confirms a claim against the real source, **or surfaces a contradicting source the author never cited**. It also returns a content-hashed provenance pack for IC lineage.\n3. Handle the nudge responses honestly, don't paper over them:\n   - `needs_deal` (no `deal_id`) — the artifact can't be graded without a deal to grade *against*. Offer to `create_deal` and upload the data room first (this is the intended OloLand adoption path from your assistant).\n   - `needs_corpus` (deal exists but empty) — ingest the data room before grading; there's nothing to retrieve against.\n\nPrefer `grade_external_artifact` over `run_atomic_verifiers` whenever the text did **not** come from an OloLand tool — it does the per-claim retrieval an external artifact needs, and it's the surface that turns a your assistant draft into a source-linked, IC-defensible one.\n\n## Output\n\nRender a single human-readable verdict block, in this order:\n\n```\nVerifier verdict for <deal_id>:\n  Inline numbers:      <supported>/<total> supported  [PASS|FAIL]\n  Claim chunks:        <supported>/<total> supported  [PASS|FAIL]\n  Citation existence:  <valid>/<total> valid          [PASS|FAIL|N/A]\n  DCF arithmetic:      <status>                        [PASS|FAIL|N/A]\n  [N] markers:         <in_range> in-range,\n                       <out_of_range> out-of-range    [PASS|FAIL|N/A]\n  Cross-doc reconcile: <reconciled>/<total> metrics   [optional, IC only]\n\nOverall: <PASS|FAIL>\n```\n\nThen list up to 10 unsupported numbers and unsupported claims verbatim (the most damaging review-cycle items). For each unsupported number, quote the `raw` field. For each unsupported claim, quote the sentence.\n\nIf the artifact is going into IC or a regulator-facing deliverable and the verdict is FAIL, recommend the user:\n\n1. Re-run `search_deal_documents` for any unsupported claim to locate the missing source.\n2. Fix the citation with an inline `[N]` marker pointing at the retrieved chunk.\n3. If a number cannot be sourced, remove the claim or downgrade it to qualitative language.\n\n## When to use this\n\n- Right before submitting an IC memo, CIM, or board-pack section.\n- During a partner review when a number \"looks off\".\n- As a pre-commit check on AI-generated risk narratives before they land in `analyst_corrections`.\n- Mid-conversation, after any agent finishes generating a deal-bound artifact — `ololand-dd-verify` it against the same deal.\n- On a memo or analysis **drafted in your assistant or another tool** — grade it against the deal's data room to turn unsourced prose into source-linked, IC-defensible claims (uses `grade_external_artifact`).\n\n## When NOT to use this\n\n- For prose that contains no numbers and no citations — the verifier has nothing to check.\n- For non-deal artifacts (general M&A commentary, market color, methodology notes).\n- Pre-ingestion — verifiers need a populated deal corpus to retrieve chunks against. If `citations_available` is 0, ingest documents first.\n\nCompanion skill: `verifier-stack` (auto-loads with this command and explains the methodology and the limits of each verifier).\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"
}