{"id":76390,"plugin_id":"plugin_asdk_app_6ad3a430b30481919b3d089dabbc9b93","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-02T18:12:10.996Z","digest":"75ad15be208c213dc79c2a52151f266940294c82131fef1f1d32d3b9d2a4aa7d","against":null,"payload":{"description":"Use when the user asks to run the OloLand ololand-dd-regulator-export workflow. Queue a regulator export pack — a tarball of every agent_run + agent_spans + output_artifacts in a date window, mapped to a compliance framework's controls. Admin / compliance role required. The defensible-audit-trail deliverable.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":454}],"name":"ololand-dd-regulator-export","skill_md_contents":"---\nname: ololand-dd-regulator-export\ndescription: \"Use when the user asks to run the OloLand ololand-dd-regulator-export\\\n  \\ workflow. Queue a regulator export pack \\u2014 a tarball of every agent_run +\\\n  \\ agent_spans + output_artifacts in a date window, mapped to a compliance framework's\\\n  \\ controls. Admin / compliance role required. The defensible-audit-trail deliverable.\"\n---\n\n\n# Workflow for ololand-dd-regulator-export\n\nFollow the OloLand command instructions below when the user asks for `ololand-dd-regulator-export` or the equivalent workflow.\n\n# ololand-dd-regulator-export\n\nYou are queueing a compliance-framework export. The Celery task `tasks.regulator_export_tasks.generate_regulator_export` builds a tarball with:\n\n- Every `agent_runs` row in the window (id, snapshots, grader verdicts, cost, status).\n- All `agent_spans` for those runs (tool calls, model calls, compactions).\n- All `output_artifacts` produced (CIMs, IC memos, forensic PDFs).\n- Control-map metadata for the named compliance framework so each artifact is keyed to the relevant control.\n\n**This command requires admin or compliance role.**\n\n## Required inputs\n\n1. **framework** — compliance framework id. The tool validates against `available_frameworks()` and returns the list on a bad input. Ask the user if unclear.\n2. **from_date** — ISO `YYYY-MM-DD`, inclusive.\n3. **to_date** — ISO `YYYY-MM-DD`, inclusive.\n\nOptional:\n- **deal_ids** — list of specific deals to restrict the export to. Omit for company-wide.\n\n## Action\n\n1. Call `request_regulator_export` with the collected fields.\n\n2. On success, the response is a `RegulatorExport` row in `status: \"queued\"`. Surface:\n   ```\n   Regulator export queued\n     Export id:    <id>\n     Framework:    <framework>\n     Window:       <from_date> to <to_date>\n     Deals:        <all|specific list>\n     Status:       queued\n   ```\n   Tell the user to poll `get_regulator_export <export_id>` for completion. Typical latency: minutes to hours depending on window size and corpus.\n\n3. When polling shows `status: \"completed\"`, surface `tarball_uri`, `tarball_sha256` (for chain-of-custody attestation), and `expires_at`. The URI is a signed download link.\n\n4. On error from the request, surface the `error_code` and explanation:\n   - `bad_request` (unknown framework) — surface the `available` list verbatim.\n   - `insufficient_role` — user is not admin/compliance.\n   - `no_company` — agent key is not company-scoped.\n\n## When to use\n\n- A regulator (SEC, FINRA, FCA, etc.) requests a defensible audit trail.\n- Internal compliance review (SOC 2 controls, ISO 27001, EU AI Act conformity).\n- IC-mandated reproducibility exercise for a closed deal.\n- Periodic compliance archive (monthly / quarterly).\n\n## When NOT to use\n\n- For one-off \"show me the audit trail for this run\" — use `ololand-dd-inspect-run` directly. Regulator exports are tarballs and asynchronous; not the right tool for a single-run query.\n- For commercial-grade reports for non-compliance audiences — use `generate_investment_memo` or `generate_cim` instead.\n\n## SHA-256 attestation\n\nWhen you surface `tarball_sha256` to the user, include the recommendation that they record the hash separately from the OloLand system at the moment of download. The hash is what makes the tarball tamper-evident to a downstream regulator — if it changes, the chain-of-custody is broken.\n\nCompanion commands: `ololand-dd-inspect-run`, `ololand-dd-replay-run`.\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"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}