← Plugin catalog
Finance
Regit PRIIPs
NICOLAS JOËL HUBERT KOENIG v1.0.0
Publisher description
From the marketplace listing
Regit PRIIPs calculates risk, performance-scenario, and cost figures from supplied product data with an authorized PRIIPs engine. It compares published and fresh KID figures for numeric Article 15 review triggers and returns structured results, coverage, and traces.
Language: English · Automatically detected from descriptions.
Files & skills
File archives
Plugin package4 files · 2.57 KBBrowse files →
Skill instructions
regit-priips-calculation3.98 KB
--- # SPDX-License-Identifier: LicenseRef-Regit-Proprietary # Copyright (c) 2026 Regit name: regit-priips-calculation description: Calculate and review PRIIPs KID risk, scenario, and cost figures from supplied facts; compare published and fresh figures for numeric review triggers. --- Use this skill when the user wants to prepare or review numeric PRIIPs KID figures from product facts, including a discrepancy check against an existing KID. Keep the job focused on the requested figures and their evidence. First establish that the request concerns PRIIPs, the exact product/share class and figure sought, and the relevant valuation or review date, holding period, and currency context needed for that figure. For another regulation, state this plugin's PRIIPs scope instead of forcing a PRIIPs operation. 1. Use only the approved `https://ai.regit.io/mcp/priips` connection with its exact resource and `priips:compute` scope. If linking or permission is missing, explain the access step and stop before calculation. 2. For an existing KID, use readable content available to the chat host to extract the published SRI, relevant MRM/CRM classes, and moderate-scenario returns by displayed holding period. Record the exact product/share class, document date, units, horizons, and page or section for each figure. The MCP connection does not ingest the document. Ask only when an extracted value or its product context is ambiguous; if content is unreadable, request the published figures and their source instead. 3. Discover the connection's current tools and advertised input schemas. Read `regit://priips/version` and `regit://priips/schemas` when available for provenance and detail; the advertised tool input schema governs calls and may differ structurally from the raw engine registry. Compute fresh risk, cost, or scenario figures only from current supplied product data and a supported tool. For SRI, obtain the MRM/CRM classes and each applicable liquidity criterion rather than inferring them from a generic liquidity label. For scenario presentation, use already-selected outcomes; do not treat presentation arithmetic as scenario selection. Chain cost operations only when their required inputs and prior Regit results exist. Never reuse old KID figures as fresh recomputations. Ask for missing, ambiguous, or invalid inputs, including numeric/range constraints, before calling; keep decimal values as strings where the live schema requires them. 4. If the user asks for a KID discrepancy check, compare the published and freshly recomputed SRI classes and moderate-scenario returns with the current numeric KID-review tool. Normalize published percentages and any Regit scenario fractions to one explicitly declared return unit only with deterministic exact-decimal arithmetic available to the host, never a binary-float or model-estimated conversion. If that is unavailable or the representation is ambiguous, request old/new values in the same stated units. Align displayed holding periods; include old/new MRM or CRM only as complete pairs when known, and supply the benchmark/proxy applicability fact. If a fresh figure cannot be computed from available current inputs, request the missing data or an externally recomputed figure with its provenance. Interpret shifts strictly greater than five percentage points and any unmatched horizons separately. A negative numeric trigger does not settle the review calendar, qualitative changes, whole-KID compliance, or revision. 5. Present published versus fresh figures with their sources, the Regit `result`, relevant `trace` steps, actual `coverage` or warnings, and engine version/provenance returned. For a discrepancy, prepare candidate corrected numeric figures and evidence for the manufacturer's review; do not claim to generate, validate, or publish a complete KID. If a tool reports an error or incomplete evidence, state that limit instead of giving an authoritative number.
Referenced files: 1
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package author
- NICOLAS JOËL HUBERT KOENIG
Package observed Oct 2, 2026.
Technical details
- First seen
- Sep 30, 2026 · 22:02 UTC
- Last seen
- Oct 2, 2026 · 18:00 UTC
- Collection status
- Collected
plugin_asdk_app_6aa9b40b7d1c8191b6dbaa860d8d1866
Download plugin data (JSON)