Skip to content

AI4RA Prompt Library

Versioned prompts, skills, agents, schemas, and component contracts for research-administration work.

This repository is the prompt-library leg of the AI4RA evaluation triad. The evaluation harness discovers components here, pairs them with datasets from AI4RA/evaluation-data-sets, and uses the shared ui-insight/AI4RA-UDM foundation where a component is UDM-aligned. Contract scope is recorded per component in component_catalog.json.

Start by filtering below, or jump to:

Browse all components

award-allowability-terms-extraction

experimental

Extracts the federal award terms that govern cost allowability — period of performance, approved budget categories, caps and exclusions, sponsor prior-approval triggers, indirect-cost treatment, and institutional compliance-approval requirements — into one structured record. It is an input-normalization step of the federal cost-allowability analysis workflow.

extractionresearch-administrationv0.1.0prompt
cost-allowability post-award award-terms extraction federal-grants research-administration

award-compliance-extraction-udm

experimental

Extracts the compliance framework and financial-management requirements from a federal award document into a single structured JSON object that drives a consolidated "Award Compliance & Financial Overview" deliverable for post-award setup and monitoring. Produces two main blocks (compliance framework with 10 fields including a normalized compliance calendar; financial management with 10 fields including budget periods and budget categories).

extractionresearch-administrationv0.1.0prompt
post-award compliance financial-management federal-awards terms-and-conditions 2-cfr-200 audit udm structured-extraction json

award-modification-intake-udm

experimental

Classifies an incoming federal award amendment / modification document and extracts the type-specific fields a Post-Award Specialist needs to enter the modification into Banner. Covers the four mapped modification processes — additional funds, no-cost extension (NCE), PI change, rebudget — plus scope change, administrative change, and combined modifications. The structured JSON output drives Banner setup; the source process-mapping workflow's human-review (ApprovalNode) step is a runtime concern handled by Vandalizer's UI and is not part of this extraction contract.

extractionresearch-administrationv0.1.0prompt
award-modification post-award intake classification ncne rebudget pi-change additional-funds udm structured-extraction json

budget-justification-generator-udm

experimental

Generates a complete, professional budget-justification narrative from a grant budget form and the project narrative / proposal. Captures both the structured per-section extracted financial data AND the generated narrative text for each section, plus the final assembled Markdown document and cross-validation notes. Organized in standard R&R Budget / SF-424A category order (A through I). Supports multi-year budgets and agency-specific rules when a NOFO / RFA is provided.

draftingresearch-administrationv0.1.0prompt
budget-justification drafting pre-award nsf nih rr-budget sf-424a narrative-generation multi-year udm structured-output json

compliance-personnel-verification-udm

experimental

Automates the SFI (Significant Financial Interest) disclosure and RST (Research Security Training) compliance check across every person named on a federal research proposal. Joins three input sources — the VERAS proposal package, the institutional SFI disclosure records, and the most recent daily RST completion spreadsheet — into a per-person compliance matrix that a Sponsored Programs Administrator (SPA) reviews in seconds rather than minutes per person. Covers the source `PROC-SFI-RST-COMPLIANCE-CHECK` process (10 steps, 80% automatable per the source process map).

extractionresearch-administrationv0.1.0prompt
compliance sfi rst personnel-verification veras pre-award conflict-of-interest research-security-training udm structured-extraction json

cost-allocability-check

experimental

Checks whether a single expense is allocable to the award under 2 CFR 200.405 — that it benefits the award and is charged in reasonable proportion to that benefit. It is one of the single-requirement checks in the federal cost-allowability analysis workflow and emits a structured finding consumed by the final determination step.

reviewresearch-administrationv0.1.0prompt
cost-allowability post-award allocability review federal-grants research-administration

cost-allowability-determination

experimental

Synthesizes the findings from the upstream single-requirement checks into one concise, decision-ready Markdown allowability review for a single expense. It is the final step of the federal cost-allowability analysis workflow.

reviewresearch-administrationv0.1.0prompt
cost-allowability post-award determination synthesis review research-administration

cost-award-terms-conformance-check

experimental

Checks whether a single expense conforms to the limitations and exclusions in the Federal award and the cost principles, under 2 CFR 200.403(b). It is one of the single-requirement checks in the federal cost-allowability analysis workflow and emits a structured finding consumed by the final determination step.

reviewresearch-administrationv0.1.0prompt
cost-allowability post-award award-terms review federal-grants research-administration

cost-consistent-treatment-check

experimental

Checks whether a single expense is accorded consistent treatment under 2 CFR 200.403(d) and 200.405(c) — that it is not direct-charged to the award when costs incurred for the same purpose in like circumstances are recovered as indirect (F&A) costs. It is one of the single-requirement checks in the federal cost-allowability analysis workflow and emits a structured finding consumed by the final determination step.

reviewresearch-administrationv0.1.0prompt
cost-allowability post-award consistent-treatment indirect-cost review research-administration

cost-documentation-check

experimental

Checks whether a single expense is adequately documented under 2 CFR 200.403(g) to support charging it to the award. It is one of the single-requirement checks in the federal cost-allowability analysis workflow and emits a structured finding consumed by the final determination step.

reviewresearch-administrationv0.1.0prompt
cost-allowability post-award documentation review federal-grants research-administration

cost-period-check

experimental

Checks whether a single expense was incurred within the award's period of performance, under 2 CFR 200.403(h) and 200.309. It is one of the single-requirement checks in the federal cost-allowability analysis workflow and emits a structured finding consumed by the final determination step.

reviewresearch-administrationv0.1.0prompt
cost-allowability post-award period-of-performance review federal-grants research-administration

cost-prior-approval-check

experimental

Checks whether a single expense represents an action that requires federal sponsor prior written approval under 2 CFR 200.407, and whether that approval is evidenced. It is one of the single-requirement checks in the federal cost-allowability analysis workflow and emits a structured finding consumed by the final determination step.

reviewresearch-administrationv0.1.0prompt
cost-allowability post-award prior-approval review federal-grants research-administration

cost-reasonableness-check

experimental

Checks whether a single expense is necessary and reasonable under the prudent-person standard of 2 CFR 200.404. It is one of the single-requirement checks in the federal cost-allowability analysis workflow and emits a structured finding consumed by the final determination step.

reviewresearch-administrationv0.1.0prompt
cost-allowability post-award reasonableness review federal-grants research-administration

cost-selected-item-check

experimental

Identifies which selected item of cost under 2 CFR 200.421-200.476 governs an expense and applies that section's rule. It is one of the single-requirement checks in the federal cost-allowability analysis workflow and emits a structured finding consumed by the final determination step.

reviewresearch-administrationv0.1.0prompt
cost-allowability post-award selected-items-of-cost review federal-grants research-administration

document-type-classifier-udm

experimental

Classifies a research-administration document into a controlled type vocabulary so downstream pipelines can route it to the correct extractor or reviewer. One call in, one small JSON object out.

classificationresearch-administrationv1.0.0prompt, skill
classification routing triage udm research-administration document-type

effort-reporting-extraction-udm

experimental

Extracts effort-reporting and personnel-compliance requirements from a federal award document into a structured JSON object that drives an "Effort Compliance Brief" for post-award compliance tracking. Captures the reporting cadence, certification method (per 2 CFR 200.430(i)), PI commitments, per-person key-personnel commitments, cost-shared effort, governing regulation, record-retention requirement, and referenced governing documents.

extractionresearch-administrationv0.1.0prompt
effort-reporting post-award certification personnel cost-share 2-cfr-200 compliance udm structured-extraction json

expense-transaction-extraction

experimental

Normalizes one expense — receipt, invoice, purchase order, p-card line, or general-ledger detail — into a single structured transaction record covering date, vendor, amount, account coding, description, and documentation status. It is the input-normalization step of the federal cost-allowability analysis workflow.

extractionresearch-administrationv0.1.0prompt
cost-allowability post-award expense extraction federal-grants research-administration

export-to-banner-extraction-udm

experimental

Extracts operational setup data from a fully-executed federal award document into the specific fields needed to populate the VERAS Export to Banner form. Focuses on Banner ERP-specific data points: award identification, dates and performance period, sponsor entity classification, budget structure and indirect-cost terms, billing and payment terms, and reporting / special-conditions text. Complements `award-compliance-extraction-udm` (broader compliance monitoring) by targeting only the operational fields Banner needs.

extractionresearch-administrationv0.1.0prompt
export-to-banner post-award banner-erp award-notice financial billing sponsor-classification udm structured-extraction json

ffr-management-extraction-udm

experimental

Extracts Federal Financial Report (FFR / SF-425) requirements and post-award financial reporting obligations from a federal award notice or agreement into a structured JSON object organized around the five buckets a sponsored-programs analyst uses when preparing FFR submissions: submission schedule, submission system and procedures, required financial data, compliance consequences, and preparation timeline.

extractionresearch-administrationv0.1.0prompt
ffr sf-425 post-award financial-reporting federal-financial-report compliance udm structured-extraction json

foa-checklist-extraction-udm

experimental

Extracts a Federal Funding Opportunity Announcement (FOA) into a structured JSON object covering the eight reference sections a federal-grants office uses for FOA review: FOA summary, key dates, funding information, eligibility, application components, evaluation process, program priorities, and special requirements. Stronger emphasis than its sibling `rfa-checklist-extraction-udm` on the **evaluation criteria**, **review process**, and **submission system** fields.

extractionresearch-administrationv0.1.0prompt
foa federal-funding pre-award checklist evaluation-criteria nih hhs doe udm structured-extraction json

noa-summary-udm

experimental

JSON extraction contract for a federal **Notice of Award (NoA)**. Extracts award identification, key personnel and federal contacts, financial terms, periods of performance, reporting deadlines, and compliance/administrative obligations into a single structured JSON object (see [`schema.json`](schema.json)).

extractionresearch-administrationv0.1.0prompt
noa notice-of-award grant-award-summary post-award compliance financial udm structured-extraction json

nsf-award-notice-extraction-udm

stable

Extracts an NSF Award Notice (initial obligation or amendment) into a single JSON object conforming to this repo's UDM-aligned extraction contract. Designed for the NSF notice format that arrives as a PDF printed from Outlook after OSP receipt — the email header, boxed notice body, and NSF-format 18-category budget table.

extractionresearch-administrationv1.1.0prompt, skill
nsf award notice noa amendment udm structured-extraction json

nsf-budget-justification-render-udm

experimental

Renders a reviewed eight-section NSF budget-justification array into Word-pasteable Markdown and HTML strings. The component is the formatting tail of a multi-step budget-justification pipeline: it does not draft, review, or reinterpret content — it transforms the structured array into two presentation forms that paste cleanly into a Microsoft Word document.

transformationresearch-administrationv1.0.0prompt
nsf budget-justification render format markdown html word udm research-administration proposal-preparation

nsf-budget-justification-review-udm

experimental

Validates and polishes a drafted NSF budget-justification array against its source structured budget and NSF narrative conventions. The component is the QA step of the multi-step budget-justification pipeline: it checks section completeness and ordering, fixes misplaced content (for example graduate tuition in the wrong section), ensures required NSF disclosures are present, and consolidates terminology across sections. Its revised array is the input to the downstream render step that emits Word-pasteable Markdown and HTML.

reviewresearch-administrationv1.0.0prompt
nsf budget-justification review polish udm research-administration proposal-preparation

nsf-budget-justification-udm

experimental

Drafts an NSF-format budget justification narrative from a structured budget object. Output is the eight canonical NSF sections (A..H) as an ordered array of section objects — one per section, each with a `key`, a fixed `title`, and `content` in narrative markdown. All eight sections are always emitted; zero-value categories produce a single-sentence content.

draftingresearch-administrationv1.0.0prompt, skill
nsf budget-justification drafting udm research-administration proposal-preparation

nsf-budget-spreadsheet-ingest-udm

experimental

Normalizes an NSF-style proposal budget workbook (or workbook-derived evidence) into the structured budget object consumed by `nsf-budget-justification-udm`. This component is the extraction half of a multi-step budget-justification pipeline: it isolates spreadsheet interpretation from narrative drafting so each responsibility can be prompted, versioned, and evaluated independently.

extractionresearch-administrationv1.0.0prompt
nsf budget spreadsheet-ingest extraction udm research-administration proposal-preparation

nsf-budget-spreadsheet-justification-udm

experimental

Drafts an NSF-format budget justification directly from an NSF-style proposal budget spreadsheet or spreadsheet evidence package. The component interprets workbook tabs for personnel, equipment, travel, participant support, other direct costs, subawards, tuition/fees, and rates, then emits the same eight-section JSON narrative contract used by `nsf-budget-justification-udm`.

draftingresearch-administrationv1.0.0prompt
nsf budget-justification spreadsheet-ingest drafting udm research-administration proposal-preparation

nsf-expense-allowability-check

experimental

Reviews a single expense against NSF award terms, supplied budget evidence, and general sponsored-programs allowability criteria. The component turns the original checklist-style "Expense-Allowability Check" prompt into an evidence-grounded chat review with explicit rule checks, budget alignment, citations, follow-up actions, and a conservative final decision.

reviewresearch-administrationv1.0.0prompt
nsf expense-allowability post-award compliance budget review research-administration

prior-approval-extraction-udm

experimental

Extracts all prior-approval requirements from a federal award document into a structured JSON object suitable for driving a tracking system of activities that need federal-agency authorization before they can be executed. Produces three logical buckets (budget-related, scope/timeline, approval procedures table) plus a list of Research Terms and Conditions (RTC) waivers and expanded-authority delegations.

extractionresearch-administrationv0.1.0prompt
prior-approval post-award modifications federal-awards rtc 2-cfr-200 compliance udm structured-extraction json

proposal-budget-personnel-extraction-udm

experimental

Extracts personnel information and compliance-requirement triggers from a proposal budget document into a structured JSON object. Identifies senior key personnel, postdocs, graduate students (RA / TA), undergraduates, and other personnel; the budget category structure; subaward recipients, equipment over $5,000, travel summary, F&A rate and base, cost sharing, and total costs. The output drives the downstream `proposal-document-completeness-udm` gap analysis.

extractionresearch-administrationv0.1.0prompt
pre-award proposal budget personnel mentoring-plan compliance-triggers nsf udm structured-extraction json

proposal-document-completeness-udm

experimental

Automates the near-final document-completeness review of a proposal package: identifies all senior key personnel, the four required documents per person (biosketch, current & pending, collaboration & affiliation, synergistic activities), subaward documents, and conditional-requirement triggers. Produces a single gap-analysis JSON for sponsored-programs analysts to use when sending a "missing documents" message back to the PI.

extractionresearch-administrationv0.1.0prompt
pre-award proposal completeness near-final-review nsf nih gap-analysis udm structured-extraction json

protocol-approval-allowability-check

experimental

Checks whether an expense tied to a regulated activity is backed by a current, in-scope institutional protocol approval — IRB (human subjects), IACUC (animals), or IBC (biosafety). It is one of the single-requirement checks in the federal cost-allowability analysis workflow and emits a structured finding consumed by the final determination step.

reviewresearch-administrationv0.1.0prompt
cost-allowability compliance irb iacuc biosafety review research-administration

regulated-activity-classifier

experimental

Flags whether an expense implicates an activity that requires institutional compliance oversight — human subjects (IRB), animals (IACUC), or biosafety (IBC) — based on expense-level signals such as the description, vendor, and account coding. It is the detection layer of the federal cost-allowability analysis workflow.

classificationresearch-administrationv0.1.0prompt
cost-allowability compliance irb iacuc biosafety classification research-administration

rfa-checklist-extraction-udm

experimental

Extracts a federal funding announcement (RFA / FOA / NOFO / program solicitation) into a structured JSON object organized around the **eight-section pre-award checklist** that a sponsored-programs analyst actually uses when triaging a new opportunity. The shape enforces placement rules — award amount lives in `award_information` only, detailed financial rules in `budget_requirements` only — so downstream consolidation does not have to re-adjudicate where a fact belongs.

extractionresearch-administrationv0.1.0prompt
rfa foa nofo grants pre-award checklist udm structured-extraction json

risk-domain-assessment-udm

experimental

Evaluates one or more award documents (Notice of Award, FOA / NOFO / RFA, modification, proposal) across 14 institutional risk domains using a standardized 1–5 scoring rubric. Each domain captures a distinct dimension of risk — programmatic complexity, financial structure, subrecipient risk, research security, compliance burden, reporting burden, administrative burden, audit risk, strategic alignment, sustainability, sensitive data, IP / privacy, sponsor reliability, reputational risk — and produces an evidence-cited justification supporting an informed institutional risk-acceptance decision.

reviewresearch-administrationv0.1.0prompt
risk-assessment risk-scoring 14-domain-rubric post-award pre-award compliance research-security audit sustainability intellectual-property reputational-risk udm structured-extraction json

section2-personnel-eligibility-udm

experimental

Automates the VERAS Section 2 review at the University of Idaho — the most-requested SPA automation in the source process map. Extracts every PI / Co-PI / Senior Key Person from VERAS Section 2, verifies employment via Banner NBAJOBS, cross-references each PI / Co-PI job title against APM Section 45.22 eligibility criteria, compiles timesheet org codes, maps org codes to Departmental Grant Administrators (DGAs) using the institutional Department List, and cross-references required DGAs against Section 2 participants. Covers the source `PROC-SPA-SECTION2-REVIEW` process (13 steps, 77% automatable per the source process map).

extractionresearch-administrationv0.1.0prompt
section2 veras pre-award personnel-eligibility apm-45-22 dga-mapping pi-eligibility banner udm structured-extraction json

solicitation-doc-modifications-udm

experimental

Given a solicitation text and a sponsor's default document requirements, emit only the **diff**: modifications to the defaults and net-new documents the solicitation introduces. Each entry links back to the default it overrides (when applicable) via `modifies_default` and carries a verbatim `source_excerpt` from the solicitation.

extractionresearch-administrationv1.0.0prompt, skill
solicitation requirements modifications udm research-administration proposal-preparation

sponsor-doc-defaults-udm

experimental

Given a sponsor organization (and optional division), emit the default set of documents that sponsor typically requires for a standard full proposal — as a structured list with page limits, format specs, required vs. optional flags, per-person indicators, and conditional triggers.

researchresearch-administrationv1.0.0prompt, skill
sponsor requirements defaults udm research-administration proposal-preparation

subaward-extraction-udm

experimental

Extracts a fully executed subaward agreement (Pass-Through Entity → Subrecipient) into a single structured JSON object covering nine sections used for research-administration setup and ongoing monitoring: basic info, project periods, PTE contacts, subrecipient contacts, financial summary, financial policies, reporting requirements, prior-approval handling, and key compliance requirements.

extractionresearch-administrationv0.1.0prompt
subaward post-award agreement pte subrecipient financial-policies contacts udm structured-extraction json

vandalizer-to-udm-translation

experimental

Converts a Vandalizer NSF-extraction JSON object (flat key/value form) into a single JSON object conforming to the `nsf-award-notice-extraction-udm` schema. This is a pure transformation — no information is invented, and fields Vandalizer does not capture emit as `null` or documented defaults.

transformationresearch-administrationv0.1.0prompt
nsf award notice udm translation vandalizer structured-transformation json