Explore AI Agent Skills & Claude Prompts

Restores the standardized chart inventory (nine charts on HistFin Charts / NWC / Seasonality) on an Overland deal Databook (.xlsx) whose charts were gutted into empty shells by an openpyxl save. Use when the user asks to "restore the Databook charts" or "fix the charts" after dl-databook-financials populates the workbook — and again after every dl-databook-kpi call. Extracts a deterministic chart-spec manifest from the bundled blank template (the live OOXML, never guessed), then transplants the template's own chart/drawing/style parts into the populated vS workbook at the zip level, leaving the sheet-name-qualified source ranges to drive Excel's recomputation on open — gated by a machine-verified preservation gate (exactly the standardized inventory restored; every other part identical to the input; idempotent). Not for borrower-specific operational pie charts (out of scope), not for chart data population, not for other workbooks.

dl-memo-prescreen

Builds the multi-slide IC Pre-Screen Memo (.pptx) for Pre-Screen IC (P7) by populating the bundled deck template from the deal's upstream artifacts — the populated Databook, Overland Model, databook narrative, DD-list returns, posting memo, and posting-IC debrief. Use when a deal is heading to Pre-Screen IC and the user asks to "build the pre-screen memo," "populate the IC deck," "draft the IC memo," or to build or update a specific memo section or slide range. Two-turn workflow: scans the deck and confirms scope with the user (Turn 1), then executes a preservation-gated build (Turn 2). Runs in the Claude PowerPoint Add-in (active deck) and Claude Desktop (uploaded or cloned template). Internal-only RESTRICTED deliverable.

dl-databook-narrative

Synthesizes a structured MD&A-style narrative (markdown + JSON) from the populated P6 analytical workbooks (Databook vS + Overland Model vS) plus optional management commentary. Use at P6 after dl-databook-financials / -charts / -kpi / -model when the user asks to "write the databook narrative," "synthesize the MD&A," or "summarize what the workbooks say." Eight catalog categories; every item carries a verifiable workbook-cell, manifest-field, or commentary-excerpt basis (anti-fabrication); unions every upstream escalation, [INSUFFICIENT DATA] marker, tie miss, and validation-cross-check escalation into one severity-classified data-gap list. Feeds dl-ddq-initial and dl-memo-prescreen. Internal-only CONFIDENTIAL; reads no RESTRICTED input; the draft banner is the literal first line of the markdown.

dl-ddq-initial

Populates the Wells & Overland DD List one-pager (.docx) in [Initial] mode: a ruthlessly prioritized, exactly-one-page Initial DD list of diligence questions and data requests, reconciled against the deal folder AND the upstream P6 analytical workbooks. Use after a posting-IC decision when the user asks to prepare or build the Initial DD list / P6 data-request list. Unions the posting memo, IC debrief punchlist, any kick-off list, AND the dl-databook-narrative output (severity-filtered); applies the IC dispositions (rejected→kill, added→new, qualified→amend); reconciles received vs. outstanding via the M365 connector (degrading to document index); orders to the Overland credit framework; drafts gap-aware evidence-backed questions whose basis stays internal; edits the bundled template in place via populate_dd_list.py with the two-stage one-page discipline. Outbound co-lender-shared (CONFIDENTIAL); reads RESTRICTED debrief + CONFIDENTIAL narrative; emits internal data of neither.

dl-databook-model

Populates the Overland Model template's three case blocks (Sponsor Base / Overland Flat / Overland Downside) atomically in one call from the populated Databook anchors plus per-case forecast drivers extracted via the defensively-degrading project / chat / MSFT 365 cascade with deterministic basis-detection (CA-EBITDA vs Reported vs escalate) and bridge-apply translation. Use at P6 Initial DD after dl-databook-financials. Writes only the contracted driver cells (Sponsor Base dollars at rows 10/21/33/36/39/42/45/48/51/56 cols V-AB; Flat % drivers row 11 cols AJ-AN; Downside template-preset by default) plus static-state anchors; the model's formula machinery stays value-identical. The machine-verified preservation check runs in memory before any file write. Internal-only CONFIDENTIAL; never outbound.

dl-databook-financials

Populates the SUCAP and FinInputs tabs of the Overland deal Databook (.xlsx) from a deal's financial source set (QoE, audited/management financials, reporting packages, compliance certificates, Posting Memo Backup, posting memo, IC debrief) under a strict openpyxl formula-protection write-gate: resolves the period grid from the SUCAP anchors, applies backwards-from-most-recent restatement precedence, classifies reclass/diligence/pro-forma, and ties CA EBITDA to the QoE control total via a plan-validate-execute workflow. Off by default behind one self-verified structure pre-pass: per-business-unit scaffold tabs rolling up to FinInputs, off-quarter marketed LTM, and in-workbook QoE staging (a bridge-shaped QoEInputs scaffold derived from the single QoE). Template bundled in assets/. Activate to build/populate the Databook SUCAP/FinInputs tabs for P6 diligence; not for the Posting Memo Backup (use dl-memo-posting-backup), general Excel tasks, or the other eight Databook sheets.

dl-utility-project-context

Populates the deal-context slot of any Direct Lending Underwriting Library phase project instruction for a specific company and emits the fully-populated PI as a clean markdown block the teammate can paste into Claude Desktop's project instructions field. Three modes — Fresh-start for a new project; Refresh when deal state has moved within the same phase (new VDR wave, QoE roll-forward, posting-IC outcome, structure update); Roll-forward when the deal advances to the next phase (Stage 1→2, 2→3-P5, 3-P5→3-P6, 3-P6→3-P7, 3-P7→3-P8). Auto-detects current phase + company by scanning the project's already-attached PI before asking the teammate to confirm mode. Runs a reverse defensively-degrading cascade (Microsoft 365 connector SharePoint scan first → chat attachments → project attachments → user) to source every field; preserves teammate-supplied carryover values across refreshes and roll-forwards; emits a field-level diff in the cascade-trace footer; never fabricates a value the cascade cannot resolve.

dl-databook-comps

Builds the PublicComps and TnxComps tabs of the Overland deal Databook from a connector cascade. Public comps via FMP then Pitchbook then S&P CIQ then web (MSCI/LSEG, Yahoo, SEC/Edgar) - US-listed, mcap >$100M, in borrower GICS sub-industry, 10-20 names target 15 SMID-weighted, filtered for negative-EBITDA / TEV-Revenue>10x / TEV-EBITDA>35x with relaxation clause for the 10-name floor. Precedents via Pitchbook then web, web-enriched, AND-filtered for TEV-Revenue>10x AND TEV-EBITDA>35x, 10-20 names. Builds a 5-year historical TEV/EBITDA chart with four series (equal-weighted time series + flat average + flat plus/minus sigma bands) per Nathan-Yau viz discipline. Writes into the Databook with formatting consistent with the workbook and layout from the PortCo Coverage Template. Optimized for Excel add-in, Claude Desktop, claude.ai. Emits modified Databook + JSON valuation_summary frozen contract consumed by dl-memo-prescreen. Activate at P6 to build Databook comps; not the legacy Comps workbook.

dl-termsheet

Drafts the Wells & Overland Term Sheet (Stage 3 / P8) — the joint co-lender offer externalized to the borrower — from the IC-approved term-sheet input captured at the Pre-Screen IC. Use when the user asks to draft or populate the Wells & Overland Term Sheet from a Pre-Screen IC debrief ("draft the term sheet", "P8 term sheet", "populate the term sheet from the IC debrief"). Populates the bundled .docx template in place: writes deal-specific text into the 17 term rows of the body table plus the leverage-basis footnote; every other paragraph and cell stays unchanged behind a cell-level preservation gate. Classifies each IC condition externalize or internal_only (only externalize entries enter the document body) and runs the outbound-redaction checklist per build. Draft output under a vS filename pending human review.

dl-sector-screen

Decomposes a sector, industry, or sub-industry into discrete sub-verticals, screens each against the Overland industry attractiveness framework, and produces a structured markdown handoff with cascade anchor companies, NAICS codes, trade orgs, and conference targets for downstream borrower identification. Use whenever the user wants to develop sourcing coverage on a sector or industry — trigger phrases include "research X sector", "screen the Y industry", "develop sourcing coverage on Z", "decompose W into sub-verticals", "what sub-verticals in Q are attractive", or any freeform sector-level sourcing question. Use this even when the user describes a sector thematically (e.g., "aging infrastructure plays", "outsourced facilities services") rather than naming it directly. Do NOT use when the user names a specific company or deal (route to borrower identification or posting memo workflows), or for sector-level work unrelated to Overland sourcing such as public equity research or general market analysis.

dl-databook-charts

dl-memo-prescreen