By kwaw-danflo
Truist Commercial Credit Memo Agent — drafts SR 11-7 compliant credit memos for C&I borrowers by orchestrating Salesforce/nCino loan data, Boom-spread financials, EDGAR peer benchmarking, and Truist underwriting standards. Use when an RM or credit officer needs a draft memo for a commercial borrower.
How to call the Boom (api.boom.build) REST API to spread borrower financials. Use whenever the credit-memo agent needs to upload financial statements for spreading, look up an existing spread, or fetch IS / BS / CF / equity statements from a completed file. Trigger on phrases like "spread the financials", "upload to Boom", "get the spread", "fetch IS / BS / CF", or when the credit-memo agent's workflow reaches the Boom step.
Truist commercial credit memo methodology. Section structure, ratio definitions, NAICS-aggregated peer analysis, covenant compliance framework, Truist-branded HTML/PDF output. Use whenever drafting, refreshing, or auditing a commercial credit memo for a C&I borrower at Truist Bank — covers C&I working capital lines, term loans, revolvers, and middle-market deals up to roughly $250M facility size. Trigger on phrases like "draft a credit memo", "refresh the memo", "covenant compliance", "risk rating writeup", or any request to produce or update a commercial loan underwriting document.
Render a one-screen inline visual summary of a commercial borrower's credit package — facility exposure, financial KPIs from latest Boom spread, loan tiles, covenant compliance, collateral coverage, and guarantor. **TRIGGER aggressively** on ANY of these phrasings when a commercial borrower is named or referenced: "summarize the deal", "summarize [borrower]", "deal summary", "summary of the [borrower] deal", "deal at a glance", "quick summary", "credit snapshot", "deal overview", "show me the credit package", "give me a snapshot", "give me an overview", "what's the deal with [borrower]", "tell me about [borrower]'s credit", **"tell me about [borrower]"**, **"tell me what you know about [borrower]"**, **"what do we know about [borrower]"**, **"research [borrower]"**, **"look up [borrower]"**, **"what's our exposure to [borrower]"**, **"what's the status of the [borrower] deal"**, **"pull up [borrower]"**, **"show me [borrower]"**. Whenever a banker mentions a company or business name in the context of credit, lending, or relationship inquiry, this is almost certainly the right skill — render the widget rather than answering from general knowledge. Prefer this skill over `commercial-credit-memo` whenever the user asks for a SUMMARY or OVERVIEW (anything that suggests a quick read), and only use `commercial-credit-memo` when the user explicitly asks to "draft", "write", "generate", or "refresh" the full credit memo. NOT for drafting the full credit memo.
How to upload a rendered credit memo PDF to nCino DocMan via the Document Manager Placeholder API. Use whenever the agent needs to write a memo (or any other document) back to a borrower's record in nCino, save to DocMan, save to the deal record, save to the loan record, or upload to a Product Package. Trigger on phrases like "save to nCino", "upload to DocMan", "save to the deal", "save the memo", "write back to nCino", or any request to register a document in the bank's system of record after the agent has produced it.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Cowork plugin that drafts Truist Commercial credit memos for C&I borrowers by orchestrating Salesforce/nCino, Boom, EDGAR, FRED, and Gmail. Built by Noland Smith (Accenture) for an internal Accenture POV meeting on the Truist Bank credit memo opportunity.
See CLAUDE.md for the full project context and strategic frame.
Credit Memo/
├── CLAUDE.md Project context, demo flow, architecture, branding
├── README.md (this file)
├── data/
│ └── borrower-profile.md Atlas Industrial Supply sandbox seeding spec
├── output/ Generated memos land here (gitignored)
├── test/ Local validation scaffold
│ ├── atlas-mock-data.json Atlas data for the static render test
│ ├── render.py Static render script (template + data → HTML)
│ └── atlas-rendered.html Output of render.py (re-runnable)
└── truist-credit-memo-agent/ ← Plugin source (referenced by marketplace.json)
├── .claude-plugin/plugin.json
├── settings.json
├── agents/credit-memo.md
├── skills/
│ ├── commercial-credit-memo/ SKILL.md + 5 references + HTML template
│ └── boom-spreading/ SKILL.md + 2 references
└── assets/
├── brand-tokens.css
├── brand-notes.md
└── truist-wordmark.svg
The plugin defines methodology + skills + branding only. Data source connections are configured at the Cowork user level (not in the plugin), so they can vary per deployment / per user. You need:
brew install claude or per https://code.claude.com/docs/en/installation)mcp_apiBOOM_API_KEY environment variable in Cowork — bearer token for the Boom REST APIanthropic-skills plugin installed in Cowork — provides the pdf skill the memo uses for HTML → PDF conversionThe canonical prompt the agent handles end-to-end:
"I just got an email from [Borrower] with their Q1 2026 financials attached. Find the email in my Gmail, upload the attachment to Boom for spreading, pull the loan record + covenants from BankingGPT sandbox via Salesforce MCP, fetch a NAICS-aggregated peer set from EDGAR for benchmarking, draft a Truist Commercial Credit Memo, render it as an HTML artifact for live review, generate a Truist-branded PDF, and upload to nCino as a draft document on the loan's DocMan record."
The agent executes the 8-step workflow defined in agents/credit-memo.md: Gmail → Salesforce → Boom → EDGAR → ratios + covenant checks → HTML render → PDF → nCino upload.
Three things you can validate from Claude Code without leaving this machine:
cd "/Users/nolandsmitth/Desktop/Credit Memo"
claude --plugin-dir ./truist-credit-memo-agent
In the Claude Code session that opens:
/help — you should see credit-memo listed under the plugin namespace and the two skills (truist-credit-memo-agent:commercial-credit-memo, truist-credit-memo-agent:boom-spreading)/agents — you should see credit-memo listed/mcp — you should see your user-level connectors (Salesforce, Gmail). The plugin itself ships no MCP servers; it expects these at the Cowork user level.If the plugin fails to load, the error message identifies the broken file (usually a YAML frontmatter issue or a path typo). Re-run after fix; /reload-plugins picks up changes without restarting.
The render test fills the HTML template with Atlas Industrial Supply data and produces a rendered HTML you can open in a browser. This validates: Truist branding, layout, page breaks, color-coded ratios, covenant flag rendering, and table density.
cd "/Users/nolandsmitth/Desktop/Credit Memo"
python3 test/render.py
open test/atlas-rendered.html
npx claudepluginhub kwaw-danflo/test-plugin --plugin truist-credit-memo-agentComplete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research