dsh-pre-duediligence
Run the following command in DeepSeek Harness:
dsh plugin install duhu2000/dsh-pre-duediligence
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install duhu2000/dsh-pre-duediligence in your terminal to install the plugin; the source is available at https://github.com/duhu2000/dsh-pre-duediligence . Restart DeepSeek Harness after installation to activate it.
About this plugin
Before every client meeting, the most time-consuming part is rarely the conversation itself but the groundwork: identifying which data points matter, tracing risk signals, and confirming operational anomalies. Registration records, litigation history, IP portfolios, executive changes - scattered across systems and spreadsheets - are slow and error-prone to piece together manually. dsh-pre-duediligence brings the entire pre-visit due-diligence workflow into a native DeepSeek Harness session, letting an agent handle data collection, evidence verification, and report generation so that business users walk in with a structured, traceable brief in hand.
Powered by five QCC MCP data sources, the plugin covers five stages: scope confirmation, data collection, evidence verification, and material output. The agent locks onto a single legal entity first, then scans operational status and risk signals at fast, standard, or deep depth, separating facts from inferences and supporting evidence from counter-evidence. The result is an eight-section pre-visit report that can be previewed online or exported as HTML, Word, or PDF. A built-in four-step prompt composer removes the guesswork from writing instructions - fill in the visit target, role, focus areas, and output format, and a natural-language prompt is generated for you.
The plugin is designed for bank relationship managers, sales and BD professionals, procurement teams, investors, and industrial-park business-development staff - anyone who benefits from structured homework before a client meeting. Pre-visit research is not a substitute for full AML / KYB compliance, audit, or credit decisions; the plugin outputs no credit scores and does not make commercial judgments on behalf of the user. All factual content comes exclusively from the live QCC MCP responses in the current session, and multi-candidate entities must be disambiguated by a human before the workflow continues.
Use Cases
- A bank RM verifying a corporate client's registration, litigation, and operational status before a visit
- Sales or BD staff preparing background, ownership, and risk signals ahead of a negotiation
- Generating a traceable, exportable pre-visit due-diligence report for investment or park BD outreach
Best For
- Bank corporate relationship managers
- Sales, BD, and procurement professionals
- Investment analysts and industrial-park business-development staff
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.