dsh-data-cleaning-agent
Enterprise list data cleaning, profiling, and optional Qichacha MCP enrichment for DeepSeek Harness.
Install
$ dsh plugin --profile web add [email protected]Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Local row-level cleaning including whitespace trimming, phone number normalization, and deduplication
- Spreadsheet data profiling and column summary calculations without leaking raw rows to LLM contexts
- Multi-format input intake for CSV, XLSX, JSON, and OCR document extraction via MCP
- Interactive 5-step workbench UI for mapping verification, rule configuration, and export downloads
- Optional enterprise data enrichment using Qichacha MCP across corporate registration, risk, IP, and operational domains
- Safe audit trails, persistent task state machines, and downloadable clean CSV/XLSX artifacts
Useful For
- Deduplicating and standardizing dirty customer or prospect spreadsheets in DeepSeek Harness
- Enriching corporate lead lists with verified registration numbers, industry codes, and company details
- Generating statistical profile summaries of enterprise datasets prior to agent analysis
- Extracting company names and unified social credit codes from document images
Who It Fits
- Data analysts and operations teams cleaning large B2B lead spreadsheets in DeepSeek Harness
- Enterprise sales and marketing teams enriching corporate profile lists
- DeepSeek Harness users requiring deterministic local tabular data manipulation
Documented Limitations
- Enterprise data enrichment requires the user to provide their own authenticated Qichacha MCP account and API quota
- Interactive workbench features depend on compatible DSH client UI packages and optional dsh-better-sidebar for full drawer navigation
- Raw detail views and file processing are bound to the local host environment
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 2 runtime, 0 development, 5 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- duhu2000/dsh-data-cleaning-agent
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 86b5c9e · 2026-09-24
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 3GitHub stars
- Forks
- 0
- Open issues
- 2
- Last commit
- 2026-09-18
- Last release
- 2026-09-18
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →Vision routing and pixel-level tools for text-only DeepSeek Harness agents with built-in free fallback.
View plugin →Session lifecycle manager for DeepSeek Harness with search, restore, idle cleanup, and diagnosis.
View plugin →