dsh-smart-charts
Interactive ECharts visualization skill for DeepSeek Harness to convert CSV, Excel, and JSON data into charts.
Install
$ dsh plugin --profile web add github:hherosoul/dsh-smart-chartsPlugin 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
- Supports 32 ECharts chart types including line, bar, pie, radar, heatmap, treemap, sankey, and geographic maps (China/World GeoJSON included)
- Automatic multi-format ingestion for CSV, TSV, TXT, Excel (.xlsx/.xls), and single-layer JSON with encoding detection
- Generates data profiles (--profile) detailing column data types, cardinality, missing rates, and sample distributions
- Sandbox execution for LLM-generated pandas data transformations with AST whitelisting and structured error suggestions
- Completely offline HTML rendering with bundled inline ECharts assets, hover tooltips, data zooming, and title editing
- Supports batch multi-chart generation and multi-file union or join merging
Useful For
- Visualizing sales, financial, or operational tabular data directly within DeepSeek Harness workspace sessions
- Allowing DSH agents to automatically inspect unfamiliar datasets and choose optimal chart types without manual prompt guidance
- Generating standalone interactive HTML report artifacts containing embedded statistics and agent analysis annotations
Who It Fits
- DeepSeek Harness users needing automated visual data analysis
- Data analysts and developers wanting offline interactive chart reports
- AI agents automating exploratory data analysis (EDA) and reporting workflows
Documented Limitations
- Requires a local Python 3.11+ environment with dependencies (pandas, numpy, openpyxl, xlrd)
- Recommended file size under 50 MB (hard upper limit around 100 MB)
- Does not support streaming data, direct database connections, or nested JSON structures deeper than 1 level
- City/county level geographic map visualizations require providing custom GeoJSON files via --geo-path
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 0 runtime, 4 development, 1 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.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
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
- hherosoul/dsh-smart-charts
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 0595787 · 2026-10-10
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
- 17GitHub stars
- Forks
- 1
- Open issues
- 0
- Last commit
- 2026-09-29
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Agent skill and plugin that transforms concise Markdown drafts into standalone, visual single-page HTML explainers and videos.
View plugin →Agent skill for DeepSeek Harness that turns ideas, plans, and codebases into interactive architecture diagrams.
View plugin →A multi-host method pack for architecture-aware, evidence-verified AI coding workflows in DeepSeek Harness.
View plugin →DeepSeek Harness Cordis plugin bundling 87 reverse engineering, security research, and CTF skills.
View plugin →