DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-data-quality

Deterministic data profiling, cleaning, and verification tools and Cordis service for DeepSeek Harness.

UI & ProductivityDeveloper ToolsSecurity & PolicySkills & Workflows
33GitHub Stars0ForksUpdated2026-09-19

Install

$ dsh plugin --profile web add dsh-data-quality

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.

source-grounded
dsh-data-quality provides deterministic, in-process dataset profiling, cleaning, and verification for DeepSeek Harness. Executing in TypeScript directly within the harness process, it supplies model tools (data_profile, data_clean, data_verify, and data_report) alongside a ctx.dataQuality service seam with a cross-plugin verifyCitations contract, durable reports stored in a JSON domain, and DAMA six-dimension data scorecards.

Key Capabilities

  • Dataset profiling with column type inference, missing rates, duplicate detection, and DAMA scorecards via data_profile
  • Ordered rule-based data cleaning (deduplication, missing-fill, type coercion, unit normalization, trimming, value mapping) via data_clean without overwriting sources
  • Rule-based data verification (not-null, unique, range, regex, enum, cross-column, freshness, metric expectations) via data_verify
  • Persistent run reporting and HTML export via data_report against the data_quality storage domain
  • Cross-plugin citation verification service (ctx.dataQuality.verifyCitations) with tolerance-based numeric comparison

Useful For

  • Auditing and profiling CSV, TSV, JSON, and JSONL datasets before running analysis workflows
  • Cleaning tabular data deterministically without relying on LLM arithmetic
  • Validating structured outputs and fact-checking document citations against underlying dataset snapshots

Who It Fits

  • DeepSeek Harness developers working with structured data and data quality pipelines
  • AI agents requiring deterministic data preparation and data integrity checks
  • Plugin authors needing citation verification services

Documented Limitations

  • Strict parsing requirements for numbers and dates without delimiter auto-detection or SQL support
  • Enforces hard row and file size limits (default 200,000 rows and 64 MiB)
  • JSON datasets for tools must be flat tabular arrays of objects
  • Overwriting input source files is explicitly forbidden

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

No automated security signals have been published yet.

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
PerryLink/dsh-data-quality
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
df57f54 · 2026-09-19

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
33GitHub stars
Forks
0
Open issues
1
Last commit
2026-09-19
Last release
2026-09-18
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app