dsh-data-quality

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

dsh-data-quality

Deterministic data profiling, cleaning, and verification for DeepSeek Harness.

• 1024 store channel: npm i -g dsh1024 once, then dsh1024 plugin --profile web add dsh-data-quality (counts toward the deepseek1024.com install ranking).










Deterministic data profiling, cleaning, and verification for DeepSeek Harness.

All computation is plain TypeScript in the harness process — the model never does the math. A ctx.dataQuality capability seam (Service Definition / local Provider / tool Consumers) exposes three model tools plus a frozen cross-plugin citation-checking contract.

[English](README.md) · [简体中文](README-zh.md) · [Español](README-es.md) · [Português](README-pt.md) · [हिन्दी](README-hi.md)

dsh plugin --profile <name> add dsh-data-quality

📖 Ecosystem knowledge base — measured data, not marketing: plugin development guide · plugin-selection data · maintenance criteria.

<!-- star-cta -->

Install & uninstall

dsh plugin --profile web add dsh-data-quality      # install (npm) — or the forms above
dsh plugin --profile web remove dsh-data-quality   # uninstall

⭐ 如果它帮到了你

这个插件是 DSH 插件家族的一员（95 个，全部 Apache-2.0）。如果你在用，给个 star —— 它不会解锁任何功能，但会让下一个人在搜索里更容易找到它。

English: part of a 95 plugin family for DeepSeek Harness. If it is useful, a star helps the next person find it — nothing is gated behind it.

What is dsh-data-quality?

Deterministic data profiling, cleaning, and verification for DeepSeek Harness.

Workflow overview: question → sealed sources → report. The examples below use the real command surface.

Comparison

fixtures/dirty-fund-holdings.csv (10 rows x 6 columns) · 5 determinable dimensions · run locally

Compatibility

Component · Version

DeepSeek Harness · dsh-v0.2.1-alpha.1 (adapted 2026-10-04): the peer range now admits the alpha.2 line; there Session.append's third parameter exists only for surface-eligible types and is a SurfaceIntent, so the audit gate still skips and the storage-domain report stays the durable copy. Verified 2026-09-24 (dual typecheck rulers + full test suite green).

Node.js · ^22.19.0 \ · \ · >=24.0.0

Package manager · pnpm@11.7.0

Platform · Windows / macOS / Linux (host-only plugin)

What you get

• ctx.dataQuality service — a Cordis service other plugins may optionally consume (inject = ['dataQuality']). Besides the three dataset operations behind the tools, it implements the frozen verifyCitations(request) contract: verify that numbers/strings cited in a document match a dataset snapshot, with relative-tolerance numeric comparison and verified / mismatch / not-found / unverifiable statuses.
• data_profile tool — dataset profiling: row/column counts, inferred column types (number/date/boolean/string/empty/mixed), missing rates, unique counts, numeric distributions (min/max/mean/median/p25/p75), IQR outlier counts, mixed-type suspicion notes, and full-table sha256 content-hash duplicate detection with the duplicate rate and a bounded sample of duplicate row indexes. Adds a deterministic DAMA six-dimension scorecard (completeness, uniqueness, validity, consistency, timeliness, accuracy — accuracy is reported undetermined without a declared schema, never fabricated). Optional deterministic systematic sampling for large files.
• data_clean tool — ordered declarative cleaning rules: dedupe (by column group), fill-missing (constant/mean/median/forward), coerce-type (number/date/boolean; failures counted and set to missing), normalize-unit (e.g. 万/亿 suffixes to base units), trim, map-values (enum mapping). Returns a per-rule audit log, a pre-delivery contract validation summary (dedupe before/after, uniqueness, non-null and type regressions), and a bounded preview; writes the cleaned dataset only when outputPath is given, and never overwrites the source.
• data_verify tool — declarative verification rules: not-null, unique, range, regex, enum, cross-column (e.g. startDate < endDate), freshness (date column within N days of a reference date). Per-rule pass/fail with capped failing-row evidence; an overall failure is a normal passed: false result, not a tool error.
• data_report tool — read persisted reports back from the data_quality storage

…(truncated)