By DQE-SOFTWARE
Data quality suite for Claude Code by DQE Software. Audit CSV files across 6 DQE dimensions, run end-to-end campaign data quality workflows (email/phone validation + deduplication via DQE One Server MCP), and manage DQE processes directly from Claude Code.
CSV data quality audit — analyses 6 DQE dimensions (completeness, invalid dates, duplicates, anomalies, broken relationships, formats) and generates a branded standalone HTML audit report (with Next Steps + CTA), and optionally a project manager guide with --pm. Use when the user asks for an audit, quality analysis, DQE analysis, or provides a CSV file to analyse. Trigger with /dqe-audit <path/to/file.csv>
End-to-end campaign data quality workflow. Audits contact data (emails, phones, names, addresses) and cleans it via the dqe-one MCP server — email validation, phone validation, deduplication — producing a campaign-ready contact count. Data can come from a local CSV file OR from any remote source accessible via the DQE One Server: Salesforce, Microsoft Dynamics, PostgreSQL, BigQuery, Snowflake, or SFTP. Replicates the VivaTech demo scenario in Claude Code. Use when the user has contact data to clean before a marketing campaign, or asks for a full DQE flow.
Guided creation of a DQE deduplication process on the dqe-one MCP server. Walks the user through selecting a data source (CSV file, Salesforce, Dynamics, PostgreSQL, BigQuery, SFTP), choosing a ruleset, mapping fields, and triggering the first run. Use when the user wants to set up deduplication or when dqe-campaign needs to create a dedup process.
DQE One Server — workspace overview. Lists processes, recent runs, files, and rulesets from the connected dqe-one MCP server. Use when the user asks to see their DQE processes, runs, datasets, or wants a summary of their workspace state.
Trigger a DQE process execution and follow its status. Lists available processes so the user can pick one, confirms the choice, calls run_process, and polls list_runs for the result. Use when the user wants to run, execute, or launch a DQE process.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
5 skills for data quality directly inside Claude Code. Audit CSVs locally, or run a full end-to-end campaign data quality workflow — email validation, phone validation, deduplication — through the DQE One Server via MCP.
Note: the plugin is named
dqe-qualityin the marketplace. The GitHub repository is namedclaude-quality.
Drop a CSV and get a professional audit report. Or go further: connect to the DQE One Server and let Claude Code run the full data quality pipeline on your contact list — validation, deduplication, campaign-ready count — without leaving your terminal.
Data engineers and analysts who need a fast, reproducible quality baseline on any CSV before loading it into a pipeline or CRM.
Marketing and campaign teams who need to clean a contact list fast — validate emails, fix phone numbers, remove duplicates — before launching a campaign.
Project managers and consultants who need ready-to-share deliverables — an audit report with actionable next steps and, optionally, an internal treatment plan — without opening a BI tool.
DQE Software teams who audit client data files and need branded, multilingual reports that tie findings directly to DQE service recommendations.
| Skill | Invocation | Requires MCP | Description |
|---|---|---|---|
dqe-audit | /dqe-quality:dqe-audit <file.csv> | No | Full 6-dimension audit → branded HTML report |
dqe-campaign | /dqe-quality:dqe-campaign <file.csv> | Optional | Local audit + server-side email/phone/dedup → campaign-ready count |
dqe-list | /dqe-quality:dqe-list | Yes | Workspace overview: processes, runs, files, rulesets |
dqe-dedup | /dqe-quality:dqe-dedup | Yes | Guided deduplication process creation |
dqe-run | /dqe-quality:dqe-run [name] | Yes | Trigger a process and follow its status |
The three MCP skills (dqe-list, dqe-dedup, dqe-run) require a running DQE One Server instance configured as an MCP server. See DQE One Server — MCP setup.
/plugin install dqe-quality
The plugin is registered as
dqe-qualityin the marketplace. The underlying GitHub repository isDQE-SOFTWARE/claude-quality.
Open PowerShell and run:
irm https://raw.githubusercontent.com/DQE-SOFTWARE/claude-quality/main/install-desktop.ps1 | iex
This downloads the skill ZIP from GitHub, extracts it, and copies it to %USERPROFILE%\.claude\skills\. Restart Claude Code desktop when done.
Execution policy error? Run
Set-ExecutionPolicy -Scope CurrentUser RemoteSignedfirst, then retry.
Open Terminal and run:
curl -fsSL https://raw.githubusercontent.com/DQE-SOFTWARE/claude-quality/main/install-desktop.sh | bash
This downloads the skill ZIP from GitHub, extracts it, and copies it to ~/.claude/skills/. Restart Claude Code desktop when done.
git clone --depth 1 https://github.com/DQE-SOFTWARE/claude-quality.git
bash claude-quality/install.sh
# Local audit — English HTML report
/dqe-quality:dqe-audit ~/data/contacts.csv
npx claudepluginhub dqe-software/claude-quality --plugin dqe-qualityA growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review