Desk Data Auditor — Data & AI agent for Claude Code
Check the freshness, completeness and internal consistency of the artifacts on disk before anyone reports from them.
How to install Desk Data Auditor
Installs to ~/.claude/agents/iman-agent-driven-options-desk-and-skills-desk-data-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Iman/agent-driven-options-desk-and-skills/HEAD/.claude/agents/desk-data-auditor.md -o ~/.claude/agents/iman-agent-driven-options-desk-and-skills-desk-data-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What Desk Data Auditor does
name: desk-data-auditor description: Check the freshness, completeness and internal consistency of the artifacts on disk before anyone reports from them. Use before publishing or acting on desk output, after a scheduled run, when numbers look surprising, or when the user asks whether the data is any good. tools: Read, Bash, Grep, Glob
You audit the artifacts, not the market. Everything you need is in the artifact directory and every artifact carries its own meta block.
The checks, i
Alternatives in Data & AI
- Credential Hunter — Autonomous credential-attack pipeline runner 4.5k ★
- Identifier Validator — Use this agent practively whenever new identifiers (PMIDs, DOIs, database IDs, ontology term IDs) are introduc 163 ★
- Blind Fact Check — Zero-context blind review of a single chapter for factual errors and AI-template traces 90 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Draft Reviewer
Review AND FIX any draft for AI slop, writing craft, and voice consistency. Runs three quality checks, then ap
DB Check
Validate database state — pending migrations, schema consistency, missing indexes.
Impl Serialization
Reviews implementation plans from a serialization and data format perspective. Use when evaluating serde usage
9remote
Long-running AI coding sessions keep working after you leave the desk, but checking on them from a phone usual
Performance Director
Cinema Studio performance director. Acting direction for AI characters: emotional beats, subtext, micro-expres
Task Reviewer
Strict quality reviewer for implementation task files. Validates completeness, self-containment, and clarity f
Related Skills
Quality Scoring
Skill for computing a quality score per wiki page — structural completeness, citation health, freshness, and r
Docs Verify
Verify documentation quality, links, freshness, and consistency: $ARGUMENTS
Docs Consistency
Review user-facing documentation for accuracy, consistency, and completeness