Agent skill
data-audit
Report on data completeness for the SPARTA QRA pipeline (Control -> URL -> Knowledge -> QRA). Queries DuckDB to show coverage percentages at each stage.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/data-audit
Metadata
Additional technical details for this skill
- project path
- /home/graham/workspace/experiments/pi-mono/.agent/skills/data-audit
- short description
- SPARTA data completeness auditor.
SKILL.md
Data Audit
Audits the SPARTA pipeline data coverage.
Usage
# Run full audit
.agent/skills/data-audit/run.sh
# Run for specific run ID (points to specific DB path if needed)
.agent/skills/data-audit/run.sh --run-id <run-id>
Logic
Connects to SPARTA DuckDB and calculates coverage for:
- Controls: Base set.
- URLs: Controls mapped to at least one URL.
- Knowledge: Controls mapped to URLs that have extracted chunks.
- QRA: Controls that have generated QRA pairs.
Visualization
After generating coverage data, offer to visualize via /create-figure:
# Pipeline coverage as stacked bar chart
create-figure metrics --input audit.json --output coverage.png --type bar --title "SPARTA Pipeline Coverage"
# Coverage heatmap by category
create-figure heatmap --input audit.json --output coverage-heatmap.png
When to offer: After presenting coverage percentages, ask: "Want me to chart the pipeline coverage?"
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?