# @6171/json Snapshot Auditor

> Audit JSON pipeline snapshots for parse validity, scalar-field coverage, run-to-run diffs, threshold-based signals, and explainable zero-signal outcomes. Use when debugging data collection or analysis pipelines that complete without producing conclusions.

- Skill: `starchild-ai-agent/6171-json-snapshot-auditor` (Agent Skill)
- Install (CLI): `npx skillmds@latest add starchild-ai-agent/6171-json-snapshot-auditor`
- Raw SKILL.md: https://api.skillmd.com/api/skills/starchild-ai-agent/6171-json-snapshot-auditor/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: starchild-ai-agent (https://skillmd.com/u/starchild-ai-agent)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/starchild-ai-agent/6171-json-snapshot-auditor

---


# JSON Snapshot Auditor

Use this skill when a data pipeline produced a snapshot but the result is empty, suspicious, or hard to explain.

## Workflow

1. Preserve the raw snapshot before transforming it. Parse it as JSON and report syntax errors with the exact location when available.
2. Separate three layers: collection health (did records arrive?), data quality (are required/scalar fields present?), and decision output (did records cross configured rules?). Never infer a quiet market or empty result from collection success alone.
3. Flatten nested objects to dotted paths for coverage checks. Treat arrays as records when they represent events; avoid counting container nodes as scalar fields.
4. Compare the current flattened snapshot with the previous run by path. Report added, removed, and changed values, including an explicit “no changes” result.
5. Apply thresholds from the snapshot or caller configuration and list both passing and rejected candidates. A zero-signal result is valid output only when the raw snapshot, rule set, and rejection reason are retained.
6. Return a compact audit with: parse status, collection count, scalar-field count, changed-field count, signal count, warnings, and a decision log.

## Interpretation

- Valid JSON + records present + zero signals means the decision layer is quiet, not that the pipeline failed.
- Missing records or too few scalar fields is a data-quality warning and should lower confidence.
- Threshold changes can explain a changed signal count even when source records are unchanged; diff the rule paths explicitly.
- Never invent missing fields or silently coerce malformed values.

## Output contract

Use stable keys: `parse`, `collection`, `quality`, `diff`, `signals`, `warnings`, `decision`. Keep raw input available for reproducibility and avoid sending it to external services unless the user explicitly asks.