Menu

Individual skill

asteria-fleet-data-quality

0upvotes

Reconcile Asteria Fleet Data Quality Hub audit tasks and produce strict JSON answers from a task prompt, case scope, answer contract, source snapshots, aliases, conversions, FX, contacts, fuel/freight transactions, and maintenance events. Use when asked to certify or audit Asteria fleet contact readiness, partner/contact mastering, fuel or freight normalization, accrual/ledger routing, source-retention panels, or maintenance-history integrity.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_021/reflect-3/reflect-3_attempt_03/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Instructions only
Last checked
Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
121
Repository last updated
Oct 29, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Asteria Fleet Data Quality

## Core Workflow

1. Read the prompt, `case_scope`, `answer_template`, and the supplied environment access file before querying data.
2. Use the catalog and schema to identify the relevant logical views, stable business keys, source-snapshot fields, reference rows, unit conversions, and FX fields.
3. Pull the complete in-scope dataset. Check pagination or truncation explicitly; do not rely on sample rows.
4. Resolve source snapshots before calculating business metrics:
   - Filter snapshots by the requested collection and cutoff/as-of period.
   - Prefer certified authoritative evidence for overlapping logical records.
   - When a logical record appears in multiple snapshots, retain the authoritative occurrence and report the duplicate group from all raw occurrences.
   - When a logical record exists only in a non-authoritative snapshot, keep it with a distinct source-basis disposition rather than dropping it silently.
5. Build the answer from the output contract, not from memory. Preserve required key names, enum values, ordering, uniqueness, numeric precision, and `additionalProperties` restrictions.
6. Validate all count partitions: raw vs logical vs duplicate rows, valid plus quarantined records, mutually exclusive readiness buckets, exception counts, and ranked limits.
Back to top