Individual skill

atlas-commerce-ops

Solve Atlas Commerce Operations workplace tasks that require authenticated SQL analysis, approved canonical data corrections, and strict answer.json output. Use for prompts mentioning Atlas Commerce Operations APIs, fulfillment scorecards, refund reconciliation, carrier scan quality corrections, warehouse productivity, support health, inventory, payments, orders, shipments, warehouses, support cases, or JSON answer templates.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_022/fewshot/codex/fewshot_attempt_02/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 6, 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

# Atlas Commerce Ops

## Core Workflow

1. Read the prompt, every request payload, and the answer template before querying. Treat the request payload as the business policy and the template as the output contract.
2. Resolve the task service URL and bearer token from the prompt or environment. Fetch `/api/schema` and `/api/data-dictionary` at the start of each task; table availability is part of the runtime contract.
3. Use read-only `POST /api/sql` for analysis. Use `POST /api/sql/transaction` only when the request explicitly approves a concrete correction.
4. Build SQL in named CTEs that mirror the request definitions: cohort, effective source rows, cutoff state, metric rollups, ranking, and final projection.
5. Prefer append-only event/source tables over denormalized `current_status` snapshots for any as-of cutoff calculation. Use snapshots only as a cross-check or when the request defines current-state semantics.
6. Round only final reported numbers, keep ordering based on unrounded values, and apply every template ordering/tie-break rule before limiting arrays.
7. Write exactly one JSON object to `answer.json`. Include no commentary, no extra fields, no omitted required fields, and use empty arrays only when the schema permits them.

Read [references/atlas_patterns.md](references/atlas_patterns.md) before writing SQL for Atlas Commerce Operations tasks.
Back to top