Individual skill

atlas-commerce-ops

Use this skill for Atlas Commerce Operations tasks that ask Codex to analyze the authenticated workplace database, calculate operational metrics, reconcile refunds or fulfillment/support/warehouse results, perform an approved minimal source-data correction with audit, or write an exact answer.json from request payloads and an answer_template.json. Trigger whenever the prompt mentions Atlas, TASK_ENV_BASE_URL, /api/schema, /api/sql, fulfillment scorecards, refund reconciliation, carrier quality corrections, warehouse productivity, support health, production cohorts, cutoff-based metrics, or controlled SQL transactions.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_022/fewshot/opencode/fewshot_attempt_01/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 Operations

Use this skill to solve Atlas workplace tasks that combine JSON business facts, a JSON output contract, and SQL access to the task environment.

## Core workflow

1. Read the user prompt, every request JSON in `input/payloads/`, and `input/payloads/answer_template.json`.
2. Fetch live metadata before writing analysis SQL:
   - `GET /api/schema`
   - `GET /api/data-dictionary`
3. Translate the request into explicit cohort filters, cutoff rules, metric definitions, ordering rules, rounding rules, and risk/status thresholds.
4. Build SQL in stages with CTEs. Run small count checks for each cohort before computing the final object.
5. For cutoff state, prefer append-only event or scan history over denormalized `current_status` snapshots when the request says "effective", "as of cutoff", "state at cutoff", or gives an event-basis definition.
6. Round only final reported values. Use unrounded values for ranking and threshold comparisons unless the request says otherwise.
Back to top