Menu

Individual skill

atlas-commerce-ops

0upvotes

Solve Atlas Commerce Operations workplace tasks that require authenticated API schema discovery, SQL analytics, strict JSON answer files, cutoff-based operational metrics, production-account filtering, refund/fulfillment/warehouse/support reporting, or controlled canonical corrections through the Atlas workplace API.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_022/fewshot/deepagents/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

## Core Workflow

1. Read the user prompt, every file under `input/payloads/`, and the answer template before querying. Treat the request JSON as the business definition source and the template as the exact output contract.
2. Discover live context with `GET /api/schema` and `GET /api/data-dictionary`. Use the database, not memory, for table names, field names, and value sets.
3. Use `POST /api/sql` for analytical work. Do not mutate data unless the prompt explicitly requests a controlled correction.
4. For correction tasks, first prove the target with read-only SQL, compute the pre-change metrics, apply only the approved canonical-field change through `POST /api/sql/transaction`, then verify the changed row, the audit row, and the post-change metrics. If verification does not match the request's success rule, report the actual observed result and `NOT_APPLIED`.
5. Write only `answer.json`. It must have exactly the keys, nesting, precision, ordering, and enum values required by the template.

Use [`scripts/atlas_api.py`](scripts/atlas_api.py) when shell quoting gets in the way:

```bash
python skill/scripts/atlas_api.py schema
Back to top