Individual skill
atlas-ops-analyst
Operational analytics against the Atlas Commerce Operations REST API. Query read-only business data, apply controlled canonical corrections, and verify audit trails. Use when the task environment provides an Atlas API base URL with /api/schema, /api/data-dictionary, /api/sql, /api/sql/transaction, or /api/correction-audit endpoints and the prompt involves querying or correcting a shared commerce database spanning orders, shipments, refunds, payments, carrier scans, support cases, warehouse work, inventory, campaigns, accounts, products, FX rates, or facilities.
experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_022/fewshot/deepagents/fewshot_attempt_01/SKILL.md
Source commit 5082a777379156a048881e94940d640702e5e09a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- 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.
- agent Repository topic
- ai Repository topic
- benchmark Repository topic
- llm Repository topic
- self-evolving Repository topic
- self-learning Repository topic
- skills Repository topic
- data Derived category
- operations Derived category
- security Derived category
- data-databases Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 9,763 bytesreferences/schema.mddoc · 9,437 bytes
Read excerpt
# Atlas Ops Analyst
## API Endpoints
[Credential-related source omitted]
- `GET /api/schema` -- Full DDL for every table and index. The response contains `tables` (each with `name` and `ddl`) and `indexes`.
- `GET /api/data-dictionary` -- Column descriptions, conventions (timestamps, dates, money), and production-exclusion flags. The response contains `conventions` and `tables` with per-column `name`, `type`, `nullable`, and `description`.
- `POST /api/sql` -- Read-only SQL. Send a JSON body with `{"query": "<SQL text>"}`. Returns a `rows` array of objects and `row_count`. Accepts only SELECT statements.
- `POST /api/sql/transaction` -- Controlled write. Send `{"transaction": "<SQL text>"}`. The SQL may include UPDATE statements that modify canonical fields on specific tables (carrier_scans, inventory_movements). Returns `{"affected_business_rows": N, "audit_rows": N}`.
- `GET /api/correction-audit` -- Returns all correction audit records. The response contains `columns` (field names) and `rows` (array of arrays). Use this to verify a correction after applying it.
## Workflow