Individual skill
atlas-commerce-ops-analytics
Analyze Atlas Commerce Operations workplace tasks that provide request payloads, answer templates, and an authenticated Atlas service. Use for cutoff-consistent fulfillment scorecards, refund reconciliation, carrier scan quality corrections, warehouse productivity reviews, support health reviews, and similar operational analytics requiring exact answer.json output through the schema, data dictionary, SQL, transaction, and correction-audit APIs.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_022/fewshot/fewshot_attempt_03/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
- 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.
- 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
- productivity 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
Read excerpt
# Atlas Commerce Ops Analytics
## Required Workflow
1. Read the user prompt, every file under `input/payloads/`, and the output template before querying. Treat the request payload as the source of business scope, cutoff timestamps, rounding, ranking, and risk rules.
2. Resolve the service URL and token only from the task environment instructions. Fetch `/api/schema` and `/api/data-dictionary` before writing SQL.
3. Use `POST /api/sql` for read-only analysis. Send parameterized SQL as `{"sql":"...","params":[...]}`. Use `POST /api/sql/transaction` only when the request explicitly authorizes a correction.
4. Build SQL in CTEs that expose the population, effective facts, metric rows, ranked rows, and final checks separately. Do not rely on convenience snapshot columns when the request asks for state "at cutoff"; derive state from effective events or scans at or before that cutoff.
5. Keep timestamps as UTC ISO text and apply request boundary language exactly. Inclusive windows use `>= start` and `<= end`; strict lateness such as "due before cutoff" uses `< cutoff`.
6. Round only final displayed rates or money values. Rank by unrounded values, then by the stated tie-break key.
7. Check the SQL response `truncated` flag. If true, narrow the query, page by stable ID ranges, or aggregate into JSON/list values so no required ID is lost.
8. Validate the answer against the template exactly: required keys only, array length and ordering rules, unique ID arrays, enum values, and numeric precision. Write only the JSON object to `answer.json`.
## Effective Records