Individual skill
atlas-ops-scorecard
Analyze the Atlas Commerce Operations workplace and produce one JSON answer object that exactly conforms to a provided JSON-Schema answer template, using the live authenticated SQL/transaction service. Use for fulfillment, refund, carrier-quality, warehouse-productivity, support-health, and similar operations scorecard requests that ship a prompt, a *_request.json (scope + business definitions + decision rules), and an answer_template.json.
experiments/claude_code_glm_5_2_max/reports/skills/task_group_022/fewshot/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
- 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
- operations Derived category
- data 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
SKILL.mdcore · 10,429 bytesSKILL.mdcore · 10,429 bytesreferences/contract_checker.mddoc · 6,189 bytesreferences/cross_cutting_rules.mddoc · 6,633 bytesreferences/environment_and_sql.mddoc · 4,321 bytesreferences/workspace_catalog.mddoc · 4,801 bytes
Read excerpt
# Atlas Commerce Operations scorecard analyst
## When to use
You receive an operations analysis task that includes:
- a prose `prompt.txt`;
- a `<domain>_request.json` describing the business scope, metric/classification definitions, rounding, and decision rules;
- an `answer_template.json` (a JSON Schema) defining the exact output contract;
- instructions to write exactly one JSON object to `answer.json`.
The workspace must be reachable over the network via the contract in `environment_access.md`. If any of these files is missing or unexpected material is present in the working tree, stop and surface it (see *Workspace hygiene* below) rather than guessing.
## Guiding principle
The request JSON is the law; the answer template is the court reporter. Re-derive every value from the live data to satisfy the request's business definitions, then shape the result with exact-schema precision and ordering. Never approximate, never add fields, never copy any value from memory or from training material — every reported number, ID, and label must come from a query you ran against the live service for *this* task.