Individual skill
finance-ops-reporting
Solve Crescent Finance Ops JSON reporting tasks from prompt, environment_access.json, request_memo.json, and answer_template.json. Use when asked to produce branch close, regional, compensation, payroll, or forecast reports from the staged API and return one strictly shaped JSON object.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_009/fewshot/codex/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
- finance 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 · 1,514 bytesSKILL.mdcore · 1,514 bytesagents/openai.yamlasset · 270 bytesreferences/reporting-playbook.mddoc · 4,803 bytes
Read excerpt
# Finance Ops Reporting
## Workflow
1. Read `payloads/answer_template.json` first and treat it as the contract for keys, nesting, rounding, and list order.
2. Read `payloads/request_memo.json` to identify the report family, target ID, comparison periods, scenario, and any special treatment flags.
3. Read `payloads/environment_access.json` for `base_url` and the allowed endpoints. Use only those endpoints, plus `GET /api/manifest` when you need an index of branches, ensembles, productions, or other public entities.
4. Query the smallest set of objects needed. Prefer exact IDs from the memo; otherwise map names through the manifest or the relevant collection endpoint.
5. Assemble the final object with the exact keys, nesting, and list order from the template. Do not add prose or helper fields.
6. Round currency to 2 decimals. Round percentages and ratios to 4 decimals. Keep intermediate values unrounded until the end.
7. Reconcile totals, rankings, and counts against the source data before emitting the answer.
## Report Families