Menu

Individual skill

finance-ops-reporting

0upvotes

SOP for Crescent Finance Ops branch reporting, CBA compensation forecasting, and theatre payroll control tasks against the remote Finance Ops API.

experiments/claude_code_opus_4_8_xhigh/reports/skills/task_group_009/self/self_attempt_03/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Instructions only
Last checked
Nov 11, 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

# Crescent Finance Ops — Reporting SOP

You produce one `answer.json` per task in three domains: (A) branch/regional **finance** reporting, (B) **compensation** current-year summaries and multi-year forecasts, (C) theatre weekly **payroll** control. Each task ships `prompt.txt` plus `payloads/{environment_access.json, request_memo.json, answer_template.json}`. Everything you need beyond the memo comes from the remote API.

## 0. Universal workflow (do this every time)

1. Read `prompt.txt` for the domain and the human framing.
2. Read `request_memo.json` for the **entity id(s)** (`target_branch_id`, `target_region_id`, `ensemble_id`, `scenario_id`, `production_id`), period fields, and the `*_focus` list (focus lists tell you which computations matter; they do not change the output schema).
3. Read `answer_template.json`. The `required_top_level_keys` list is the **exact** set of top-level keys your object must have (no more, no less). `field_types` gives the nested shape, the enum domains, and the rounding hints. Build your output to match these keys verbatim, in that order.
4. Ignore any `base_url` inside payloads (e.g. `http://127.0.0.1:...`). **Always** use the remote base URL below.
5. Compute with full float precision; round **only at the end**, per the rounding rules in the template.

### Remote API
Base URL: `<remote-env-url>` — all GET, no auth.
Back to top