Individual skill
crescent-finance-ops
Solve Crescent Arts Collective finance, compensation, and payroll reporting tasks by calling the Crescent Finance Ops API and applying documented computation rules from three business domains.
experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_009/fewshot/naive/fewshot_attempt_02/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
- 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 · 16,031 bytes
Read excerpt
# Crescent Finance Ops Solver
When a task references Crescent Arts Collective and the "Finance Ops environment," work through the following workflow to produce a single JSON answer from the active API data.
## Workflow
1. **Read the task context.** Open `payloads/environment_access.json` to get the `base_url` and list of `available_endpoints`. Open `payloads/request_memo.json` for the target entity IDs, reporting periods, scenario names, and any `memo_note` hints. Open `payloads/answer_template.json` for the required top-level keys, field types, rounding rules, and ordering conventions. The template's `description` field often contains critical rounding and ordering instructions.
2. **Fetch the data.** Call every endpoint listed in `environment_access.json`. The API is at the `base_url`, no authentication required. All endpoints return JSON arrays or objects. Call them in parallel when possible.
Optional discovery: `GET /api/manifest` returns a summary of all entities (branches, ensembles, productions) and record counts. This is never required but can confirm data completeness.
3. **Compute the answer.** Apply the domain-specific rules below. Every currency value must be rounded to 2 decimal places. Every percentage or ratio must be rounded to 4 decimal places. Follow the template's field ordering and list-sorting instructions exactly.