Individual skill
credit-office-json
Use this skill for credit office committee tasks that require JSON answers from the shared public API, including branch loan regrades, watch-list stress packets, pending application allocation, competing CRE decisions, FDIC or NCUA benchmark variance, concentration flags, CDFI factor scores, and schema/enums in answer_template.json. Trigger whenever the prompt mentions TASK_ENV_BASE_URL, branch_id, segment_id, credit policy, lending committee, or committee-ready JSON from a credit-office API.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_011/fewshot/cc/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
- engineering 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 · 4,599 bytesSKILL.mdcore · 4,599 bytesSKILL.mdcore · 4,599 bytesreferences/credit-office-rules.mddoc · 6,880 bytesscripts/credit_office_tools.pyruns · 25,759 bytes
Read excerpt
# Credit Office JSON Solver
Use this skill when a task asks for a committee-ready JSON answer from the shared credit office API. These tasks are data-reconciliation problems: fetch the public records, apply the public policy formulas, and shape the answer exactly to `input/payloads/answer_template.json`.
## Required Workflow
1. Read the prompt and `input/payloads/answer_template.json` completely before fetching data.
2. Use the API base URL from the task runner, usually `TASK_ENV_BASE_URL`; if the prompt gives a literal base URL, use that. Do not read local task-environment data files.
3. Fetch `GET /api/manifest` and `GET /api/policies` first. Treat policy payloads as authoritative if they differ from this skill's remembered formulas.
4. Fetch only public endpoints needed by the prompt:
- Branch tasks: `/api/branches/{branch_id}`, `/api/branches/{branch_id}/metrics`, `/api/branches/{branch_id}/loans`, `/api/branches/{branch_id}/sector-exposures`, and `/api/branches/{branch_id}/applications` as applicable.
- Bank benchmark tasks: `/api/benchmarks/fdic/q4-2024`.
- Credit-union segment tasks: `/api/credit-union-segments/{segment_id}` and `/api/benchmarks/ncua/q1-2025`.
5. Build a small scratch derivation table before composing the final JSON. Check totals, ratios, ordering, and enum spellings against the template.