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

Read pinned source

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.

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

# 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.
Back to top