Menu

Individual skill

credit-office

0upvotes

Build credit-office committee packets from a public credit office API. Re-derive risk ratings, score CDFI factors, apply stressed-DSCR shocks, check sector/CRE concentration against policy limits and FDIC/NCUA benchmarks, assign watch-list actions and decline reason codes, and produce committee-ready JSON from the answer template supplied with each task.

experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_011/fewshot/naive/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 Skill

This skill teaches the solver how to construct committee-ready credit packets from the public credit office API (`<TASK_ENV_BASE_URL>`). Every task supplies a prompt, an `input/payloads/answer_template.json` that defines the required output shape, and a target branch or segment. The API, the policy endpoint, and the template constrain every answer so that only the provided enums, identifiers, and shapes are used.

## Phase 1: Collect All Inputs

Before any computation, collect four sets of inputs in parallel.

### 1A. Read the answer template

Read `input/payloads/answer_template.json` first. It defines:
- Required top-level keys
- Field types, enums, allowed values, numeric precision
- Sort orders ("ascending loan_id", "descending exposure, then ascending loan_id", etc.)
Back to top