Menu

Individual skill

credit-risk-committee-analyst

0upvotes

Analyze bank and credit-union loan portfolios for lending-committee or credit-risk-committee decision packages. Use this skill whenever a user asks about branch risk ratings, loan portfolio regrades, watch-list stress testing, lending allocations, credit-union segment posture, concentration analysis, competing credit decisions, or FDIC/NCUA benchmark comparisons. Also trigger when the task involves a shared credit office API, branch loan data, credit policy rules, or committee-ready JSON outputs for any financial-institution workflow—even if the user doesn't use the exact words "committee" or "credit risk."

experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_011/fewshot/cc/fewshot_attempt_01/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
Local scripts
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

# Credit Risk Committee Analyst

This skill guides analysis of bank and credit-union lending portfolios for committee decision packages. The target environment provides a shared credit office REST API with branch data, loans, applications, sector exposures, policies, and FDIC/NCUA benchmark data. The solver reads raw data from the API, applies policy rules algorithmically, and produces structured committee-ready JSON answers.

## Core workflow

Every committee task follows the same general pattern:

1. **Read the task prompt** to identify the target entity (branch_id or segment_id), the review type, and the required output template from `input/payloads/answer_template.json`. The template defines the exact JSON shape, enum choices, precision, and ordering rules.

2. **Fetch the manifest** from `{TASK_ENV_BASE_URL}/api/manifest` to confirm available endpoints and benchmark versions. The manifest is the authoritative source for what data exists.

3. **Fetch policy data** from `{TASK_ENV_BASE_URL}/api/policies`. The policy document contains every rule you need: risk-rating thresholds, CDFI factor scoring tables, CRE weighted score weights and classes, stress formulas, concentration rules, and watch-list action definitions. Always read `references/policy-rules.md` alongside the raw policy JSON to understand how to apply each rule section.
Back to top