Menu

Individual skill

credit-office-committee-json

0upvotes

Use this skill whenever a task asks for committee-ready JSON from the shared credit office API, especially prompts mentioning <TASK_ENV_BASE_URL>, branch_id, segment_id, lending committee, credit risk, risk-rating migration, pending application allocation, CRE comparisons, watch-list stress, CDFI scoring, FDIC/NCUA benchmarks, sector exposures, or an answer_template.json.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_011/fewshot/cc/fewshot_attempt_02/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 Committee JSON

Use this skill to solve credit-office API tasks that require controlled JSON output. These tasks are calculation-heavy: the main risk is not prose quality, it is missing an endpoint, using the wrong denominator, drifting from the template enum values, or rounding/sorting inconsistently.

## Core Workflow

1. Read the user prompt and `input/payloads/answer_template.json` before calculating.
2. Extract the target identifiers and constraints: `branch_id`, `segment_id`, application IDs, review/as-of date, current-rating cutoff, benchmark family, required output keys, enum choices, precision, and ordering rules.
3. Resolve the API base URL from the runner-provided `<TASK_ENV_BASE_URL>` value, environment variable, or staged environment access file. Use only public API endpoints.
4. Fetch `GET /api/manifest` and `GET /api/policies` first. Then fetch only the target data needed for the prompt:
   - Branch: `/api/branches/{branch_id}`, `/metrics`, `/loans`, `/sector-exposures`, `/applications`
   - Benchmarks: `/api/benchmarks/fdic/q4-2024`, `/api/benchmarks/ncua/q1-2025`
   - Credit-union segment: `/api/credit-union-segments/{segment_id}`
5. Do calculations with code, `jq`, or the bundled helper. Avoid mental arithmetic for ratios, capacity, exposure aggregation, stress results, and score weighting.
Back to top