Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/eddmpython/dartlab/creditnpx skills add eddmpython/dartlab --skill creditgit clone --depth 1 https://github.com/eddmpython/dartlabWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.11881 |
| Opus 5 | $0.00000 | $0.05940 |
| Sonnet 5 | $0.00000 | $0.02376 |
| Haiku 4.5 | $0.00000 | $0.01188 |
Grade A, and why
credit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 760 lines — stays where its author put it; the contents beside it link to each section on GitHub.
엔진 역할
credit 은 단일 기업의 부도 위험·재무 건전성을 독립 평가하는 L2 엔진이다. 79 개사 검증 (대기업 87% · 중대형 82%) 의 dCR 등급 (dCR-AA+ ~ dCR-D) 을 DART 공시 기반으로 산출한다. 외부 신평사 (Moody's · KIS · NICE) 가 반영하는 시스템적 중요성·정성 요소는 dCR 만으로 판단하지 않는다.
analysis 엔진의 안정성·현금흐름 축과 상호 보완. credit 종합 등급 → analysis 로 인과 깊게, 또는 analysis 안정성 점수 → credit 으로 외부 신평 보정 비교.
시간축 — 등급 이력 → 현재 dCR → 누적 PD
credit.migration 모듈이 등급 전이 행렬과 forward PD ladder 를 제공한다. 학술 기반 — CreditMetrics (J.P. Morgan, 1997) Cohort 접근, Basel III IRB 표준. 관측 등급 변경 → row-stochastic transition matrix → 행렬 거듭제곱 (M^h) → 등급별 h 년 누적 부도확률.
from dartlab.credit.scoring.migration import buildTransitionMatrix, forwardPdLadder
matrix = buildTransitionMatrix() # data/credit/transition.json 자동 로드
ladder = forwardPdLadder(horizons=(1, 3, 5))
# → DataFrame: rating · 1yPD · 3yPD · 5yPD (D 등급은 absorbing → PD = 1.0)
forecast precision = stable (observed transitions, 점예측 X). story 6 막에서 '등급 이력 회고 → 현재 dCR → n 년 누적 PD' 시간 narrative 결합.
공개 호출 방식
import dartlab
# 1. 가이드 (7 축 목록)
guide = dartlab.credit()
# 2. 종합 등급 (axis 미지정)
verdict = dartlab.credit("005930")
# → {"grade": "dCR-AA+", "score": 12.4, "axes": [...], "outlook": "안정적"}
# 3. 축 단독 (7 축 중 하나)
repayment = dartlab.credit("005930", "채무상환")
leverage = dartlab.credit("005930", "자본구조")
# 영문 alias 도 지원: dartlab.credit("005930", "repayment")
# 4. 상세 모드 — 모든 지표 시계열 + narrative
detailed = dartlab.credit("005930", detail=True)
# 5. Company 바인딩
c = dartlab.Company("005930")
verdict = c.credit()
repayment = c.credit("채무상환")
호출 동작
stockCode 미지정 → 7 축 가이드 DataFrame (axis · label · description · example · group).
stockCode 만 지정 → 종합 등급 dict — 3-Track 모델 (일반·금융·지주) + Notch Adjustment + CHS 시장 보정 적용. grade (dCR 등급), score (위험 점수 0~100), healthScore (100-score), axes (7 축 list), outlook (안정적·긍정적·부정적).
stockCode + axis → 해당 축 dict — axis (축 풀네임), score (해당 축 위험 점수), weight (가중치 %), metrics (개별 지표 name·value·score).
detail=True → 7 축 상세 + 모든 지표 시계열 (YoY · 5 년 평균) + narrative (한국어 인과 문장, story 블록 재료).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 760 lines · 0 tokens per session scan A 6f8bb123d406
credit is a skill published in the GitHub repository eddmpython/dartlab (209 stars, last pushed 10d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 11,881 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
build_workspace_app
This guide covers the full lifecycle of building, running, and serving a custom OpenBB Workspace application from an extension project scaffolded by openbb-cookiecutter. It assumes the project shell already exists (see the developextension skill for scaffolding instructions).
configure_mcp_server
This guide covers installation, configuration, authentication, tool discovery, prompt management, and client integration for openbb-mcp-server.
develop_extension
This is a complete guide for creating a new OpenBB Platform extension from scratch. Follow every phase in order. When the user says "build me an application that does X", use this guide to scaffold, implement, install, and verify the extension.
work_with_server
This guide explains how to call tools, interpret responses, discover capabilities, use prompts, and handle errors when interacting with an OpenBB MCP server.
fin-data-acquisition
根据REFINEDDESIGN.md中的变量定义，自动获取所需数据并生成可执行的回归分析脚本（Python/Stata）。.
alphasift
自动选股 Skill。Use when: 用户要按策略筛选 A 股、列出可用策略、运行双低/放量突破/均衡多因子/资金热度等选股，或保存运行并做 T+N 后验评估。通过 alphasift CLI 或 Python 接口输出候选股票列表。.