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/industrynpx skills add eddmpython/dartlab --skill industrygit 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 | $0.05834 |
| Opus 5 | $0.00000 | $0.02917 |
| Sonnet 5 | $0.00000 | $0.01167 |
| Haiku 4.5 | $0.00000 | $0.00583 |
Grade A, and why
industry 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
엔진 역할
industry 는 단일 종목을 밸류체인 공정 단계 와 peer 그룹에 연결하는 L2 분석엔진 (산업 매퍼) 이다. 산업 분류 (taxonomy.json) 와 종목→공정 매핑 (nodes.json) 을 데이터로 들고 있고, 매칭/집계/lifecycle 파이프라인이 분석 표면을 만든다. 분류체계는 운영자가 JSON 직접 편집해 갱신.
회사 재무 인과는 analysis, 부도 위험은 credit, 시장 매크로는 macro, 정량 가격 신호는 quant, 횡단 후보 발굴은 scan (L1.5) 이 담당. industry 는 산업 컨텍스트 분석 을 다른 L2 엔진과 동등한 도메인 격리 로 제공한다 — 다른 L2 를 직접 import 하지 않고 결합은 L3 조합기 story 가 한다.
공개 호출 방식
import dartlab
# 1. 산업 목록 가이드
guide = dartlab.industry()
# → DataFrame: 산업ID · 산업명 · 공정수
# 2. 특정 산업의 공정·종목
nodes = dartlab.industry("semiconductor")
# → DataFrame: 공정 · 공정명 · 종목코드 · 종목명 · 역할 · 위치
# 3. 공정 단계 필터
fab_only = dartlab.industry("semiconductor", stage="fab")
# 4. 공정별 매출/영업이익 집계 (최근 관측 연간 사업연도)
summary = dartlab.industry("semiconductor", summary=True)
# → DataFrame: stage · 공정명 · 매출(조) · 영업이익(조) · 기업수 · 영업이익률(%) · coverageRatio
# 5. 연도별 공정 매출 추이
timeline = dartlab.industry("semiconductor", timeline=True)
# 6. 단일 기업의 산업 위치 (Company-bound)
c = dartlab.Company("005930")
position = c.industry()
# → dict: chainId · chainName · stage · stageLabel · confidence · matches · products · peers
# 7. 전 시장 상세 자산은 명시적으로만 계산
detail = c.industry(detail=True)
# → 위치 + 섹터 분포 · 이익풀 · 관계 · 집중도
강행 호출 룰 (agent 답변 품질 회귀 차단)
- 단일 종목 산업 질문 =
Company.panel("IS").data.industryBadge1 회 인용 (Track E 자동 부착).EngineCall("industry")별도 호출 금지 — industryBadge 가 이미 industryName · stageName · phase · peers · confidence 완전 형태. - 여러 종목 / 산업 전체 질문은
EngineCall(apiRef="industry", args={...})1 차 — RunPython 직접 industry parquet 로드 금지. - 본문 안 산업명·phase·peers 에
[tableRef:...]inline 표기 필수. lifecycle phase (도입/성장/성숙/쇠퇴) 는[conf:30]기본 (Vernon 3-phase 정의 기준 변동성). - 공정 (chainName) 비교는 같은 산업 안에서만. cross-industry 비교는 한계 명시 필수.
호출 동작
dartlab.industry() (인자 없음) → 등록된 산업 목록 가이드 DataFrame.
dartlab.industry(industryId) → 해당 산업의 공정·종목 DataFrame. stage 로 특정 공정만 필터.
summary=True → year 기준 공정별 매출/영업이익 집계. year=None이면 finance 원장의 최근 연간 사업연도를 선택한다. timeline=True → 연도별 공정 매출 시계열. lifecycle=True → 산업 라이프사이클 phase 시계열 (Vernon 3-phase + 쇠퇴. 도입 ≥30% / 성장 1030% / 성숙 010% / 쇠퇴 0% 미만 YoY). concentration=True → 산업 매출 시장구조 집중도 (HHI/CR3 + 상위 5사). dynamics=True → 이익 풀 동학(아래). polarization=True → 산업 양극화 교차검증(아래). 동시 사용 X. 우선순위 summary > timeline > lifecycle > concentration > dynamics > polarization.
What ships with it
4 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 · 334 lines · 0 tokens per session scan A ad4119d25461
industry 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 5,834 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。.