viz

A visualization engine that turns analysis results into chart specifications or diagrams. It supports common charts such as line, bar, table, radar, waterfall, heatmap, histogram, combo, sparkline, and pie charts.

In plain words
What is it for?
Use it to emit charts or Mermaid diagrams from Python-based analysis. Charts can be rendered inline or saved for a web application, with a source-data panel available for evidence-linked results.
Why use it?
Analysis data is harder to compare when it is shown only as text. The engine links each chart to its supporting evidence so users can inspect the source behind it.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/eddmpython/dartlab/viz
Any agent
npx skills add eddmpython/dartlab --skill viz
Clone the repo
git clone --depth 1 https://github.com/eddmpython/dartlab

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.03449
Opus 5 $0.00000 $0.01724
Sonnet 5 $0.00000 $0.00690
Haiku 4.5 $0.00000 $0.00345

Measured 2d ago against content hash 345e328a56e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

viz 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.

src/dartlab/skills/specs/engines/viz/SKILL.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

엔진 역할

viz 는 분석 결과를 차트 spec 으로 변환한다. 직접 차트 이미지를 그리지 않고 — spec dict 를 만들어 (a) emit_chart(spec) 로 stdout 마커 출력 → AI tool result 로 인라인 렌더 또는 (b) landing/static/charts/{code}/manifest.json 정적 빌드 → svelte ChartRenderer 가 등록 chartType 단일 분기 렌더.

evidence 회로 강제 — 모든 ChartSpec 은 evidenceBinding 또는 evidenceIds 가 채워져야 emit. drill-back 으로 차트 점 클릭 시 source 데이터 패널 진입.

공개 호출 방식

# RunPython 안에서
from dartlab.viz import emit_chart, emit_diagram
import dartlab

c = dartlab.Company("005930")
ratios = c.panel("ratios", freq="Q")

# 1. 시계열 line
emit_chart({
    "chartType": "line",
    "title": "영업이익률 추이",
    "data": [{"period": p, "value": v}
             for p, v in zip(ratios["period"], ratios["operatingMargin"])],
    "xAxis": "period",
    "yAxis": "value",
    "unit": "%",
    "evidenceBinding": {
        "tableRef": "table:005930:ratios:Q",
        "source": "dart",
        "stockCode": "005930",
        "topic": "ratios",
    },
})

# 2. peer 비교 bar
emit_chart({
    "chartType": "bar",
    "title": "peer ROE",
    "data": peer_rows,
    "xAxis": "stockCode",
    "yAxis": "roe",
    "evidenceIds": ["scan:profitability:2025Q3"],
})

# 3. 다이어그램 (mermaid)
emit_diagram("mermaid", "graph LR\n  A-->B\n  B-->C")

# 4. CompileVisual tool (AI 도구 경로 — auto evidence)
# LLM 이 자율 호출
# 회사 페이지 정적 차트 빌드
uv run python -X utf8 landing/_scripts/buildCompanyCharts.py --code 005930
# → landing/static/charts/005930/manifest.json + section JSON

강행 호출 룰 (agent 답변 품질 회귀 차단)

차트 시각화에서 다음 4 룰 강행:

  1. 차트 생성은 CompileVisual tool 1 회 — chartType + data + 인자. RunPython 직접 matplotlib/plotly 호출 금지 (visualRef 미발급 → UI 렌더 실패).
  2. 모든 차트의 evidenceBinding 필수 — 차트 안 모든 값에 ref 박힌 source 명시. evidenceBinding 누락 시 거부 (해결책 포함 경고).
  3. 데이터 부족 시 차트 만들지 마라 — 표 + coverage note 로 낮춘다. 환각 차트 (X 값 없는 그래프, peer 4 개 미만 분포 등) 금지.
  4. 본문 안 차트 인용에 [visualRef:...] 표기 — UI 가 inline 렌더링하므로 ref id 필수.

호출 동작

emit_chart(spec) — ChartSpec dict 를 stdout 에 [VIZ_SPEC_START]...[VIZ_SPEC_END] 마커로 출력. agent 가 extract_viz_specs(stdout) 로 추출 → view_spec TraceEvent → 클라이언트 ChartRenderer 가 인라인 렌더. evidenceBinding 또는 evidenceIds 누락 시 거부 (해결책 포함 경고).

Read the full file on GitHub · 297 lines

Files

What ships with it

10 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.

Changes

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.

  1. 2d ago First seen · 297 lines · 0 tokens per session scan A 345e328a56e2

Subscribe to this mod's changes

viz 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 3,449 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.

Related

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).

OpenBB-finance/OpenBB · 57 tokens

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.

OpenBB-finance/OpenBB · 53 tokens

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.

OpenBB-finance/OpenBB · 33 tokens

configure_mcp_server

This guide covers installation, configuration, authentication, tool discovery, prompt management, and client integration for openbb-mcp-server.

OpenBB-finance/OpenBB · 31 tokens

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)。.

csmar432/finai-research · 36 tokens

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。.

ZhuLinsen/alphasift · 76 tokens