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 skills add csmar432/finai-research --skill fin-viz-launchgit clone --depth 1 https://github.com/csmar432/finai-researchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/csmar432/finai-research/fin-viz-launch)<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-viz-launch"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-viz-launch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-viz-launch"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-viz-launch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.03770 |
| Opus 5 | $0.00023 | $0.01885 |
| Sonnet 5 | $0.00009 | $0.00754 |
| Haiku 4.5 | $0.00005 | $0.00377 |
Grade A, and why
fin-viz-launch 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 12d 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 — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fin-viz-launch
将用户的研究描述转换为高质量学术图表,自动推荐最佳图表类型并生成matplotlib/seaborn代码,输出≥300 DPI的PDF/SVG/PNG。
触发条件
- 关键词:
画图可视化figurechartplot图表图表生成生成图表生成图片 - Skill语法:
Skill: fin-viz-launch - 前置条件: 有可用数据 (DataFrame) 或数据路径
三种工作模式
模式一:快速模式 (Quick Mode)
通过关键词匹配,无须LLM直接调用预设模板:
from scripts.research_framework import FinancialChartFactory, ChartConfig
factory = FinancialChartFactory(output_dir="figures/")
# 关键词 → 预设映射
# "平行趋势" → parallel_trends
# "安慰剂" → placebo_distribution
# "相关性" → correlation_heatmap
# 直接使用预设
fig = factory.plot("parallel_trends", df,
time_var="year",
treat_var="treat",
y_var="innovation",
save_path="figures/parallel_trends.pdf",
dpi=300,
)
模式二:LLM模式 (CoDA-Style Pipeline)
描述 → 选择图表类型 → 生成代码 → 执行 → 迭代:
from scripts.research_framework import ChartLLMGenerator
generator = ChartLLMGenerator(
model="deepseek",
output_dir="figures/",
)
# 用户描述
user_description = "显示处理组和对照组在政策前后的创新投入趋势,标注置信区间"
# LLM选择图表类型并生成代码
result = generator.generate(
description=user_description,
data=df,
context={"methodology": "DID", "journal": "经济研究"},
)
# result = {
# "chart_type": "parallel_trends",
# "code": "...",
# "reasoning": "选择了带置信区间的平行趋势图...",
# }
# 执行代码
fig = generator.execute(result["code"])
模式三:交互模式 (Interactive Mode)
用户确认后再生成:
用户: 画一个展示DID回归结果的图
AI推荐: 系数森林图 (forest plot) 适合展示DID系数和置信区间
请确认:
1. 接受推荐 → 生成森林图
2. 换成其他类型 → 选择: 条形图/时序图/热力图
3. 自定义参数 → 指定: 颜色/标签/标题
> 1
[生成森林图...]
20种预设图表模板
实证研究图表
| 图表类型 | 关键词 | 用途 |
|---|---|---|
parallel_trends |
平行趋势, pre-trend | DID平行趋势检验 |
placebo_distribution |
安慰剂, placebo | 安慰剂检验分布 |
robustness_summary |
稳健性, robustness | 稳健性系数森林图 |
psm_distribution |
PSM, 倾向得分 | 倾向得分分布 |
did_coef_timeline |
DID系数, 时序 | DID系数时间变化 |
cumulative_effect |
累积, CAR | 累积处理效应 |
event_study |
事件研究, 窗口 | 事件窗口期收益 |
描述性图表
| 图表类型 | 关键词 | 用途 |
|---|---|---|
correlation_heatmap |
相关性, 相关矩阵 | 变量相关热力图 |
descriptive_bar |
描述性, 对比 | 分组对比柱状图 |
heterogeneity_bar |
异质性, 分组 | 异质性分析柱状图 |
marginal_effects |
边际效应 | 边际效应图 |
ridgeline |
分布, 时序 | Ridgeline时序分布 |
waffle |
构成, 比例 | Waffle构成图 |
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.
- 12d ago First seen · 444 lines · 45 tokens per session scan A ae46215145a4
fin-viz-launch is a skill published in the GitHub repository csmar432/finai-research (100 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 3,770 once invoked, about $0.0002 per session on Opus 5. 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
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
figure-creation
Create, edit, or plan figures in Stencila Markdown — simple image figures, executable code figures, multi-panel subfigure layouts with grid arrangements, and SVG annotation overlays using overlay components. Use when asked to add or revise a figure, chart, plot, caption, subfigure grid, panel layout, overlay…
econometrics-phd-level
A guide to econometrics, the use of statistics to study relationships in data, based on a 12-part Korean lecture series. It routes questions to explanations of topics such as regression, panel data, instrumental variables, and causal comparisons.
r-econometrics
Generates rigorous, modern, reproducible R code for causal inference and panel econometrics with fixest, heterogeneity-robust DiD estimators (Callaway-Sant'Anna, Sun-Abraham, BJS, de Chaisemartin-D'Haultfoeuille), weak-IV-robust inference, optimal-bandwidth RDD via rdrobust, and wild cluster bootstrap. Use when the…
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
audit-reproducibility
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.