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-paper-figuregit 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-paper-figure)<a href="https://agentmods.dev/skills/csmar432/finai-research/fin-paper-figure"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-paper-figure/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-paper-figure"><img src="https://agentmods.dev/badge/skills/csmar432/finai-research/fin-paper-figure.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 | $0.00014 | $0.08914 |
| Opus 5 | $0.00007 | $0.04457 |
| Sonnet 5 | $0.00003 | $0.01783 |
| Haiku 4.5 | $0.00001 | $0.00891 |
Grade A, and why
fin-paper-figure 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 13d 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 — 1,069 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fin-paper-figure
Generate academic-quality figures (>=300 DPI) for economics and finance papers. Reads FIGURE_PLAN.md and actual data, then produces publication-ready figures using FinancialChartFactory.
Step 0: Environment Check
Before generating any figures, verify the environment:
# Check required packages
python -c "import matplotlib; import seaborn; import pandas; print('OK')"
# Check data availability
ls -la data/processed/
ls -la output/fin-experiments/
# Verify output directories exist
import os
output_base = "output/fin-manuscript/draft_v1"
figure_dir = f"{output_base}/figures"
os.makedirs(figure_dir, exist_ok=True)
print(f"Figure output directory: {figure_dir}")
Step 1: Read Input Files
Read the figure plan and actual data:
import pandas as pd
from pathlib import Path
# Read FIGURE_PLAN.md
outline_path = Path("output/fin-manuscript/draft_v1/FIGURE_PLAN.md")
if outline_path.exists():
figure_plan = outline_path.read_text(encoding="utf-8")
print("Read FIGURE_PLAN.md")
# Read TABLE_PLAN.md for reference
table_plan_path = Path("output/fin-manuscript/draft_v1/TABLE_PLAN.md")
if table_plan_path.exists():
table_plan = table_plan_path.read_text(encoding="utf-8")
# Read PAPER_OUTLINE.md to determine journal style
outline_path = Path("output/fin-manuscript/draft_v1/PAPER_OUTLINE.md")
if outline_path.exists():
paper_outline = outline_path.read_text(encoding="utf-8")
# Extract target journal
# target_journal = extract_journal(paper_outline)
Step 2: Configure Chart Settings
Set up the ChartConfig based on the target journal:
from dataclasses import dataclass
from typing import List, Optional
from enum import Enum
class JournalStyle(Enum):
CHINESE_TOP = "chinese_top" # 经济研究/金融研究/管理世界
AEA = "aea" # AER/JF/JFE/RFS
CHICAGO = "chicago" # JPE
IEEE = "ieee" # 通用英文
@dataclass
class ChartConfig:
"""Configuration for academic figure generation."""
# Canvas
figsize: tuple = (8, 5.5) # width, height in inches
dpi: int = 300 # dots per inch (publication standard)
tight_layout: bool = True
# Font (critical for Chinese journals)
font_family: str = "Times New Roman" # English journals
font_size: int = 10
title_fontsize: int = 12
label_fontsize: int = 10
legend_fontsize: int = 9
tick_fontsize: int = 9
# Colors
color_palette: str = "colorblind" # "Set2" for Chinese printing
primary_color: str = "#2E86AB" # Blue
secondary_color: str = "#F6AE2D" # Orange
accent_color: str = "#E94F37" # Red for policy year
ci_color: str = "#2E86AB" # Confidence interval fill
# Output
output_formats: List[str] = None # ["pdf", "png", "svg"]
style: str = "seaborn-v0_8-paper"
# Grid
grid_alpha: float = 0.3
grid_linestyle: str = "--"
# Line styles
line_width: float = 1.5
marker_size: float = 5
ci_alpha: float = 0.2
def __post_init__(self):
if self.output_formats is None:
self.output_formats = ["pdf", "png"]
# Chinese journal configuration (经济研究/金融研究/管理世界)
CHINESE_CONFIG = ChartConfig(
figsize=(8, 5.5),
dpi=300,
font_family="SimHei",
font_size=10,
title_fontsize=12,
label_fontsize=10,
legend_fontsize=9,
tick_fontsize=9,
color_palette="Set2", # Better for Chinese printing
primary_color="#2E86AB",
secondary_color="#F6AE2D",
accent_color="#E94F37",
ci_color="#2E86AB",
output_formats=["pdf", "png"],
style="seaborn-v0_8-paper",
grid_alpha=0.3,
grid_linestyle="--",
line_width=1.5,
marker_size=5,
ci_alpha=0.2,
)
# English top journal configuration (JF/JFE/RFS/AER)
ENGLISH_CONFIG = ChartConfig(
figsize=(7, 5),
dpi=300,
font_family="Times New Roman",
font_size=10,
title_fontsize=12,
label_fontsize=10,
legend_fontsize=9,
tick_fontsize=9,
color_palette="colorblind",
primary_color="#4472C4",
secondary_color="#ED7D31",
accent_color="#C00000",
ci_color="#4472C4",
output_formats=["pdf", "png"],
style="seaborn-v0_8-paper",
grid_alpha=0.3,
grid_linestyle="--",
line_width=1.5,
marker_size=5,
ci_alpha=0.2,
)
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.
- 13d ago First seen · 1,069 lines · 14 tokens per session scan A 7ba44343d5be
fin-paper-figure is a skill published in the GitHub repository csmar432/finai-research (100 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 8,914 once invoked, about $0.0001 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.…
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…
review-paper
Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via…
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.