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 cyijun/china-financial-services --skill pptx-authorgit clone --depth 1 https://github.com/cyijun/china-financial-servicesWrote 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/cyijun/china-financial-services/pptx-author)<a href="https://agentmods.dev/skills/cyijun/china-financial-services/pptx-author"><img src="https://agentmods.dev/badge/skills/cyijun/china-financial-services/pptx-author/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/cyijun/china-financial-services/pptx-author"><img src="https://agentmods.dev/badge/skills/cyijun/china-financial-services/pptx-author.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 | $0.00041 | $0.00783 |
| Opus 5.5 | $0.00016 | $0.00313 |
| Sonnet 5.5 | $0.00008 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
pptx-author 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pptx-author
Use this skill when running headless and you need to deliver a Chinese market research PowerPoint deck as a file artifact rather than editing a live document through an Office integration.
Output contract
- Write to
./out/<name>.pptx. Create./out/if it does not exist. - Return the relative path in your final message so the orchestration layer can collect it.
How to build the deck
Write a short Python script and run it with Bash. Use python-pptx:
from pptx import Presentation
from pptx.util import Inches, Pt
from pptx.dml.color import RGBColor
from pptx.enum.text import PP_ALIGN, MSO_ANCHOR
prs = Presentation("./templates/firm-template.pptx") # if a template is provided
# or: prs = Presentation()
slide = prs.slides.add_slide(prs.slide_layouts[5]) # title-only
# Set Chinese-friendly font
def set_chinese_font(run, font_name="微软雅黑", font_size=18, bold=False):
font = run.font
font.name = font_name
font.size = Pt(font_size)
font.bold = bold
# For CJK fallback on non-Windows systems
run._element.set("lang", "zh-CN")
title = slide.shapes.title
for paragraph in title.text_frame.paragraphs:
paragraph.clear()
run = paragraph.add_run()
run.text = "A股新能源汽车行业深度"
set_chinese_font(run, "微软雅黑", 28, bold=True)
# ... add tables / charts / text boxes with set_chinese_font() ...
prs.save("./out/china-sector-primer.pptx")
Chinese context conventions
- Fonts: Default to 微软雅黑 (Microsoft YaHei) or SimHei for Chinese text; Times New Roman for English words and numbers. If the target system may lack 微软雅黑, fall back to SimHei or specify a system-available CJK font.
- Language: Slide titles and body text may be written in Chinese. Keep titles punchy and takeaway-oriented.
- Numbers and units: Use Chinese market conventions — e.g., 亿元人民币, 万亿元, 个百分点, PE(TTM), PB(LF).
- Content conventions (mirror the live-Office skill but for Chinese research reports):
- One idea per slide. Title states the takeaway; body supports it.
- Every number traces to the model. If a figure comes from Tushare, footnote the interface and date, e.g.,
数据来源: Tushare daily_basic 2024-12-01. If from a local workbook, cite the path and cell, e.g.,见 ./out/comps.xlsx Sheet1 B7. - Use the firm template when one is mounted at
./templates/; otherwise default layouts. - Charts: Prefer embedding a PNG rendered from the model over native pptx charts when fidelity matters. Save the PNG to
./out/and insert it withslide.shapes.add_picture(). - No external sends. This skill writes a file; it never emails or uploads.
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.
- 1mo ago First seen · 66 lines · 41 tokens per session scan A f1a761bffbf2
pptx-author is a skill published in the GitHub repository cyijun/china-financial-services (21 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 783 once invoked, about $0.0002 per session on Opus 5.5. 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
invoice
A printable invoice page — sender + recipient block, line items table, tax breakdown, totals, and payment instructions. Use when the brief mentions "invoice", "bill", "billing statement", or "发票".
report-generator
Generate professional HTML/PDF investment reports with interactive visualizations.
cwicr-report-generator
Generate professional cost estimation reports from CWICR calculations. HTML, PDF, Excel outputs with charts and breakdowns.
financial-parser
Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.
financial-document-parser
Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.
iflytek-ocr-invoice
An image-reading tool that extracts structured information from Chinese invoices, receipts, bills, and tickets. OCR means turning text in a photo or scan into computer-readable data.