Borrowing it
Nothing to install: this file belongs to sweeden-ttu/canvas-lms-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sweeden-ttu/canvas-lms-mcp/main/.cursor/skills/latex-blog-series-publisher/SKILL.mdgit clone --depth 1 https://github.com/sweeden-ttu/canvas-lms-mcpWrote 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/sweeden-ttu/canvas-lms-mcp/latex-blog-series-publisher)<a href="https://agentmods.dev/skills/sweeden-ttu/canvas-lms-mcp/latex-blog-series-publisher"><img src="https://agentmods.dev/badge/skills/sweeden-ttu/canvas-lms-mcp/latex-blog-series-publisher/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/sweeden-ttu/canvas-lms-mcp/latex-blog-series-publisher"><img src="https://agentmods.dev/badge/skills/sweeden-ttu/canvas-lms-mcp/latex-blog-series-publisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00071 | $0.00866 |
| Opus 5.5 | $0.00028 | $0.00346 |
| Sonnet 5.5 | $0.00014 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
latex-blog-series-publisher 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 2mo 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.
What it actually says
LaTeX → Blog Series Publisher (Jekyll + KaTeX + Mermaid)
Turn one LaTeX source into a navigable blog series with consistent structure, cross-links, and rendering that works in Jekyll with KaTeX and Mermaid.
Inputs to request (if missing)
- LaTeX source (
.tex) and any assets (figures/bib) - Target site location (Jekyll root) and desired output folder (
_posts/vsnotes/) - Desired series title/slug, and target number of parts (or “auto by sections”)
- Audience level (intro / advanced / mixed)
Core workflow
-
Parse the LaTeX outline
- Extract
\section,\subsection,\paragraphheadings. - Identify special blocks: equations, code listings, tables, figures, references.
- Extract
-
Design the series plan
- Map major sections to posts (“Part 1…N”) and keep each post focused.
- Add a consistent per-post structure:
- Context + learning goals
- Main content
- Worked example
- Summary + exercises (optional)
-
Convert content to Markdown suitable for Jekyll
- Preserve math delimiters as
\( \)and\[ \](KaTeX renders these in the browser). - Convert LaTeX lists to Markdown lists.
- Convert
\texttt{}/\verbto backticks. - Convert
\begin{verbatim}/ listings to fenced code blocks.
- Preserve math delimiters as
-
Handle figures/tables
- If images are present, reference them under an assets folder (e.g.,
assets/img/series-slug/). - If images are not available, insert placeholders:
> TODO: Add figure “...” (from LaTeX Figure X).
- If images are present, reference them under an assets folder (e.g.,
-
Mermaid extraction
- If the LaTeX uses a convention like
\begin{mermaid}...\end{mermaid}(or commented markers), convert to fenced Mermaid:-
graph TD ...
-
- If no Mermaid exists, propose diagrams where it clarifies architecture or workflows.
- If the LaTeX uses a convention like
-
Create series navigation
- Add front matter fields like
series,part, and optionalprev_url/next_url. - Add a “Series contents” block at the top of each post linking to all parts.
- Add front matter fields like
Jekyll post template (default)
Use this front matter:
---
layout: post
title: "Series Title — Part X: Specific Topic"
date: 2026-01-30
tags: [trustworthy-ai]
series: series-slug
part: 1
description: "One-sentence summary of this part."
---
Then structure:
## Why this matters## Key ideas## Worked example## Common pitfalls## Summary## Exercises(optional)
Quality bar
- No “wall of text”: break up long sections with headings and examples
- Each post has a clear learning goal and recap
- Math renders with KaTeX (keep delimiters consistent)
- Mermaid diagrams render (use fenced blocks)
- Internal links work, and series ordering is explicit
- Technical claims have either a derivation, citation, or an example
What to return to the user
- A complete list of generated Markdown files and where they should live in the Jekyll repo
- Any required site additions (KaTeX/Mermaid includes if not already present)
- A short “edit map” describing which LaTeX sections landed in which post
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.
- 2mo ago First seen · 91 lines · 71 tokens per session scan A ea49731e4ea5
latex-blog-series-publisher is a skill published in the GitHub repository sweeden-ttu/canvas-lms-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 71 tokens to every session and 866 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
canvas-cli
Manage Canvas LMS (https://www.instructure.com/canvas) from the terminal with the canvas CLI — courses, assignments, submissions and grading, modules, pages, quizzes, discussions, announcements, users, enrollments, sections, files, and analytics. Use this whenever the user wants to list or create assignments, grade…
canvas-admin-roster
Admin skill for walking the Canvas account hierarchy: list accounts and sub-accounts, see courses and users under each, look up which canned reports are available, and enroll or remove users from a specific course — one action at a time. Trigger phrases include "admin roster", "list accounts", "sub accounts", "account…
canvas-peer-review-tracker
Educator skill for tracking peer-review assignments in Canvas. Lists who has been asked to review whom, who has submitted versus who is still pending, and lets you assign new reviewers or send reminder messages — one student at a time. Trigger phrases include "peer reviews", "who hasn't done their peer review", "peer…
canvas-course-requirements
Student plan for one Canvas course, built from the requirement graph instead of guessed from raw module flags. Shows what is genuinely left, what is blocked, and what Canvas cannot yet say either way, with the endpoint and field behind every verdict. Trigger phrases include "what do I still have to do in this course"…
canvas-accessibility-sweep
Educator and learning-designer skill for a pre-launch accessibility and broken-link sweep of a Canvas course. Walks the structural accessibility audit and the link audit over a course's pages, assignments, syllabus, announcements, and (optionally) quizzes, then produces a prioritised remediation list you can work…
canvas-course-pulse
Educator skill for tracking week-over-week course health trends in Canvas. Surfaces assignment performance trends, login activity, engagement gaps, and struggling students across a longer time horizon than a daily check. Trigger phrases include "course pulse", "course health", "course trends", "week-over-week…