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 thtskaran/claude-skills --skill ml-contentgit clone --depth 1 https://github.com/thtskaran/claude-skillsWrote 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/thtskaran/claude-skills/ml-content)<a href="https://agentmods.dev/skills/thtskaran/claude-skills/ml-content"><img src="https://agentmods.dev/badge/skills/thtskaran/claude-skills/ml-content/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/thtskaran/claude-skills/ml-content"><img src="https://agentmods.dev/badge/skills/thtskaran/claude-skills/ml-content.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 | $0.00101 | $0.16742 |
| Opus 5.5 | $0.00040 | $0.06697 |
| Sonnet 5.5 | $0.00020 | $0.03348 |
| Haiku 4.5 | $0.00010 | $0.01674 |
Grade A, and why
ml-content 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 — 611 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ml-content
Generate ML explainer content that looks like 3Blue1Brown, not like AI slop.
⚠️ PRIME DIRECTIVE — treat every video as nuclear. ZERO errors ship.
The content goes public to an audience that will fact-check it. A single wrong number, mislabeled quantity, or overstated claim destroys trust in everything else and gets screenshotted. So: nothing — not even slightly — may be wrong. Every spoken line, every on-screen number and label, every caption, and the thumbnail must be verified against the primary source before it is rendered, and audited again on the rendered video before it ships (§10, the non-negotiable gate). If you cannot cite the exact source line for a claim, you do not say it, write it, or put it on screen. Soften it or cut it. No "dramatic license" on numbers. When in doubt, it is wrong until proven right.
This skill was rebuilt from a full read of Grant Sanderson's actual production code (github.com/3b1b/videos, 503K LOC, 2015→2026) and the real manimGL engine (github.com/3b1b/manim). Every rule below is grounded in that source with file:line citations. Where this skill once guessed, it now measures.
The video engine is manimGL (the 3b1b version), driven by manimgl. Manim Community Edition (CE) is a different library with a different, incompatible API — code written for one crashes on the other. Static IG carousels use HTML/matplotlib (see the Carousel section); everything animated is manimGL.
0. Why the old output was slop (read this once)
The previous version of this skill produced overlapping elements, weak animation, no consistency, and infographic-feeling stills. The root causes, now fixed:
- It shipped Manim CE code while preaching manimGL. The old template used
from manim import *,MathTex,ThreeDScene,set_camera_orientation,set_fill_by_value,Create,begin_ambient_camera_rotation— none of which exist in manimGL (grepover the entire engine = 0 hits). It would not even run. - 100% of real output was actually built in matplotlib, hand-placing ~57 text calls + ~20 boxes per scene with absolute coordinates. That is the worst possible tool for animation: no relative layout, no transform system, no camera. Overlap is guaranteed.
- It treated overlap as a validation problem (bbox asserts, frame validators, ffmpeg caption-pads) instead of a construction problem. 3b1b never validates overlap — it makes overlap structurally impossible by building self-arranging objects.
- It treated motion as decoration. Elements faded in from nowhere as disconnected islands. In real 3b1b, objects are born from the thing they abstract (
TransformFromCopy), so every motion teaches. - Planning was marketing copy with word-count targets. Real 3b1b planning is an ordered list of named teaching beats that reads top-to-bottom as the narration.
What ships with it
11 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.
- REBUILD-NOTES.md 5.8 KB
- scripts/carousel_template.html 7.5 KB
- scripts/helpers_template.py 5.9 KB runs code
- scripts/manim_scene.py 11 KB runs code
- scripts/pipeline/assemble.py 2.7 KB runs code
- scripts/pipeline/build_captions.py 2.7 KB runs code
- scripts/pipeline/timing.py 3.2 KB runs code
- scripts/pipeline/vo_continuous.py 2.2 KB runs code
- scripts/render_3d.py 11 KB runs code
- scripts/render_carousel.py 2.9 KB runs code
- scripts/thumbnail_template.py 4.2 KB runs code
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 · 611 lines · 0 tokens per session scan A 7609f92caa70
ml-content is a skill published in the GitHub repository thtskaran/claude-skills (22 stars, last pushed 4mo ago), licensed MIT. It adds 101 tokens to every session and 16,742 once invoked, about $0.0004 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
math-modeling
A workflow for mathematical modelling, where real-world questions are represented with mathematics and solved with code or analysis.
math-modeling
A workflow for mathematical modelling, where real-world questions are represented with mathematics and solved with code or analysis.
release
Cut a booping plugin release — verify the version bump against the last published tag, draft public-voiced release notes, merge the release branch into master, tag, and publish the GitHub release. Use when cutting a vX.Y.Z release of this repo.
LaTeX工具
A tool for creating, compiling, and checking mathematical modelling papers written in LaTeX, a document system often used for technical writing.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
DOCX工具
A tool for creating, editing, checking, and converting Microsoft Word DOCX files. It also handles LaTeX research papers, mathematical formulas, tables, tracked changes, and comments.