natolambert/rlhf-book

Textbook on reinforcement learning from human feedback

2.4kStars on the repository
10Mods indexed here, across every type
todayLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

gemini-feedback

01

natolambert/rlhf-book

Skill Claude CodeCodex

Get feedback from Gemini API on a diagram image for textbook quality review.

not rated 2.4k +8 today A 18 tokens

push-to-pr

03

natolambert/rlhf-book

Skill Claude CodeCodex

Create a new PR or push commits to an existing PR for the current branch.

not rated 2.4k +8 today A 20 tokens

natolambert/rlhf-book

Skill Claude CodeCodex

Start or verify live preview for RLHF Book course lecture slides without breaking relative image assets. Use when serving, opening, checking, or debugging teach/course/lec.md slides.

not rated 2.4k +8 today A 43 tokens

update-pr-body

06

natolambert/rlhf-book

Skill Claude CodeCodex

Update the body of a GitHub pull request. Use when the user asks to update, edit, or modify a PR description/body.

not rated 2.4k +8 today A 31 tokens

paper-page-figure

07

natolambert/rlhf-book

Skill Claude CodeCodex

Turn the first page of a paper (arXiv or any PDF) into a slide-ready PNG for a colloquium deck's 30-40% right column. Use when a slide cites a landmark paper and a screenshot of the paper itself is the best visual.

not rated 2.4k +8 today A 60 tokens

qa-video-timestamps

08

natolambert/rlhf-book

Skill Claude CodeCodex

Extract per-question (MM:SS) timestamps from a recorded course video by OCR-ing the slide counter, then add YouTube deep links to the course page's Q&A question lists. Use after a Q&A or lecture recording is published, or when adding/refreshing "Show questions" timestamp links in book/templates/course.html.

not rated 2.4k +8 today A 71 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: