44 tagged Alignment, measured the same way as everything else here.
Browse within: RLHF 29agent 22Evaluation 21reward 21reward-model 21agpl 11anthropic-skills 11DPO Alternative 5Efficient Training 5LLM Alignment 5Post-Training 5Preference Optimization 5Reference-Free 5SimPO 5
Skill Claude Code
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.
Skill Claude CodeCodex
Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra…
Skill Claude CodeCodex
A conversational teaching workflow that helps someone learn a technical subject through dialogue, real errors, and their own explanations.
Skill Claude CodeCodex
This skill should be used when a request is ambiguous, underspecified, conflicting, or high impact. It is intended for vague verbs like optimize, improve, fix, refactor, and add feature; for missing file paths or unknown dependencies; and for risky actions like deploy, delete, overwrite, or migrate. It should not be…
shihchengwei-lab/separation-and-audit-claude-code
Skill Claude CodeCodex
A design review guide for words users or players can see, such as interface labels, system messages, errors, stories, and dialogue. It checks those words against a project's design principles and forbidden patterns.
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: