227 tagged dataset, measured the same way as everything else here.
Browse within: ai-skills 208skill-registry 206skills 206agent 5agents 5
ATOM00blue/machine-learning-library
Skill Claude Code
Retrieve and cite from this machine-learning education corpus (923 docs — arXiv papers, course lectures, explainer articles). Use when the user asks an ML/deep-learning question, wants to learn a topic, asks for sources/papers/lectures on a concept, or wants a study path grounded in this repo.
Skill Claude CodeCodex
Verify every Swiss case citation in a draft against the OpenCaseLaw corpus with the ocl CLI before answering or filing; report resolved, missing, ambiguous and pinpoint status; never invent or "fix" a citation.
Skill Claude CodeCodex
Look up domain credibility scores using the CRED-1 open dataset. Use when checking if a news source or website is reliable, flagged as misinformation, or has credibility concerns.
Skill Claude Code
Export Claude Code and Codex conversation history to Hugging Face as structured training data. Use when the user asks about exporting conversations, uploading to Hugging Face, configuring codeclaw, reviewing PII/secrets in exports, or managing their dataset.
Skill Claude CodeCodex
Use when the user needs deep data analysis (multi-round SQL queries, aggregation, trend comparison) or wants to persist data (Excel / CSV / API / databases) as a long-lived, cross-platform structured asset — typical scenarios include complex or repeated analysis, accessing the same data across multiple Agents /…
Skill Claude CodeCodex
A set of instructions for adding and repairing datasets in kpubdata, a project that describes public data APIs with specification files. It covers recording real API responses, replaying examples, validating schemas, and updating documentation.
Yinzhanqing/embodied-eval-automation
Skill Codex
Plan, explain, build, run, monitor, validate, transfer, and audit reproducible embodied-model studies and batch episode collection. Use when a user wants to connect a local, SSH, or cloud GPU host; understand and compare a policy, VLA, world model, world-action model, or hybrid with a benchmark; discover and reuse…
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: