skypilot-multi-cloud-orchestration
OpenRaiser
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instan…
1.4KGitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “vibe-research”
225–240 / 482
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 482
peft-fine-tuning
OpenRaiser
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <…
1.4KGitHub
huggingface-accelerate
OpenRaiser
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mix…
ResearchSkill source recorded
1.4KGitHub
unsloth
OpenRaiser
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
ResearchSkill source recorded
1.4KGitHub
academic-plotting
OpenRaiser
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate…
ResearchSkill source recorded
1.4KGitHub
ray-data
OpenRaiser
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales f…
ResearchSkill source recorded
1.4KGitHub
trend-discovery
ScrapeCreators
Use when the user wants to discover trending social topics, hashtags, sounds, posts, reels, shorts, creators, or formats in a niche. Searches public trend and discovery…
2KGitHub
Commonplace
zby
The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.
81GitHub
Paper Reading Zh
MrGeDiao
Evidence-aware Chinese paper reading rules for Codex, Claude Code, Claude Project, and ChatGPT Project
98GitHub
api-design
affaan-m
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs. Use when des…
252.3KGitHub
spec-driven-development
addyosmani
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguou…
92.2KGitHub
mode-creator
thedotmack
Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot set…
93KGitHub
github-dashboard
nexu-io
GitHub repository analytics dashboard — stars, forks, contributors, issues, pull requests, recent activity, and top contributors. Use when the brief asks for a GitHub re…
91KGitHub
writing-plans
obra
Use when you have a spec or requirements for a multi-step task, before touching code
280.4KGitHub
requesting-code-review
obra
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
280.4KGitHub
academy-guide
anthropics
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases…
173KGitHub