Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
45,100 skills from 2,196 repositories · updated 9 hours ago
45,100 skills
- find-simplificationsCherryHQ/cherry-studioUse when asked to find or plan Cherry Studio cleanup, simplification, refactoring, dead-code removal, duplicated state removal, unnecessary APIs, speculative generality, or library replacements, especially when the result should become evidence-backed proposed Agent Notes.PlanningNo warnings★ 53K↓ —
- code-mate-opencodeCherryHQ/cherry-studioRun OpenCode non-interactively for coding tasks. Use when the user asks to delegate work to OpenCode.EngineeringNo warnings★ 53K↓ —
- cherry-tool-guideCherryHQ/cherry-studioCherry tool routing: bun, uv, rg, knowledge, memory, schedules, skills, MCP, web. Read before shell workarounds.ProductivityNo warnings★ 53K↓ —
- code-mate-antigravityCherryHQ/cherry-studioRun Antigravity CLI non-interactively for coding tasks. Use when the user asks to delegate work to Antigravity.EngineeringNo warnings★ 53K↓ —
- ml-paper-writingOrchestra-Research/AI-Research-SKILLsWrite publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.ScienceNo warnings★ 14K↓ —
- cherry-studio-feedbackCherryHQ/cherry-studioUse when Cherry Studio 用户希望报告、提交或整理 BUG、UI/UX 问题或功能建议，但未明确要求创建 GitHub Issue。DesignNo warnings★ 53K↓ —
- long-contextOrchestra-Research/AI-Research-SKILLsExtend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.ProductivityNo warnings★ 14K↓ —
- ray-trainOrchestra-Research/AI-Research-SKILLsDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.OtherNo warnings★ 14K↓ —
- tensorrt-llmOrchestra-Research/AI-Research-SKILLsOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.DevOpsNo warnings★ 14K↓ —
- vast-gpuwanshuiyin/Auto-claude-code-research-in-sleepRent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.OtherNo warnings★ 18.1K↓ —
- optimizing-attention-flashOrchestra-Research/AI-Research-SKILLsOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.ProductivityNo warnings★ 14K↓ —
- distributed-llm-pretraining-torchtitanOrchestra-Research/AI-Research-SKILLsProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.OtherNo warnings★ 14K↓ —
- fine-tuning-with-trlOrchestra-Research/AI-Research-SKILLsFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.OtherNo warnings★ 14K↓ —
- prompt-guardOrchestra-Research/AI-Research-SKILLsMeta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.SecurityNo warnings★ 14K↓ —
- mamba-architectureOrchestra-Research/AI-Research-SKILLsState-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.PlanningNo warnings★ 14K↓ —
- nemo-curatorOrchestra-Research/AI-Research-SKILLsGPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.MediaNo warnings★ 14K↓ —
- auto-paper-improvement-loopwanshuiyin/Auto-claude-code-research-in-sleepAutonomously improve a generated paper via Claude review through claude-review MCP → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.ScienceNo warnings★ 18.1K↓ —
- prior-art-searchwanshuiyin/Auto-claude-code-research-in-sleepSearch patent databases and academic literature for prior art relevant to an invention. Use when user says "现有技术检索", "prior art search", "专利检索", "check patents", or wants to find relevant prior art.OtherNo warnings★ 18.1K↓ —Also in 1 other repo
- instructorOrchestra-Research/AI-Research-SKILLsExtract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output libraryOtherNo warnings★ 14K↓ —
- exa-searchwanshuiyin/Auto-claude-code-research-in-sleepAI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic databases (arXiv, Semantic Scholar).ScienceNo warnings★ 18.1K↓ —
- auto-paper-improvement-loopwanshuiyin/Auto-claude-code-research-in-sleepAutonomously improve a generated paper via Gemini review through gemini-review MCP → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.ScienceNo warnings★ 18.1K↓ —
- nemo-guardrailsOrchestra-Research/AI-Research-SKILLsNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.OtherNo warnings★ 14K↓ —
- paper-talkwanshuiyin/Auto-claude-code-research-in-sleepEnd-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks). Trigger phrases: "做 talk", "做 PPT 全流程", "talk pipeline", "end-to-end slides", "做演讲", "conference talk full workflow". Use when the user wants the complete talk artifact, not just a slide deck.ScienceNo warnings★ 18.1K↓ —
- paper-poster-htmlwanshuiyin/Auto-claude-code-research-in-sleepDEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says "做海报", "poster", "conference poster", "paper poster", or asks to design/redo a research poster.ScienceNo warnings★ 18.1K↓ —
verl-rl-training
Orchestra-Research/AI-Research-SKILLs
DevOpsUpdated Oct 11, 2026
From the author
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill verl-rl-training -a claude-code
Installs to .claude/skills/verl-rl-training/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 93
Security100
Provenance90
Maintenance100
Licence100
Adoption65
Files (3)
- SKILL.md
- references/api-reference.md
- references/troubleshooting.md