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.
46,700 skills from 2,243 repositories · updated 21 hours ago
46,700 skills
- analyze-resultswanshuiyin/Auto-claude-code-research-in-sleepAnalyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.OtherNo warnings★ 18.2K↓ —
- model-mergingOrchestra-Research/AI-Research-SKILLsMerge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.DevOpsNo warnings★ 14K↓ —
- code-mate-piCherryHQ/cherry-studioRun Pi non-interactively for repository tasks. Use when the user asks to delegate analysis or implementation to Pi.EngineeringNo warnings★ 53K↓ —
- frontend-design-reviewmicrosoft/skillsReview and create distinctive, production-grade frontend interfaces with high design quality and design system compliance. Evaluates using three pillars: frictionless insight-to-action, quality craft, and trustworthy building. USE FOR: PR reviews, design reviews, accessibility audits, design system compliance checks, creative frontend design, UI code review, component reviews, responsive design checks, theme testing, and creating memorable UI. DO NOT USE FOR: Backend API reviews, database schema reviews, infrastructure or DevOps work, pure business logic without UI, or non-frontend code.OfficialDesignNo warnings★ 3.1K↓ —
- 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↓ —
- 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↓ —
- cherry-regression-testCherryHQ/cherry-studioRun Cherry Studio critical-path system regression tasks through the repository-owned Playwright E2E workflow. Use for full regression, release acceptance, development-branch system validation, or a named cherry-regression-test task on GitHub-hosted macOS and Windows runners.TestingNo warnings★ 53K↓ —
- 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↓ —
- pytorch-fsdp2Orchestra-Research/AI-Research-SKILLsAdds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.ProductivityNo 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↓ —
- install-memuNevaMind-AI/memUInstall or uninstall memU for whatever agent you are — identify your host, print its packaged guide, and follow it to wire (or unwire) both seams (record and inject). Use when the user asks to install, set up, integrate, remove, or uninstall memU.OtherNo warnings★ 14.6K↓ —
- create-skillCherryHQ/cherry-studioCreate a new skill in the current repository. Use when the user wants to create/add a new skill, or mentions creating a skill from scratch. This skill follows the workflow defined in .agents/skills/README.md and helps scaffold, validate, and sync new skills.ProductivityNo warnings★ 53K↓ —
- agent-notesCherryHQ/cherry-studioUse when deciding whether a Cherry Studio change needs an Agent Note, authoring or reviewing a Spec, recording a durable bug-fix decision, moving a note between proposed/implemented/rejected, or checking supersession and stacked Spec approval.ProductivityNo warnings★ 53K↓ —
- research-wikiwanshuiyin/Auto-claude-code-research-in-sleepPersistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.ScienceNo warnings★ 18.2K↓ —
- 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↓ —
- agent-platform-migrate-from-ai-studiogoogle/skillsGuides agents and users through migrating from Gemini API in Google AI Studio to Gemini Enterprise Agent Platform (formerly Vertex AI). Use this skill when moving applications to Google Cloud, to leverage Cloud credits, or to unify inferencing with other Cloud infrastructure (IAM, billing, telemetry).OfficialDevOpsNo warnings★ 21.6K↓ —
- outlinesOrchestra-Research/AI-Research-SKILLsGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation libraryEngineeringNo warnings★ 14K↓ —
- segment-anything-modelOrchestra-Research/AI-Research-SKILLsFoundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.MediaNo warnings★ 14K↓ —
- stable-diffusion-image-generationOrchestra-Research/AI-Research-SKILLsState-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.MediaNo 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↓ —
- 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↓ —
- code-mate-claude-codeCherryHQ/cherry-studioRun Claude Code non-interactively for coding tasks. Use when the user asks to delegate work to Claude Code.EngineeringNo warnings★ 53K↓ —
- arxivwanshuiyin/Auto-claude-code-research-in-sleepSearch, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.ScienceNo warnings★ 18.2K↓ —
evaluating-code-models
Orchestra-Research/AI-Research-SKILLs
EngineeringUpdated Oct 11, 2026
From the author
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill evaluating-code-models -a claude-code
Installs to .claude/skills/evaluating-code-models/ · 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 (4)
- SKILL.md
- references/benchmarks.md
- references/custom-tasks.md
- references/issues.md