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 10 hours ago
45,100 skills
- 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↓ —
- systems-paper-writingOrchestra-Research/AI-Research-SKILLsComprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.ScienceNo warnings★ 14K↓ —
- serverless-modalwanshuiyin/Auto-claude-code-research-in-sleepRun GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.DevOpsNo warnings★ 18.1K↓ —
- moe-trainingOrchestra-Research/AI-Research-SKILLsTrain Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.PlanningNo warnings★ 14K↓ —
- golden-man-kwyusufkaraaslan/Skill_SeekersUse when testing the man golden buildTestingNo warnings★ 15.2K↓ —
- model-pruningOrchestra-Research/AI-Research-SKILLsReduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.OtherNo warnings★ 14K↓ —
- paper-writewanshuiyin/Auto-claude-code-research-in-sleepDraft LaTeX paper section by section from an outline. Use when user says \"写论文\", \"write paper\", \"draft LaTeX\", \"开始写\", or wants to generate LaTeX content from a paper plan.ScienceNo warnings★ 18.1K↓ —
- golden-pdf-kwyusufkaraaslan/Skill_SeekersUse when testing keyword categorizationDocumentsNo warnings★ 15.2K↓ —
- rebuttalwanshuiyin/Auto-claude-code-research-in-sleepWorkflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.ProductivityNo warnings★ 18.1K↓ —
- azure-keyvault-secrets-tsmicrosoft/skillsManage secrets using Azure Key Vault Secrets SDK for JavaScript (@azure/keyvault-secrets). Use when storing and retrieving application secrets or configuration values.OfficialDevOpsNo warnings★ 3.1K↓ —
- azure-storage-file-datalake-pymicrosoft/skillsAzure Data Lake Storage Gen2 SDK for Python. Use for hierarchical file systems, big data analytics, and file/directory operations. Triggers: "data lake", "DataLakeServiceClient", "FileSystemClient", "ADLS Gen2", "hierarchical namespace".OfficialDevOpsNo warnings★ 3.1K↓ —
- research-refine-pipelinewanshuiyin/Auto-claude-code-research-in-sleepRun an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.ScienceNo warnings★ 18.1K↓ —
- golden-pptx-kwyusufkaraaslan/Skill_SeekersUse when testing keyword categorizationDocumentsNo warnings★ 15.2K↓ —
- 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↓ —
- integrity-forensicswanshuiyin/Auto-claude-code-research-in-sleepRun the Anti-Autoresearch integrity-forensics DETERMINISTIC slice (numeric core + rules-only reporter) against a paper via a SHA-pinned thin launcher, then convert the verdict into a typed policy gate (BLOCK/WARN/NO_NEW_BLOCKER) and an append-only obligations ledger. Codex-native limitation: upstream ships no Codex-native auditor pack, so the full nine-dimension semantic sweep requires a Claude Code session — this pack runs the honestly-scoped deterministic-only mode (it can flag, it can never say CLEAN). Use when user says "integrity forensics", "forensic audit this paper", "投稿前自查诚信".SecurityNo warnings★ 18.1K↓ —
- 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↓ —
- tensorboardOrchestra-Research/AI-Research-SKILLsVisualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkitEngineeringNo warnings★ 14K↓ —Also in 1 other repo
- 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↓ —
- ablation-plannerwanshuiyin/Auto-claude-code-research-in-sleepUse when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.PlanningNo warnings★ 18.1K↓ —
- golden-epubyusufkaraaslan/Skill_SeekersUse when testing the epub golden buildTestingNo warnings★ 15.2K↓ —
- auto-review-loopwanshuiyin/Auto-claude-code-research-in-sleepAutonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or max rounds is reached.EngineeringNo warnings★ 18.1K↓ —
- golden-chatyusufkaraaslan/Skill_SeekersUse when testing the golden_chat golden buildTestingNo warnings★ 15.2K↓ —
- golden-htmlyusufkaraaslan/Skill_SeekersUse when testing the html golden buildTestingNo warnings★ 15.2K↓ —
- golden-pptxyusufkaraaslan/Skill_SeekersUse when testing the pptx golden buildDocumentsNo warnings★ 15.2K↓ —
optimizing-attention-flash
Orchestra-Research/AI-Research-SKILLs
ProductivityUpdated Oct 11, 2026
From the author
Optimizes 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.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill optimizing-attention-flash -a claude-code
Installs to .claude/skills/optimizing-attention-flash/ · 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/benchmarks.md
- references/transformers-integration.md