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 7 hours ago
45,100 skills
- dart-write-documentationflutter/agent-pluginsRules and formatting guidelines for writing Dart /// API documentation and doc comments. Use when documenting Dart code, writing doc comments for any Dart declaration (libraries, classes, methods, variables, etc.), or when instructed to follow the Effective Dart documentation guidelines.OfficialWritingNo warnings★ 3.1K↓ —
- khazix-writerKKKKhazix/khazix-skills数字生命卡兹克（Khazix）的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于：写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。即使用户只是说"帮我把这个写成文章"或"用我的风格写一下"，只要上下文涉及内容创作和公众号输出，都应该触发。也适用于用户丢过来一个PDF、brief、新闻链接、语音转文字或任何素材说"帮我写篇文章"的场景。不要用于短内容（小红书帖子、推特、朋友圈）或纯标题摘要生成（那个用wechat-title skill）。WritingNo warnings★ 21.7K↓ —
- flutter-use-http-packageflutter/agent-pluginsUse the `http` package to execute GET, POST, PUT, or DELETE requests. Use when you need to fetch from or send data to a REST API.OfficialEngineeringNo warnings★ 3.1K↓ —
- training-llms-megatronOrchestra-Research/AI-Research-SKILLsTrains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.ProductivityNo 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↓ —
- grant-proposalwanshuiyin/Auto-claude-code-research-in-sleepDraft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.ScienceNo warnings★ 18.1K↓ —
- pyvene-interventionsOrchestra-Research/AI-Research-SKILLsProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.TestingNo warnings★ 14K↓ —
- dart-use-pattern-matchingflutter/agent-pluginsApplies Dart 3 pattern matching, switch expressions, and destructuring idiomatically to validate data schemas, handle algebraic data types, and decompose control flow. Use when refactoring complex if-else chains, parsing polymorphic JSON or API responses, destructuring Lists, URI/path segments, String.split() tokens, Records, or Maps, or enforcing exhaustiveness on sealed classes. Don't use for simple boolean conditions, single-variable type promotion (use `is`), or basic collection filtering.OfficialEngineeringNo warnings★ 3.1K↓ —
- dart-generate-test-mocksflutter/agent-pluginsDefine and generate mock objects for external dependencies using `package:mockito` and `build_runner`. Use when unit testing classes that depend on complex external services like APIs or databases.OfficialTestingNo warnings★ 3.1K↓ —
- dse-loopwanshuiyin/Auto-claude-code-research-in-sleepAutonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning.DesignNo warnings★ 18.1K↓ —
- paper-figurewanshuiyin/Auto-claude-code-research-in-sleepGenerate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.ScienceNo warnings★ 18.1K↓ —
- 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↓ —
- 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↓ —
- experiment-tracking-swanlabOrchestra-Research/AI-Research-SKILLsProvides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.OtherNo warnings★ 14K↓ —
- 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↓ —
- nnsight-remote-interpretabilityOrchestra-Research/AI-Research-SKILLsProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.PlanningNo warnings★ 14K↓ —
- sparse-autoencoder-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.OtherNo warnings★ 14K↓ —Also in 1 other repo
- frontend-ui-dark-tsmicrosoft/skillsBuild dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.OfficialDesignNo warnings★ 3.1K↓ —
- idea-discoverywanshuiyin/Auto-claude-code-research-in-sleepWorkflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review to go from a broad research direction to validated, pilot-tested ideas. Use when user says \"找idea全流程\", \"idea discovery pipeline\", \"从零开始找方向\", or wants the complete idea exploration workflow.ScienceNo warnings★ 18.1K↓ —
- constitutional-aiOrchestra-Research/AI-Research-SKILLsAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.OtherNo warnings★ 14K↓ —
- auto-review-loopwanshuiyin/Auto-claude-code-research-in-sleepAutonomous multi-round research review loop. Repeatedly reviews using Gemini via gemini-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.EngineeringNo warnings★ 18.1K↓ —
- openalexwanshuiyin/Auto-claude-code-research-in-sleepSearch academic papers via OpenAlex API for open citation data, institutional affiliations, and funding information. Use when user says "openalex search", "search openalex", "open citation graph", or wants comprehensive academic metadata beyond arXiv/Semantic Scholar.ScienceNo warnings★ 18.1K↓ —
- krillinai-coverkrillinai/OpenCreatorUse when generating a cover image with the KrillinAI CLI from a complete image prompt, including validating image-provider configuration and inspecting the generated image and saved prompt.MediaNo warnings★ 13.9K↓ —
- speculative-decodingOrchestra-Research/AI-Research-SKILLsAccelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.PlanningNo warnings★ 14K↓ —
fine-tuning-with-trl
Orchestra-Research/AI-Research-SKILLs
OtherUpdated Oct 11, 2026
From the author
Fine-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.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-with-trl -a claude-code
Installs to .claude/skills/fine-tuning-with-trl/ · 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 (5)
- SKILL.md
- references/dpo-variants.md
- references/online-rl.md
- references/reward-modeling.md
- references/sft-training.md