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 6 hours ago
45,100 skills
- evolving-ai-agentsOrchestra-Research/AI-Research-SKILLsProvides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.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↓ —
- crewai-multi-agentOrchestra-Research/AI-Research-SKILLsMulti-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.PlanningNo warnings★ 14K↓ —
- autogpt-agentsOrchestra-Research/AI-Research-SKILLsAutonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.DevOpsNo warnings★ 14K↓ —
- paper-illustrationwanshuiyin/Auto-claude-code-research-in-sleepGenerate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.MediaNo warnings★ 18.1K↓ —
- pineconeOrchestra-Research/AI-Research-SKILLsManaged vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.DevOpsNo warnings★ 14K↓ —Also in 1 other repo
- clipOrchestra-Research/AI-Research-SKILLsOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.MediaNo warnings★ 14K↓ —
- faissOrchestra-Research/AI-Research-SKILLsFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.OtherNo warnings★ 14K↓ —
- qdrant-vector-searchOrchestra-Research/AI-Research-SKILLsHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.OtherNo warnings★ 14K↓ —
- peft-fine-tuningOrchestra-Research/AI-Research-SKILLsParameter-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% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.ProductivityNo warnings★ 14K↓ —
- slides-polishwanshuiyin/Auto-claude-code-research-in-sleepPer-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic style leaks, fixes text-frame overflow, and catches per-slide layout drift. Trigger phrases: "polish slides", "slides 排版不对", "PPTX 字体太小", "和 Beamer 比一下", "per-page review", "和 codex 一页一页过".DocumentsNo warnings★ 18.1K↓ —
- eas-update-insightsexpo/skillsCheck the health of published EAS Update: crash rates, install/launch counts, unique users, payload size, and the split between embedded and OTA users per channel. Use when the user asks how an update is performing, whether a rollout is healthy, how many users are on the embedded build vs OTA, or wants to gate CI on update health.OfficialOtherNo warnings★ 3K↓ —
- hqq-quantizationOrchestra-Research/AI-Research-SKILLsHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.DevOpsNo warnings★ 14K↓ —
- proof-orchestratorwanshuiyin/Auto-claude-code-research-in-sleepManage a stateful, run-directory-based proof project: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional DeepSeek second opinion as additional evidence only. Use when the user asks for proof-run orchestration, a GPT Pro handoff, or cross-run proof continuation — use /proof-writer for ordinary proof drafting and /proof-checker for rigorous verification or submission acceptance.WritingNo warnings★ 18.1K↓ —
- mlflowOrchestra-Research/AI-Research-SKILLsTrack ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platformDevOpsNo 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↓ —
- 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↓ —
- 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↓ —
- krillinai-pipelinekrillinai/OpenCreatorUse when validating or documenting a multi-stage KrillinAI CLI output plan; the current pipeline command supports dry-run planning only, not end-to-end execution.PlanningNo warnings★ 13.9K↓ —
- 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↓ —
- krillinai-subtitlekrillinai/OpenCreatorUse when generating subtitles with KrillinAI CLI from a YouTube link, Bilibili/local video, or existing media, including platform caption download, Whisper fallback, translation, bilingual SRT, and short vertical subtitle output.MediaNo warnings★ 13.9K↓ —
- plantuml-asciigithub/awesome-copilotGenerate ASCII art diagrams using PlantUML text mode. Use when user asks to create ASCII diagrams, text-based diagrams, terminal-friendly diagrams, or mentions plantuml ascii, text diagram, ascii art diagram. Supports: Converting PlantUML diagrams to ASCII art, Creating sequence diagrams, class diagrams, flowcharts in ASCII format, Generating Unicode-enhanced ASCII art with -utxt flagPlanningNo warnings★ 40.4K↓ —
- krillinai-render-verticalkrillinai/OpenCreatorUse when rendering portrait videos with KrillinAI CLI, including converting source video to vertical format, adding short bilingual subtitles, rendering dubbed vertical videos, and checking vertical subtitle readability.MediaNo warnings★ 13.9K↓ —
- skills-managerCherryHQ/cherry-studio搜索、安装或创建 Agent Skill；用户说“find a skill”“搜索技能”“帮我做个 skill”或想扩展能力时使用。OtherNo warnings★ 53K↓ —
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