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.
46,100 skills from 2,198 repositories · updated 34 minutes ago
46,098 skills
- formula-derivationwanshuiyin/Auto-claude-code-research-in-sleepStructures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.ScienceNo warnings★ 18.3K↓ —
- azure-data-tables-javamicrosoft/skillsBuild table storage applications with Azure Tables SDK for Java. Use when working with Azure Table Storage or Cosmos DB Table API for NoSQL key-value data, schemaless storage, or structured data at scale.OfficialDevOpsNo warnings★ 3.2K↓ —
- 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★ 18.3K↓ —
- 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★ 18.3K↓ —
- golden-chat-emptyyusufkaraaslan/Skill_SeekersUse when testing the golden_chat_empty golden buildTestingNo warnings★ 15.2K↓ —
- meta-applywanshuiyin/Auto-claude-code-research-in-sleepPrivileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with cross-model jury and human approval at landing. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.OtherNo warnings★ 18.3K↓ —
- unslothOrchestra-Research/AI-Research-SKILLsExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimizationProductivityNo warnings★ 14.1K↓ —Also in 2 other repos
- skypilot-multi-cloud-orchestrationOrchestra-Research/AI-Research-SKILLsMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.OtherNo warnings★ 14.1K↓ —Also in 2 other repos
- ray-dataOrchestra-Research/AI-Research-SKILLsScalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.DataNo warnings★ 14.1K↓ —Also in 1 other repo
- 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★ 18.3K↓ —
- kill-argumentwanshuiyin/Auto-claude-code-research-in-sleepTwo-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.ScienceNo warnings★ 18.3K↓ —
- azure-computemicrosoft/skillsAzure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, burstable, lightweight server, website, backend, GPU, machine learning, HPC simulation, dev/test, workload, family, load balancer, Flexible orchestration, Uniform orchestration, cost estimate, capacity reservation (CRG), reserve, guarantee capacity, pre-provision, CRG association, CRG disassociation, machine enrollment (EMM), Essential Machine Management, monitor. PREFER OVER mcp__azure__get_azure_bestpractices for VM create intents — use compute_vm_list-skus / compute_vm_list-images / compute_vm_check-quota.OfficialDevOpsNo warnings★ 3.2K↓ —Also in 2 other repos
- 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★ 53.1K↓ —
- golden-pptx-kwyusufkaraaslan/Skill_SeekersUse when testing keyword categorizationDocumentsNo warnings★ 15.2K↓ —
- code-mate-qoderCherryHQ/cherry-studioRun the Qoder CLI non-interactively with structured output. Use when the user asks to delegate a coding task to Qoder.EngineeringNo warnings★ 53.1K↓ —
- wiki-enrichwanshuiyin/Auto-claude-code-research-in-sleepFill in the per-paper TODO sections of research-wiki/papers/<slug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers/ as TODO scaffolds.ScienceNo warnings★ 18.3K↓ —
- code-mate-openclawCherryHQ/cherry-studioRun the local OpenClaw agent non-interactively. Use when the user asks to delegate a bounded task to OpenClaw.EngineeringNo warnings★ 53.1K↓ —
- idea-discovery-robotwanshuiyin/Auto-claude-code-research-in-sleepWorkflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says \"robotics idea discovery\", \"机器人找idea\", \"embodied AI idea\", \"机器人方向探索\", \"sim2real 选题\", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.EngineeringNo warnings★ 18.3K↓ —
- azure-ai-vision-imageanalysis-javamicrosoft/skillsBuild image analysis applications with Azure AI Vision SDK for Java. Use when implementing image captioning, OCR text extraction, object detection, tagging, or smart cropping.OfficialDevOpsNo warnings★ 3.2K↓ —
- golden-pptxyusufkaraaslan/Skill_SeekersUse when testing the pptx golden buildDocumentsNo warnings★ 15.2K↓ —
- wiki-changelogmicrosoft/skillsAnalyzes git commit history and generates structured changelogs categorized by change type. Use when the user asks about recent changes, wants a changelog, or needs to understand what changed in the repository.OfficialEngineeringNo warnings★ 3.2K↓ —
- 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★ 14.1K↓ —
- stripe-docsstripe/aiUse when the user or agent needs to read, search, or look up Stripe documentation or API reference. Prefer this over curl or WebFetch for any docs.stripe.com content. Use to fetch gated documentation.OfficialEngineeringNo warnings★ 2K↓ —Also in 5 other repos
- security-threat-modelopenai/skillsRepository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.OfficialSecurityNo warnings★ 28.4K↓ —Also in 1 other repo
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