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.
47,303 skills from 2,272 repositories · updated 7 minutes ago
47,303 skills
- cli-creatoropenai/skillsBuild a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.OfficialEngineeringNo warnings★ 28.4K↓ —Also in 1 other repo
- invention-structuringwanshuiyin/Auto-claude-code-research-in-sleepStructure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a patent-ready structure.OtherNo warnings★ 18.2K↓ —
- auto-review-loop-llmwanshuiyin/Auto-claude-code-research-in-sleepAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".EngineeringNo warnings★ 18.2K↓ —
- saveAgriciDaniel/claude-obsidianSave a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation, save this analysis, keep this insight, preserve this chat result.PlanningNo warnings★ 15.9K↓ —
- azure-mgmt-apimanagement-pymicrosoft/skillsAzure API Management SDK for Python. Use for managing APIM services, APIs, products, subscriptions, and policies. Triggers: "azure-mgmt-apimanagement", "ApiManagementClient", "APIM", "API gateway", "API Management".OfficialDevOpsNo warnings★ 3.2K↓ —
- llavaOrchestra-Research/AI-Research-SKILLsLarge Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.MediaNo warnings★ 14K↓ —
- cloudflarecloudflare/skillsDiscover and choose Cloudflare products for apps, APIs, AI agents, storage, networking, and security. Use for architecture and product selection, including when the user describes a need without naming a Cloudflare product; then find the relevant skill or documentation.OfficialDevOpsNo warnings★ 3.2K↓ —
- workers-profilingcloudflare/skillsProfile or debug CPU usage and memory allocation in deployed Cloudflare Workers and Durable Objects. Then use this information to optimize your code.OfficialDevOpsNo warnings★ 3.2K↓ —
- wranglercloudflare/skillsRun or troubleshoot Wrangler CLI commands in projects that have a wrangler.jsonc, wrangler.json, or wrangler.toml file, including local development, Previews, deployment, and resource management. For new projects and projects without a Wrangler configuration file, use the cf CLI instead.OfficialDevOpsNo warnings★ 3.2K↓ —
- web-perfcloudflare/skillsAudit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.OfficialOtherNo warnings★ 3.2K↓ —
- 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↓ —
- verl-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.DevOpsNo warnings★ 14K↓ —
- code-mate-hermesCherryHQ/cherry-studioRun Hermes Agent non-interactively for local coding tasks. Use when the user asks to delegate work to Hermes.EngineeringNo warnings★ 53K↓ —
- 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↓ —
- wiki-queryAgriciDaniel/claude-obsidianAnswer an explicitly vault-scoped question from an Obsidian wiki without changing it. Use when the user selects the vault as the evidence source: query the wiki, query quick, query deep, explain from the wiki, summarize the vault, find in wiki, search the wiki, or based on the wiki. Do not route ordinary general-knowledge questions here.ProductivityNo warnings★ 15.9K↓ —
- langchainOrchestra-Research/AI-Research-SKILLsFramework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.DevOpsNo 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↓ —
- paper-writingwanshuiyin/Auto-claude-code-research-in-sleepWorkflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished, submission-ready PDF. Use when user says \"写论文全流程\", \"write paper pipeline\", \"从报告到PDF\", \"paper writing\", or wants the complete paper generation workflow.ScienceNo warnings★ 18.2K↓ —
- stripe-paystripe/aiHelps users send funds to another Stripe business, transfer money to a Stripe Profile handle or network ID, or ask whether an agent can pay a Stripe business. Use Stripe Directory to find or verify a recipient when the user doesn't provide an exact Stripe Profile handle or network ID.OfficialOtherNo warnings★ 2K↓ —Also in 4 other repos
- 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
- weights-and-biasesOrchestra-Research/AI-Research-SKILLsTrack ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platformOtherNo warnings★ 14K↓ —Also in 1 other repo
- 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★ 53K↓ —
- proof-orchestratorwanshuiyin/Auto-claude-code-research-in-sleepManage a stateful, run-directory-based proof project with Codex: 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★ 18.2K↓ —
- writing-systems-paperswanshuiyin/Auto-claude-code-research-in-sleepParagraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says "写系统论文", "systems paper structure", "OSDI paper", "SOSP paper", or wants fine-grained structural guidance for a systems conference submission.WritingNo warnings★ 18.2K↓ —
verl-rl-training
Orchestra-Research/AI-Research-SKILLs
DevOpsUpdated Oct 11, 2026
From the author
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill verl-rl-training -a claude-code
Installs to .claude/skills/verl-rl-training/ · 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/api-reference.md
- references/troubleshooting.md