Skills.

Give your AI a better way to work.

A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.

Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.

Filter by category

54,221 results · page 113 of 1,808

  • evaluating-code-modelsSkillMonitoring & ops

    Lets your agent benchmark code generation models on HumanEval, MBPP, MultiPL-E, and other coding tests.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • evaluating-cosmos-policySkillWeb & browsing

    Lets your agent run NVIDIA Cosmos Policy robot-manipulation evaluations in LIBERO and RoboCasa GPU simulations.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • evaluating-llms-harnessSkillAI & models

    Lets your agent run standardized benchmark tests like MMLU and GSM8K to measure how well a language model performs.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • evolving-ai-agentsSkillAI & models

    Gives your agent guidance on automatically improving and optimizing other AI agents using evolution algorithms.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • experiment-tracking-swanlabSkillMonitoring & ops

    Guides your agent in logging ML experiment runs, metrics, and media to SwanLab dashboards.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • faissSkillSearch

    Lets your agent search billions of vectors for similar items using Facebook's FAISS library.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • fine-tuning-openvla-oftSkillDev tools

    Lets your agent fine-tune and evaluate OpenVLA robot policies for action generation on LIBERO and ALOHA setups.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • fine-tuning-serving-openpiSkillDatabases & data

    Lets your agent fine-tune and run pi0 robot policy models on custom datasets using JAX or PyTorch.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • fine-tuning-with-trlSkillAI & models

    Lets your agent fine-tune language models with reinforcement learning methods like SFT, DPO, and PPO.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • gguf-quantizationSkillCloud & infra

    Lets your agent convert AI models to the GGUF format and compress them so they run fast on ordinary laptops or Macs without a GPU.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • gptqSkillDocs & knowledge

    Lets your agent compress large language models to 4-bit so they fit and run fast on consumer GPUs.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • grpo-rl-trainingSkillProductivity

    Guides your agent through fine-tuning language models with GRPO reinforcement learning using the TRL library.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • guidanceSkillAI & models

    Lets your agent force an LLM to produce output that exactly matches formats like JSON, emails, or dates using regex and grammar rules.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • hqq-quantizationSkillDatabases & data

    Lets your agent compress large language models to 4/3/2-bit precision without calibration data.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • huggingface-accelerateSkillDev tools

    Lets your agent convert PyTorch training scripts to run distributed on multiple GPUs with a few lines of code.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • huggingface-tokenizersSkillDev tools

    Lets your agent tokenize text quickly and train custom tokenizers for NLP work.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • implementing-llms-litgptSkillFiles & storage

    Lets your agent implement, download, and fine-tune open-source LLMs like Llama and Phi using LitGPT.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • instructorSkillAI & models

    Lets your agent turn free-form LLM responses into validated, structured data using Pydantic schemas with automatic retries.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • knowledge-distillationSkillCloud & infra

    Guides your agent through training smaller language models to copy the behavior of larger ones, cutting inference costs.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • langchainSkillDocs & knowledge

    Helps your agent write LLM applications with agents, chains, and RAG pipelines using the LangChain framework.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • langsmith-observabilitySkillDatabases & data

    Lets your agent trace, evaluate, and monitor language model calls to debug and test AI applications.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • llama-cppSkillDocs & knowledge

    Lets your agent run language models locally on CPUs, Apple Silicon, and AMD/Intel GPUs without NVIDIA hardware.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • llama-factorySkillAI & models

    Gives your agent expert guidance for fine-tuning LLMs with LLaMA-Factory, including WebUI, QLoRA and multimodal setups.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • llamaindexSkillDocs & knowledge

    Helps your agent load documents, build searchable indexes, and answer questions over them using retrieval-augmented generation.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • llavaSkillMedia

    Lets your agent answer questions about images and have multi-turn picture conversations using an open vision-language model.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • long-contextSkillDocs & knowledge

    Guides your agent to extend transformer context windows using RoPE, YaRN, ALiBi, and position interpolation for long documents.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • mamba-architectureSkillMedia

    Helps your agent build and run Mamba state-space language models with linear complexity, fast inference, and long sequences.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • miles-rl-trainingSkillAI & models

    Gives your agent guidance for running large reinforcement learning training jobs with the miles framework.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • ml-paper-writingSkillDev tools

    Lets your agent draft ML research papers and verify citations for top AI conferences.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details
  • mlflowSkillCloud & infra

    Lets your agent track machine learning experiments, log metrics and models, and manage model versions and deployments.

    Ready to connect★ 13k

    github.com/orchestra-research/ai-research-skills13k stars

    View details

What is a skill?

A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.

53,789 of the 54,221 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.

Install one and every AI you use gets it

Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.

Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.

See how to connect your AI