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.

Category: AI & models

8,700 results · page 16 of 290

  • guidanceSkillAI & models

    Lets your agent force an AI model to output exact formats like JSON or code using grammar rules.

    Ready to connect★ 13k

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

    View details
  • instructorSkillAI & models

    Lets your agent turn LLM text responses into validated structured data like JSON with typed fields.

    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 large language models with LLaMA-Factory, including QLoRA and multimodal setups.

    Ready to connect★ 13k

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

    View details
  • miles-rl-trainingSkillAI & models

    Guides your agent through setting up large-scale reinforcement learning training for big language models.

    Ready to connect★ 13k

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

    View details
  • model-mergingSkillAI & models

    Lets your agent combine several trained AI models into one new model without retraining.

    Ready to connect★ 13k

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

    View details
  • model-pruningSkillAI & models

    Lets your agent shrink large language models for faster, lighter inference without retraining.

    Ready to connect★ 13k

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

    View details
  • moe-trainingSkillAI & models

    Lets your agent train sparse Mixture of Experts AI models with less compute using DeepSpeed or HuggingFace.

    Ready to connect★ 13k

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

    View details
  • nanogptSkillAI & models

    Lets your agent read and explain a small, clean GPT implementation for learning how transformers work.

    Ready to connect★ 13k

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

    View details
  • nemo-guardrailsSkillAI & models

    Lets your agent check AI inputs and outputs for jailbreaks, toxic content, personal data, and false claims.

    Ready to connect★ 13k

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

    View details
  • nnsight-remote-interpretabilitySkillAI & models

    Lets your agent run interpretability experiments on huge AI models remotely, without needing a local GPU.

    Ready to connect★ 13k

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

    View details
  • openrlhf-trainingSkillAI & models

    Lets your agent fine-tune large language models using RLHF methods like PPO, GRPO, RLOO, and DPO.

    Ready to connect★ 13k

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

    View details
  • outlinesSkillAI & models

    Lets your agent generate AI model outputs that always follow a strict JSON, XML, or code structure.

    Ready to connect★ 13k

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

    View details
  • ray-trainSkillAI & models

    Lets your agent launch and manage machine learning training jobs across many machines, with automatic tuning and recovery.

    Ready to connect★ 13k

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

    View details
  • sglangSkillAI & models

    Lets your agent run language models faster and get structured outputs like JSON or regex-constrained text.

    Ready to connect★ 13k

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

    View details
  • simpo-trainingSkillAI & models

    Lets your agent fine-tune language models to match human preferences using a simpler, faster method than DPO.

    Ready to connect★ 13k

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

    View details
  • slime-rl-trainingSkillAI & models

    Guides your agent through RL post-training of GLM models using the slime framework with Megatron and SGLang.

    Ready to connect★ 13k

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

    View details
  • sparse-autoencoder-trainingSkillAI & models

    Guides your agent through training sparse autoencoders to break down neural network activity into interpretable features.

    Ready to connect★ 13k

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

    View details
  • training-llms-megatronSkillAI & models

    Lets your agent train large language models (2B-462B parameters) with efficient GPU parallelism strategies.

    Ready to connect★ 13k

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

    View details
  • transformer-lens-interpretabilitySkillAI & models

    Guides your agent through inspecting and editing transformer model internals to study how the model works.

    Ready to connect★ 13k

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

    View details
  • verl-rl-trainingSkillAI & models

    Guides your agent through training LLMs with reinforcement learning methods like RLHF, GRPO, and PPO using verl.

    Ready to connect★ 13k

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

    View details
  • llmSkillAI & models

    Gives your agent guidelines for using language model features inside the app.

    Ready to connect★ 12k

    github.com/elie222/inbox-zero12k stars

    View details
  • llm-testSkillAI & models

    Gives your agent guidelines for writing tests for LLM-related features.

    Ready to connect★ 12k

    github.com/elie222/inbox-zero12k stars

    View details
  • review-ai-prompt-changesSkillAI & models

    Lets your agent review changes to AI prompts and tool descriptions in a branch or PR.

    Ready to connect★ 12k

    github.com/elie222/inbox-zero12k stars

    View details
  • testingSkillAI & models

    Gives your agent guidelines for testing apps with Vitest, including unit, integration, AI tests, and LLM eval suites.

    Ready to connect★ 12k

    github.com/elie222/inbox-zero12k stars

    View details
  • sesh-modeSkillAI & models

    Guides your agent through a strict plan, write specs, test, then implement workflow for more reliable code.

    Ready to connect★ 12k

    github.com/quickwit-oss/quickwit12k stars

    View details
  • angular-architectSkillAI & models

    Lets your agent build Angular 17+ apps with standalone components, routing, NgRx state, and bundle optimizations.

    Ready to connect★ 11k

    github.com/jeffallan/claude-skills11k stars

    View details
  • api-designerSkillAI & models

    Helps your agent design REST or GraphQL APIs and write OpenAPI specifications.

    Ready to connect★ 11k

    github.com/jeffallan/claude-skills11k stars

    View details
  • chaos-engineerSkillAI & models

    Helps your agent design chaos experiments, failure injection plans, and game day runbooks for distributed systems.

    Ready to connect★ 11k

    github.com/jeffallan/claude-skills11k stars

    View details
  • embedded-systemsSkillAI & models

    Lets your agent write and debug firmware for microcontrollers like STM32 and ESP32, including RTOS and power tuning.

    Ready to connect★ 11k

    github.com/jeffallan/claude-skills11k stars

    View details
  • feature-forgeSkillAI & models

    Lets your agent run structured requirements sessions that turn feature ideas into specs, user stories, and acceptance criteria.

    Ready to connect★ 11k

    github.com/jeffallan/claude-skills11k 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.

52,524 of the 52,958 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