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
9,019 results · page 17 of 301
- View details
qzcliSkillAI & models
Lets your agent submit, list, and stop GPU compute jobs on the Qizhi platform from the command line.
Ready to connect★ 16k
- View details
rebuttalSkillAI & models
Lets your agent draft point-by-point rebuttals to peer reviews within venue word limits.
Ready to connect★ 16k
- View details
research-refineSkillAI & models
Lets your agent turn a vague research idea into a concrete, detailed research plan through iterative review.
Ready to connect★ 16k
- View details
research-refine-pipelineSkillAI & models
Lets your agent turn a vague research idea into a focused proposal plus a detailed experiment plan in one run.
Ready to connect★ 16k
- View details
research-reviewSkillAI & models
Lets your agent request a critical external review of research papers, ideas, or experimental results.
Ready to connect★ 16k
- View details
resubmit-pipelineSkillAI & models
Lets your agent resubmit a polished paper to a new venue without new experiments or edits to prior submissions.
Ready to connect★ 16k
- View details
result-to-claimSkillAI & models
Lets your agent judge what claims finished experiment results actually support and what evidence is missing.
Ready to connect★ 16k
- View details
specification-writingSkillAI & models
Lets your agent draft a complete patent specification from your claims and invention disclosure.
Ready to connect★ 16k
- View details
vast-gpuSkillAI & models
Lets your agent rent, manage, and delete rented GPU servers on vast.ai.
Ready to connect★ 16k
- View details
writing-systems-papersSkillAI & models
Helps your agent structure a 10-12 page systems research paper with page allocation and paragraph templates.
Ready to connect★ 16k
- View details
- View details
find-similar-functionsSkillAI & models
Lets your agent search your codebase for existing similar functions before writing new JavaScript or TypeScript code.
Ready to connect★ 15k
- View details
improve-reactSkillAI & models
Has your agent audit a React codebase and write prioritized, self-contained improvement plans without touching source code.
Ready to connect★ 15k
- View details
shipSkillAI & models
Lets your agent take a finished code branch through review, commit, push, and opening a pull request.
Ready to connect★ 15k
- View details
make-custom-agentSkillAI & models
Lets your agent create and configure custom GitHub Copilot agents and chat participants.
Ready to connect★ 15k
- View details
make-skillSkillAI & models
Lets your agent create new Copilot agent skills, generating a SKILL.md file and folder structure.
Ready to connect★ 15k
- View details
migrationsSkillAI & models
Guides your agent through how EF Core database migrations work internally, like SQL generation and model diffing.
Ready to connect★ 15k
- View details
model-buildingSkillAI & models
Gives your agent guidance for editing EF Core model-building code like ConventionSet and ModelBuilder.
Ready to connect★ 15k
- View details
install-memuSkillAI & models
Lets your agent install or uninstall memU by detecting your setup and following the matching guide.
Ready to connect★ 14k
- View details
ara-rigor-reviewerSkillAI & models
Lets your agent review research artifacts and score them on six rigor dimensions with a severity-ranked report.
Ready to connect★ 13k
- View details
constitutional-aiSkillAI & models
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
Ready to connect★ 13k
- View details
distributed-llm-pretraining-torchtitanSkillAI & models
Lets your agent run large-scale distributed LLM pretraining on many GPUs using PyTorch's torchtitan.
Ready to connect★ 13k
- View details
dspySkillAI & models
Helps your agent build and auto-optimize prompt-based AI programs and RAG systems using the DSPy framework.
Ready to connect★ 13k
- View details
evaluating-llms-harnessSkillAI & models
Lets your agent test and compare language models on 60+ standard academic benchmarks like MMLU and HumanEval.
Ready to connect★ 13k
- View details
evolving-ai-agentsSkillAI & models
Gives your agent guidance on evolving and optimizing AI agents using automated, benchmark-driven improvement loops.
Ready to connect★ 13k
- View details
fine-tuning-with-trlSkillAI & models
Lets your agent fine-tune language models using reinforcement learning methods like SFT, DPO, and PPO.
Ready to connect★ 13k
- View details
guidanceSkillAI & models
Lets your agent force an AI model to output exact formats like JSON or code using grammar rules.
Ready to connect★ 13k
- View details
instructorSkillAI & models
Lets your agent turn LLM text responses into validated structured data like JSON with typed fields.
Ready to connect★ 13k
- 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
- 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
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.
54,764 of the 55,196 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.