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: Docs & knowledge
4,535 results · page 9 of 152
- View details
spec-traceSkillDocs & knowledge
Lets your agent trace a claim about web spec behaviour through the spec's algorithm chain and end with a verdict.
Ready to connect★ 13k
- View details
prompt-masterSkillDocs & knowledge
Lets your agent write, fix, and improve prompts for AI tools like image generators and coding assistants.
Ready to connect★ 13k
- View details
ara-compilerSkillDocs & knowledge
Lets your agent turn papers, code, logs, or notes into a structured research artifact with claims, concepts, and evidence.
Ready to connect★ 13k
- View details
awq-quantizationSkillDocs & knowledge
Lets your agent shrink large language models to 4-bit size so they run faster and fit in less GPU memory.
Ready to connect★ 13k
- View details
crewai-multi-agentSkillDocs & knowledge
Lets your agent run multiple specialized agents together on complex tasks with roles, memory, and step-by-step workflows.
Ready to connect★ 13k
- View details
gptqSkillDocs & knowledge
Lets your agent shrink large language models to 4-bit so they fit and run faster on consumer GPUs.
Ready to connect★ 13k
- View details
langchainSkillDocs & knowledge
Lets your agent build LLM-powered apps with agents, chains, memory, and document retrieval across many AI providers.
Ready to connect★ 13k
- View details
llama-cppSkillDocs & knowledge
Lets your agent run language models locally on Macs, CPUs, or non-NVIDIA GPUs without cloud services.
Ready to connect★ 13k
- View details
llamaindexSkillDocs & knowledge
Lets your agent index documents and answer questions over them using retrieval-augmented search.
Ready to connect★ 13k
- View details
long-contextSkillDocs & knowledge
Teaches your agent how to extend a model's context window to handle long documents up to 128k+ tokens.
Ready to connect★ 13k
- View details
optimizing-attention-flashSkillDocs & knowledge
Helps your agent speed up transformer attention and cut GPU memory use when running models with long sequences.
Ready to connect★ 13k
- View details
peft-fine-tuningSkillDocs & knowledge
Lets your agent customize large language models by training a tiny fraction of their parameters on limited GPU memory.
Ready to connect★ 13k
- View details
presenting-conference-talksSkillDocs & knowledge
Lets your agent turn a research paper into conference slides with speaker notes and a talk script.
Ready to connect★ 13k
- View details
pytorch-fsdp2SkillDocs & knowledge
Lets your agent add PyTorch FSDP2 sharding to training scripts so large models fit across multiple GPUs.
Ready to connect★ 13k
- View details
quantizing-models-bitsandbytesSkillDocs & knowledge
Guides your agent through compressing large language models to 8-bit or 4-bit so they use much less GPU memory.
Ready to connect★ 13k
- View details
sentencepieceSkillDocs & knowledge
Lets your agent break text into subword pieces using BPE or Unigram, including multilingual and CJK text.
Ready to connect★ 13k
- View details
serving-llms-vllmSkillDocs & knowledge
Lets your agent serve LLMs as an API server that handles many requests on limited GPU memory.
Ready to connect★ 13k
- View details
unslothSkillDocs & knowledge
Gives your agent expert guidance on fine-tuning language models faster with less memory using Unsloth.
Ready to connect★ 13k
- View details
writing-emdash-docsSkillDocs & knowledge
Lets your agent write, revise, and review EmDash documentation with accurate technical content and consistent style.
Ready to connect★ 12k
- View details
atlassian-mcpSkillDocs & knowledge
Lets your agent search and update Jira tickets and Confluence pages, including managing sprints and backlogs.
Ready to connect★ 11k
- View details
code-documenterSkillDocs & knowledge
Lets your agent write and check technical docs like code docstrings, API specs, and user guides.
Ready to connect★ 11k
- View details
cpp-proSkillDocs & knowledge
Lets your agent write, optimize, and debug C++ code using modern C++20/23 features and performance techniques.
Ready to connect★ 11k
- View details
rust-engineerSkillDocs & knowledge
Lets your agent write, review, and debug Rust code including ownership, lifetimes, traits, and async with tokio.
Ready to connect★ 11k
- View details
spec-minerSkillDocs & knowledge
Lets your agent extract specs, API docs, and dependency maps from undocumented codebases.
Ready to connect★ 11k
- View details
hive.context-preservationSkillDocs & knowledge
Helps your agent save key facts from tool results into notes before its memory gets trimmed.
Ready to connect★ 11k
- View details
hive.note-takingSkillDocs & knowledge
Lets your agent keep a running scratchpad of decisions, key values, and open questions so important context survives long tasks.
Ready to connect★ 11k
- View details
handoffSkillDocs & knowledge
Lets your agent write or update a handoff document so a fresh agent can pick up the work.
Ready to connect★ 10k
- View details
customizeSkillDocs & knowledge
Lets your agent configure the Feynman research workbench, including specialists, skills, connectors, and settings.
Ready to connect★ 10k
- View details
pdf-exploreSkillDocs & knowledge
Lets your agent read scientific PDFs and pull out methods, figures, tables, and citations with page references.
Ready to connect★ 10k
- View details
session-logSkillDocs & knowledge
Lets your agent write a session log summarizing completed work, findings, questions, and next steps.
Ready to connect★ 10k
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.