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
55,384 results · page 1142 of 1,847
- View details
ai-coding-agents-command-runtimeSkillAI & models
Lets your agent design slash-command runtimes for coding-agent CLIs, covering registries, lazy loading, and dispatch.
Ready to connect★ 88
- View details
ai-coding-agents-execution-sandboxSkillFiles & storage
Helps your agent design safe execution sandboxes for coding agents, covering isolation, filesystem rules, network policy, and destructive-command guards.
Ready to connect★ 88
- View details
ai-coding-agents-observability-evalsSkillMonitoring & ops
Helps your agent design tracing, replay, and eval systems to measure coding-agent quality, regressions, and cost.
Ready to connect★ 88
- View details
ai-coding-agents-permissionsSkillAI & models
Lets your agent design approval and permission systems for coding-agent runtimes, from tool prompts to sandbox escalation.
Ready to connect★ 88
- View details
ai-coding-agents-pluginsSkillAI & models
Lets your agent design and review plugin systems for coding-agent CLIs, including manifests, extension points, and trust boundaries.
Ready to connect★ 88
- View details
ai-coding-agents-provider-runtimeSkillAI & models
Lets your agent design the provider layer for coding agents, covering streaming, retries, and fallback routing.
Ready to connect★ 88
- View details
ai-coding-agents-release-distributionSkillAI & models
Lets your agent design how a coding-agent CLI ships and updates, covering packaging, release channels, and safe migrations.
Ready to connect★ 88
- View details
ai-coding-agents-remote-runtimeSkillAI & models
Guides your agent through designing remote execution runtimes for coding agents, covering sessions, reconnects, and permission bridging.
Ready to connect★ 88
- View details
ai-coding-agents-sessionsSkillAI & models
Helps your agent design how coding-agent sessions save, resume, and restore their state across runs.
Ready to connect★ 88
- View details
ai-coding-agents-settings-policySkillAI & models
Lets your agent design and review settings and policy layers for coding-agent runtimes, from source precedence to validation.
Ready to connect★ 88
- View details
ai-coding-agents-tasksSkillProductivity
Helps your agent design task systems for coding agents, covering task lists, background work, cancellation, and teammate coordination.
Ready to connect★ 88
- View details
ai-coding-agents-terminal-uiSkillMedia
Guides your agent in designing terminal user interfaces for coding agents, covering prompts, history, keybindings, and background tasks.
Ready to connect★ 88
- View details
ai-coding-agents-toolsSkillSearch
Lets your agent apply coding skill guidance when designing tool registries, deferred loading, and permission-aware execution.
Ready to connect★ 88
- View details
ai-data-curation-pretrainingSkillAI & models
Lets your agent build and audit LLM pretraining datasets, covering filtering, dedup, decontamination, and data mixing.
Ready to connect★ 88
- View details
ai-deep-researchSkillAI & models
Gives your agent a deep research skill for building repeatable, evidence-backed research workflows with citations.
Ready to connect★ 88
- View details
ai-distributed-trainingSkillAI & models
Guides your agent through scaling multi-GPU model training, from picking a parallelism strategy to cutting rented GPU costs.
Ready to connect★ 88
- View details
ai-integration-phaseSkillMedia
Lets your agent write an AI-SPEC.md contract covering framework choice, implementation guidance, and evaluation strategy.
Ready to connect★ 89
- View details
ai-llmSkillCloud & infra
Gives your agent an llm skill for planning, comparing, fine-tuning, and operating LLM systems from strategy to deployment.
Ready to connect★ 88
- View details
ai-llm-inferenceSkillAI & models
Guides your agent through llm inference tuning, covering batching, caching, quantization, routing, and serving stack choices.
Ready to connect★ 88
- View details
ai-local-model-opsSkillAI & models
Lets your agent set up and run local AI models on your own machine using tools like Ollama and LM Studio.
Ready to connect★ 88
- View details
ai-ml-data-scienceSkillMedia
Lets your agent run data-science projects end to end, from framing the problem to evaluating models and writing handoff reports.
Ready to connect★ 88
- View details
ai-ml-timeseriesSkillAI & models
Guides your agent through time-series forecasting: building, validating, and comparing forecast models.
Ready to connect★ 88
- View details
ai-mlopsSkillCloud & infra
Guides your agent through deploying, monitoring, and fixing production AI systems with release gates and incident plans.
Ready to connect★ 88
- View details
ai-post-trainingSkillAI & models
Lets your agent plan and run post-training for language models, choosing methods like RLHF, DPO, or GRPO.
Ready to connect★ 88
- View details
ai-pretrainingSkillAI & models
Lets your agent build a GPT-style transformer and BPE tokenizer from scratch, step by step.
Ready to connect★ 88
- View details
ai-product-operating-modelSkillAI & models
Lets your agent design an operating model for AI in product teams, covering platform ownership, data boundaries, and rollout.
Ready to connect★ 88
- View details
ai-prompt-engineeringSkillAI & models
Gives your agent a prompt engineering skill for designing, testing, and shipping reliable LLM prompts.
Ready to connect★ 88
- View details
ai-ragSkillSearch
Guides your agent through designing a RAG agent skill: picking retrieval modes, chunking, hybrid search, and evaluation.
Ready to connect★ 88
- View details
ai-scaling-lawsSkillAI & models
Lets your agent size AI models and token budgets using scaling laws like Chinchilla.
Ready to connect★ 88
- View details
ai-vector-brainSkillDatabases & data
Lets your agent build a pgvector retrieval brain for repos, docs, or policy corpora with SQL, scripts, and evals.
Ready to connect★ 88
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
55,384 of the 55,384 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 workspace 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.