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
9,105 results · page 181 of 304
- View details
agents-hooksSkillAI & models
Configures Claude Code hooks and Codex hooks.json/notify callbacks. Use when adding guardrails, preflight, audit trails, worktree automation, or budget enforcement.
Ready to connect★ 87
- View details
agents-skillsSkillAI & models
Creates and audits agent skills with SKILL.md, references, scripts, and platform-scoped metadata. Use when creating, updating, or validating shared skills.
Ready to connect★ 87
- View details
agents-swarm-orchestrationSkillAI & models
Coordinates multi-agent execution across subagents, teams, and workflows. Use when planning dependency-aware fan-out, verifier passes, runtime selection, or Loop Engineering.
Ready to connect★ 87
- View details
ai-architecture-advisorSkillAI & models
Chooses among AI/ML approaches: classical ML, LLM, RAG, fine-tuning, agents, multimodal, embeddings/recsys, dense/MoE/SSM/diffusion. Use when picking or scaling an architecture.
Ready to connect★ 87
- View details
ai-coding-agentsSkillAI & models
Creates coding agents on Claude Code, Codex, and Agent SDK. Use when defining review, test, refactor, or team agents — not building a runtime.
Ready to connect★ 87
- View details
ai-coding-agents-command-runtimeSkillAI & models
Designs slash-command runtimes for coding-agent CLIs. Use when modeling command registries, lazy loading, aliases, forked commands, or remote-safe dispatch.
Ready to connect★ 87
- View details
ai-coding-agents-permissionsSkillAI & models
Designs approval and permission systems for coding-agent runtimes. Use when modeling tool approvals, plan-mode transitions, sandbox prompts, or worker permission handoffs.
Ready to connect★ 87
- View details
ai-coding-agents-pluginsSkillAI & models
Designs plugin systems for coding-agent runtimes and CLIs. Use when adding plugin manifests, extension points, built-in plugins, or reloadable agent integrations.
Ready to connect★ 87
- View details
ai-coding-agents-provider-runtimeSkillAI & models
Designs provider runtimes for coding agents. Use when modeling model abstraction, streaming semantics, tool-call normalization, retries, or fallback routing.
Ready to connect★ 87
- View details
ai-coding-agents-release-distributionSkillAI & models
Designs release and distribution systems for coding-agent CLIs. Use when modeling packaging, auto-update channels, plugin compatibility, cache migrations, or install footprints.
Ready to connect★ 87
- View details
ai-coding-agents-remote-runtimeSkillAI & models
Designs remote execution and bridge runtimes for coding agents. Use when implementing remote sessions, local-UI remote-execution, reconnect logic, or permission bridging.
Ready to connect★ 87
- View details
ai-coding-agents-sessionsSkillAI & models
Designs session lifecycle for coding-agent runtimes. Use when implementing resume, transcript restoration, checkpoint rewind, cross-worktree recovery, or session-state persistence.
Ready to connect★ 87
- View details
ai-coding-agents-settings-policySkillAI & models
Designs settings and policy layers for coding-agent runtimes. Use when modeling source precedence, managed policy, env controls, or runtime settings validation.
Ready to connect★ 87
- View details
ai-data-curation-pretrainingSkillAI & models
Builds and audits LLM pretraining corpora: extraction, filtering, dedup, decontamination, data mixing, synthetic data. Use when curating or ablating a pretraining data pipeline.
Ready to connect★ 87
- View details
ai-deep-researchSkillAI & models
Builds repeatable deep-research workflows for verified synthesis. Use when producing evidence-backed briefs, comparisons, dossiers, or research pipelines.
Ready to connect★ 87
- View details
ai-distributed-trainingSkillAI & models
Guides multi-GPU pre-training: DDP, FSDP2, ZeRO, tensor/pipeline/expert parallelism, fp8/Muon. Use when scaling a run, training MoE, or reproducing GPT-2 on rented GPUs.
Ready to connect★ 87
- View details
ai-evalsSkillAI & models
Designs trustworthy LLM, agent, responsible-AI, and multimodal evaluations. Use when measuring quality, fairness, privacy, grounding, safety, or judge reliability.
Ready to connect★ 87
- View details
ai-llm-inferenceSkillAI & models
LLM inference patterns for latency, batching, caching, quantization, routing, and serving stacks. Use when optimizing throughput, tail latency, or serving cost.
Ready to connect★ 87
- View details
ai-local-model-opsSkillAI & models
Runs local and self-hosted LLM workflows with Ollama, LM Studio, MLX, Open WebUI, llamafile, and adapters. Use when operating private model stacks.
Ready to connect★ 87
- View details
ai-ml-timeseriesSkillAI & models
Time-series forecasting with temporal validation, panel models, probabilistic forecasts, and TS foundation models. Use when modeling ordered observations.
Ready to connect★ 87
- View details
ai-post-trainingSkillAI & models
Post-training and alignment: reward modeling, RLHF/PPO, DPO/DAAs, GRPO, RLVR, RLAIF, over-optimization. Use when adapting an SFT model with preference or verifiable-reward signals.
Ready to connect★ 87
- View details
ai-pretrainingSkillAI & models
Builds a transformer/GPT and BPE tokenizer from scratch. Use when implementing autograd, self-attention, a nanoGPT-style pretraining loop, or a byte-level tokenizer.
Ready to connect★ 87
- View details
ai-product-operating-modelSkillAI & models
Designs operating models for AI in product teams. Use when planning platform ownership, provider strategy, data boundaries, evals, or sensitive-data controls.
Ready to connect★ 87
- View details
ai-prompt-engineeringSkillAI & models
Prompt engineering for production LLMs — structured outputs, evals, RAG, tool workflows, multimodal prompting, and safety. Use when designing, debugging, or shipping prompts.
Ready to connect★ 87
- View details
ai-scaling-lawsSkillAI & models
Sizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal N and D, tokens-per-parameter ratios, or over-training tradeoffs.
Ready to connect★ 87
- View details
android-clean-architectureSkillAI & models
Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.
Ready to connect★ 87
- View details
article-writingSkillAI & models
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibili
Ready to connect★ 87
- View details
benchmarkSkillAI & models
Performance baseline measurement and regression detection
Ready to connect★ 87
- View details
code-review-fixSkillAI & models
Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.
Ready to connect★ 87
- View details
compose-multiplatform-patternsSkillAI & models
Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.
Ready to connect★ 87
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.
55,111 of the 55,543 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.