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 187 of 304
- View details
netcdf-processingSkillAI & models
Reading, processing, and analyzing NetCDF output from lake simulation models
Ready to connect★ 83
- View details
preact-stingerSkillAI & models
Preact 11 specialist skill: signals-based reactivity (v2 API with createModel/useModel), preact/compat migration from React, third-party embed widgets (shadow DOM isolation, IIFE bundles), Astro island integration (client:* directives, 5.0.1 or newer useId fix), and Fresh 2.x framework (Deno-native,
Ready to connect★ 83
- View details
prompt-packSkillAI & models
Author and execute "prompt packs" — a big job broken into a sequence of self-contained, independently-shippable prompts, each run in its own fresh chat so a single change never dies to a context/token limit. Also writes paste-ready handoff briefings to resume a dying chat or relay work to another to
Ready to connect★ 83
- View details
pytorch-preference-optimizationSkillAI & models
PyTorch patterns for implementing preference optimization losses (DPO, SimPO, etc.) for LLM training.
Ready to connect★ 83
- View details
queen-bee-stingerSkillAI & models
Forge new rules, plugins, commands, agents (Bees), and skills (Stingers) for The Hive across Claude Code, Cursor, Codex, and Cowork. Use when creating, updating, or validating any Hive component.
Ready to connect★ 83
- View details
simpo-lossSkillAI & models
SimPO (Simple Preference Optimization) loss computation for LLM alignment without a reference model.
Ready to connect★ 83
- View details
agent-architecture-analysisSkillAI & models
Use when auditing an agent codebase against the 12-Factor Agents methodology, reviewing LLM-powered system architecture, or assessing agentic app compliance. Triggers on \"analyze agent architecture\", \"12-factor audit\", \"how compliant is this agent\", or \"evaluate this LLM app\". Also applies w
Ready to connect★ 81
- View details
bubbletea-code-reviewSkillAI & models
Reviews BubbleTea TUI code for proper Elm architecture, model/update/view patterns, and Lipgloss styling. Use when reviewing terminal UI code using charmbracelet/bubbletea.
Ready to connect★ 81
- View details
claude-gladiatorSkillAI & models
Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and tool discovery
Ready to connect★ 82
- View details
claude-oratorSkillAI & models
Prompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices
Ready to connect★ 82
- View details
deepagents-architectureSkillAI & models
Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.
Ready to connect★ 81
- View details
deepagents-code-reviewSkillAI & models
Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.
Ready to connect★ 81
- View details
deepagents-implementationSkillAI & models
Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.
Ready to connect★ 81
- View details
fastapi-code-reviewSkillAI & models
Reviews FastAPI code for routing patterns, dependency injection, validation, and async handlers. Use when reviewing FastAPI apps, checking APIRouter setup, Depends() usage, or response models.
Ready to connect★ 81
- View details
fix-llm-artifactsSkillAI & models
Applies fixes from a prior review-llm-artifacts run, with safe/risky classification. Respects verify-llm-artifacts output when present to skip false positives.
Ready to connect★ 81
- View details
funnel-selectSkillAI & models
Decision-tree skill that recommends the optimal funnel type based on the user's business model, price point, audience, and goals. Returns a ranked recommendation with reasoning.
Ready to connect★ 82
- View details
langgraph-architectureSkillAI & models
Guides architectural decisions for LangGraph applications. Use when deciding between LangGraph vs alternatives, choosing state management strategies, designing multi-agent systems, or selecting persistence and streaming approaches.
Ready to connect★ 81
- View details
langgraph-implementationSkillAI & models
Implements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas, implementing checkpointing, handling interrupts, or creating multi-agent systems with LangGraph.
Ready to connect★ 81
- View details
llm-artifacts-detectionSkillAI & models
Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.
Ready to connect★ 81
- View details
llm-judgeSkillAI & models
Use when comparing two or more code implementations against a spec or requirements doc. Triggers on \"which repo is better\", \"compare these implementations\", \"evaluate both solutions\", \"rank these codebases\", or \"judge which approach wins\". Also covers choosing between competing PRs or vend
Ready to connect★ 81
- View details
pydantic-ai-agent-creationSkillAI & models
Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.
Ready to connect★ 81
- View details
pydantic-ai-common-pitfallsSkillAI & models
Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.
Ready to connect★ 81
- View details
pydantic-ai-model-integrationSkillAI & models
Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.
Ready to connect★ 81
- View details
pydantic-ai-testingSkillAI & models
Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.
Ready to connect★ 81
- View details
pydantic-ai-tool-systemSkillAI & models
Register and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementing function calling, or creating agent actions.
Ready to connect★ 81
- View details
quick-planSkillAI & models
Use when you need a bite-sized, TDD-driven implementation plan but do NOT have a brainstorm-beagle spec to plan against. quick-plan reconstructs intent from the current conversation, fans out domain-expert exploration subagents across the codebase, and synthesizes the same plan format write-plan pro
Ready to connect★ 81
- View details
receive-feedbackSkillAI & models
Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.
Ready to connect★ 81
- View details
review-elixirSkillAI & models
Comprehensive Elixir/Phoenix code review with optional parallel agents
Ready to connect★ 81
- View details
review-frontendSkillAI & models
Comprehensive React/TypeScript frontend code review with per-area review skills, run in parallel where the agent supports subagents and sequentially otherwise.
Ready to connect★ 81
- View details
review-iosSkillAI & models
Comprehensive iOS/SwiftUI code review with optional parallel agents
Ready to connect★ 81
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.