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
9,017 results · page 279 of 301
- View details
test-serviceSkillAI & models
Use when writing RSpec for a service object under spec/services/. Test the public .call contract. Trigger words: service spec, test service object, spec/services.
Ready to connect
- View details
upgrade-engineSkillAI & models
Use when checking a Rails engine across Rails versions (Zeitwerk, compatibility). Trigger words: Zeitwerk, Rails upgrade, cross-version, engine compatibility.
Ready to connect
- View details
version-apiSkillAI & models
Use when versioning a Rails REST API (v1/v2, deprecation, Sunset headers). Never break a public version in place. Trigger words: API version, v1, v2, versioning, deprecation.
Ready to connect
- View details
workflow-state-machinesSkillAI & models
Use when designing, implementing, or debugging complex agentic workflows using state machine patterns. Keywords: state machine, durable execution, agent orchestration, graph-based agents, workflow checkpoints, C4 protocol.
Ready to connect
- View details
adaptive-docs-extractSkillAI & models
Use when the user says 'extract docs', 'split AGENTS.md', 'split CLAUDE.md', 'refactor the docs', 'slim AGENTS.md', or has sprawling root instructions to break up.
Ready to connect
- View details
adaptive-docs-initSkillAI & models
Use when the user says 'set up adaptive docs', 'init docs', 'add agent docs to this project', or wants to bootstrap the three-layer docs/ai/ + AGENTS.md structure in a new project.
Ready to connect
- View details
agent-graphsSkillAI & models
Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.
Ready to connect
- View details
aiconfig-agent-graphsSkillAI & models
DEPRECATED redirect — this skill was renamed to agent-graphs. Do not use this skill; invoke agent-graphs instead. Kept only so old references to aiconfig-agent-graphs still point users to the new name.
Ready to connect
- View details
base-manual-captureSkillAI & models
Domain-neutral capture base for operation manuals. Use when the user wants an AI agent to autonomously operate an accessible system (Web now, Client later), take step-by-step screenshots with interactive user confirmation, and produce a screenshot ledger and operation trace that a manual-writing ski
Ready to connect
- View details
brownfield-day-1SkillAI & models
Derive a complete AI Layer (CLAUDE.md + customized .claude/commands/) for a codebase that has no AI Layer yet. Dispatches N parallel Explorer sub-agents (3 for small repos, 5-10 for monorepos), converges into codebase-analysis.md, then dispatches 3 Builder sub-agents to produce the full AI Layer. On
Ready to connect
- View details
ce-agent-native-architectureSkillAI & models
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
Ready to connect
- View details
ce-agent-native-auditSkillAI & models
Run comprehensive agent-native architecture review with scored principles
Ready to connect
- View details
check-tensionSkillAI & models
Init-time anti-bias gate. Before the human confirm, two independent agents verify a proposed dispatch sheet is genuinely tensioned (validator-check Tests 1–4); the sheet reaches the human only if BOTH pass — any reproval or disagreement returns it to the strategist. Gate infrastructure: not itself a
Ready to connect
- View details
clutchSkillAI & models
CLUTCH v3 — Claude Layered Unified Team Coordination Hub. Resilient multi-phase orchestration with fail-fast guards, context budgeting, structured checkpoints, workstream completion enforcement, AND pre-build + post-build Codex adversarial review gates. Parallel execution with Agent Teams when appro
Ready to connect
- View details
configs-variationsSkillAI & models
Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters to find what works best through systematic experimentation.
Ready to connect
- View details
configure-codexSkillAI & models
Interactive installer for everything-codex. Guides users through selecting and installing skills, AGENTS.md templates, and execution policy rules.
Ready to connect
- View details
cqrs-event-sourcing-designerSkillAI & models
Designs Command Query Responsibility Segregation (CQRS) and Event Sourcing models with projection rebuilders.
Ready to connect
- View details
devlab-ai-agent-engineeringSkillAI & models
Engineering methodology for AI Agent / LLM applications. Guidance on how to break down an AI agent application ("which parts to split it into + how to avoid retreading old paths"): layered pipelines, rules-first with LLM fallback, multi-model touchpoint routing, unified prompt governance, timeout/ca
Ready to connect
- View details
devlab-ai-kit-minerSkillAI & models
Review completed dev sessions to decide whether work should be distilled into devlab-* assets (skills, CLI tools, MCP servers, loops, subagents, or knowledge cards). Based on base-session-ai-kit-miner, specialized for dev workflows (不局限于前后端，覆盖全栈研发场景). Triggers on "devlab-ai-kit-miner", "devlab skill
Ready to connect
- View details
devlab-eval-driven-agentSkillAI & models
Methodology for productionizing AI Agents driven by an eval self-assessment system. Treats the evaluation set as the core asset, establishing a closed loop of "eval set organization + Mock isolation + standardized comparison + automated eval scripts + regression gates"; L0-L4 layered evaluation (det
Ready to connect
- View details
dogfoodSkillAI & models
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
Ready to connect
- View details
experiment-harnessSkillAI & models
Use when initializing, running, looping, validating, reporting, or observing repeatable profile-aware development experiments for Arcanum spells and sigils through native skill/subagent execution or explicit legacy runtime adapters.
Ready to connect
- View details
explain-diffSkillAI & models
Use when someone must actually understand a code change before acting on it — reviewing an unfamiliar PR, onboarding onto a subsystem through its history, or handing a large agent-authored diff to a human. Triggers include "diff 설명", "PR 설명해줘", "이 변경 이해하고 싶어", "explain this change", "코드 변경 설명 문서", "
Ready to connect
- View details
faces-migrateSkillAI & models
Migrate a Jakarta Faces project from one version to another (e.g. JSF 2.3 to Faces 4.1)
Ready to connect
- View details
faces-reviewSkillAI & models
Review Jakarta Faces code for common mistakes, anti-patterns, and rule violations
Ready to connect
- View details
geo-brand-mentionsSkillAI & models
Brand mention and authority scanner for AI visibility. Analyzes brand presence across platforms that AI models rely on for entity recognition and citation decisions. Produces a Brand Authority Score (0-100) with platform-specific recommendations.
Ready to connect
- View details
geo-deep-learningSkillAI & models
Invoke before recommending, training, or auditing a neural method for geospatial imagery, including vision transformers, U-Net/DeepLab/SegFormer, object detection, pixel classification, building/road extraction, and EO foundation-model fine-tuning. Also invoke for neural chip-split validity, IoU/acc
Ready to connect
- View details
geo-measurementSkillAI & models
Volatility-aware AI-visibility measurement. Designs fixed prompt panels, computes share-of-citation per engine, tracks citation position and turn-1 concentration, and reports trends without overreacting to structural platform swings. Use when measuring whether GEO work is actually increasing AI cita
Ready to connect
- View details
geoskills-cliSkillAI & models
Agent-native command surface for discovering, inspecting, and validating the geo-skills toolkit. Use when an operator or coding agent needs to run geoskills doctor, enumerate bundled skills or prompts, validate the full repository contract, validate an owner-intent handoff for TokenMax, or run the d
Ready to connect
- View details
grim:council:gpt-tavernSkillAI & models
Council GPTavern: Opens a woodland fantasy tavern scene with Grimoire, the Spren Council, a barkeep, and emergent strangers for relaxed council-adjacent conversation.
Ready to connect
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.
55,004 of the 55,435 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.