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
8,898 results · page 296 of 297
- View details
skill-issueSkillAI & models
Triggers when an agent authors, reviews, names, or decides whether to create an agent skill, including requests to write SKILL.md, choose a skill type, evaluate skill-worthy content, or split material into references/scripts. Not for running skill evaluations or description optimization, which belon
Ready to connect
- View details
soc-integrationSkillAI & models
Use when composing an SoC from peripherals and a bus fabric, or when generating device trees, ACPI tables, docs, or pin lists from a hardware description and they keep drifting out of sync
Ready to connect
- View details
soundsSkillAI & models
Manage Claude Code and Codex sound feedback. Select sound packs, enable or disable sounds, adjust volume, play test sounds, and view status.
Ready to connect
- View details
spring-boot-modulithSkillAI & models
Spring Modulith 2.0 implementation for bounded contexts in Spring Boot 4. Use when structuring application modules, implementing @ApplicationModuleListener for event-driven communication, testing with Scenario API, enforcing module boundaries, externalizing events to Kafka/AMQP, building a modular m
Ready to connect
- View details
spring-boot-verifySkillAI & models
Verify Spring Boot 4.x projects for correct dependencies, configuration, and migration readiness. Use when analyzing pom.xml, build.gradle, application.yml, discussing Spring Boot project setup, dependency versions, configuration validation, version compatibility, migration to Spring Boot 4, depreca
Ready to connect
- View details
spring-boot-web-apiSkillAI & models
Spring Boot 4 REST API implementation patterns. Use when creating REST controllers, REST endpoints, request validation, exception handlers with ProblemDetail (RFC 9457), API versioning, content negotiation, WebFlux reactive endpoints, HTTP clients with @HttpExchange, JSON serialization with Jackson
Ready to connect
- View details
spring-refreshSkillAI & models
Check Spring Boot skill content freshness against latest research and flag skills needing updates. Use when running /spring-refresh, or when user mentions "refresh spring skills", "spring boot update check", "skill freshness", "stale spring content", "update spring boot skills".
Ready to connect
- View details
suika-scatter-gather-planningSkillAI & models
Decompose one bounded deliverable into genuinely independent work packets, give each packet an ownership and evidence contract, and recombine the results through an explicit merge order and integrated acceptance check. Use for parallel contributors, subagents, multi-package changes, or large work wi
Ready to connect
- View details
support-signalSkillAI & models
Cluster a batch of support tickets or threads into ranked product themes, then hand them to product-signal for the roadmap. Trigger when there's a pile of support tickets, or the user says "what are the tickets telling us", "cluster these tickets", "support themes", "top issues this month", or wants
Ready to connect
- View details
synapse-reinstSkillAI & models
Re-inject Synapse A2A initial instructions after context has been cleared. Use this skill when the agent has lost its identity, A2A communication protocol, or configuration after /clear or context reset, when synapse send/reply commands stop working, or when the agent no longer recognizes its SYNAPS
Ready to connect
- View details
trend-huntingSkillAI & models
Identifies emerging trends in the niche using Claude + Twitter/X + Apify. Maps viral formats (Reels, carousels, threads), detects timing before saturation, generates 2+ hook variations and identifies the winner by engagement. Output: actionable trends report + ready-to-test variations
Ready to connect
- View details
using-arkhe-skillsSkillAI & models
Use when starting any conversation - establishes how arkhe skills bootstrap on Claude Code, Antigravity CLI (agy) / Gemini CLI, and Codex CLI, and maps Claude-only tools (AskUserQuestion, TaskCreate, EnterPlanMode, the Skill tool, the Agent tool) to their cross-platform equivalents
Ready to connect
- View details
are-dashboardSkillAI & models
Show telemetry dashboard (costs, tokens, traces) (experimental)
Ready to connect
- View details
- View details
are-specifySkillAI & models
Generate project specification from AGENTS.md docs (experimental)
Ready to connect
- View details
bumpSkillAI & models
Bump version, update CHANGELOG.md and README.md, then tag and release on GitHub
Ready to connect
- View details
capshelfSkillAI & models
Use the capshelf CLI to manage shared skills, Pi extensions, subagents, settings, and MCP configs across multiple projects from a user-owned data repo.
Ready to connect
- View details
capstone-radarSkillAI & models
Unified A-F grading and ship/no-ship decisions for the 6-skill radar family (5 companions + capstone). Aggregates handoffs from data-model, ui-path, roundtrip, time-bomb, and ui-enhancer; owns 5 grep-reliable domains; tracks velocity; celebrates improvements. Triggers: "capstone radar", "can I ship"
Ready to connect
- View details
clawchat-liveware-sampleSkillAI & models
Use when the owner talks about the auto-installed "Liveware Sample" (page title "Hello from your agent") — the guide to their first Liveware. The page sends the owner to chat with these exact sentences, so route on them verbatim — "把 Liveware Sample 换成购物清单" / "把 Liveware Sample 换成纪念日倒计时" / "把 Livewa
Ready to connect
- View details
data-model-radarSkillAI & models
Audits SwiftData/Core Data model layer for field completeness, serialization gaps, relationship integrity, semantic ambiguity, dead fields, and migration safety. Finds model-layer bugs that manifest as workflow bugs. Triggers: "audit models", "model radar", "/data-model-radar".
Ready to connect
- View details
entropy-box-zhSkillAI & models
Centers on Entropy Box solution consulting (Consult): turns well-scoped embodied AI technical requirements into candidate implementation approaches and well-grounded engineering workflows. The current LLM first clarifies and breaks down broad requirements, then consults on each sub-problem individua
Ready to connect
- View details
excessive-agencySkillAI & models
Detects autonomous agents that take irreversible or high-impact actions
Ready to connect
- View details
llm-supply-chainSkillAI & models
Detects compromised or backdoored models loaded from unverified sources,
Ready to connect
- View details
local-ai-filmSkillAI & models
Produce AI short films (atmosphere pieces / mood pieces / trailers / vlogs / narrative films with dialogue) using local or cloud models. Directing hub entry point: manages go/no-go decisions, anti-homogenization, pitfall avoidance, execution workflow, and final post-production assembly. Trigger scen
Ready to connect
- View details
majority-minority-changeSkillAI & models
This skill should be used when users need to analyze county-level racial composition change between two Census snapshots and identify where places crossed a majority-minority threshold.
Ready to connect
- View details
model-dosSkillAI & models
Detects LLM endpoints missing token caps, rate limits, or prompt-length
Ready to connect
- View details
onescience-modelscope-publishSkillAI & models
OneScience ModelScope model publishing skill. Reorganizes paper-reproduction model artifacts into the standard ModelScope directory structure, checks the completeness of core directory contents, generates the configuration templates and audit tools required by the platform, and outputs the modelscop
Ready to connect
- View details
onescience-primitivesSkillAI & models
OneScience primitives resource recall skill. Retrieves relevant primitive resources (models, components, data pipelines, applications, visualization specs, workflow plans, contracts, etc.) based on natural language requirements, recalling them via scope determination, fast filtering, and semantic ma
Ready to connect
- View details
onescience-trainerSkillAI & models
OneScience scientific model training execution skill. Used when the user wants to plan, generate, and execute model training workflows based on text instructions, web instructions, local project paths, existing checkpoints, or a project's native training entry point, covering domains such as meteoro
Ready to connect
- View details
opentiny-next-app-integrationSkillAI & models
Use when an existing Vue 3 + Vite app needs OpenTiny TinyRobot Chat, GenUI, business WebMCP, business Skill, or PageTool integration and the installed APIs, ownership boundaries, or validation scope must be established from the project.
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.
53,789 of the 54,221 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.