Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
agentuity-cli-cloud-stream-delete
Delete a stream by ID (soft delete). Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
ux-researcher
Expert in understanding user behaviors, needs, and motivations through qualitative and quantitative research methods to drive user-centered design.
majiayu000/claude-skill-registry 163
-
aws-strands
Build AI agents with Strands Agents SDK. Use when developing model-agnostic agents, implementing ReAct patterns, creating multi-agent systems, or building production agents on AWS. Triggers on Strands, Strands SDK, model-agnostic agent, ReAct agent.
majiayu000/claude-skill-registry 163
-
Agent Creating
Used to create a new agent. Used when a user wants to create a new agent
majiayu000/claude-skill-registry 163
-
ci-operations
CI provider abstraction with unified API for GitHub and GitLab operations (PR, issues, CI status)
majiayu000/claude-skill-registry 163
-
policyengine-data-testing
Testing patterns for PolicyEngine data generation pipelines (policyengine-us-data, policyengine-uk-data)
majiayu000/claude-skill-registry 163
-
00-finalize-llmops-skill
Consolidate all Part 8 skills into a production-ready llmops-fine-tuner skill
majiayu000/claude-skill-registry 163
-
prowler-ci
Helps with Prowler repository CI and PR gates (GitHub Actions workflows). Trigger: When investigating CI checks failing on a PR, PR title validation, changelog gate/no-changelog label, conflict marker checks, secret scanning, CODEOWNERS/labeler automation, or anything under .github/workflows.
majiayu000/claude-skill-registry 163
-
aico-backend-task-breakdown
Break down PM story into independent backend task files following LAYERED ARCHITECTURE order: Types → Database → Repository → Service → API → Tests.
UNIQUE VALUE: Creates independent task files (story-{name}-{n}-{task}.md) for each task. Tasks are ordered by backend architecture layers.
Use this skill when:
- Running /backend.tasks command
- User asks to "break down story", "create backend tasks", "split into tasks"
- Have story at docs/reference/pm/stories/ and need organized task files
- Need tasks ordered by backend architecture layers (not random order)
- Starting backend work and want organized task list
Task order is CRITICAL: Setup → Static UI → Dynamic → Interactions → Tests
Output: Create multiple files in docs/reference/backend/tasks/ with story- prefix
majiayu000/claude-skill-registry 163
-
audit_logging
Ensure every critical action is logged (vital for UAG/Trust Room).
majiayu000/claude-skill-registry 163
-
tizen-app-scaffold
Generates secure Tizen app projects (native/web/.NET) with privilege declarations, SMACK labels, and secure storage templates pre-configured.
majiayu000/claude-skill-registry 163
-
design-init
Initialize new design documentation from templates. Use when creating new design docs, documenting new systems, starting architecture documentation, or setting up design docs for a new module.
majiayu000/claude-skill-registry 163
-
ha-operations
Interact with Home Assistant in the network infrastructure setup. Provides guidance for
API access, health checks, sending notifications, and calling services via REST API.
Use when working with Home Assistant, checking HA health, sending HA notifications,
calling HA services, or troubleshooting "Home Assistant returns 405", "HA health check
failing", "can't access HA API", or "HA notifications not working". Covers the critical
fact that HA only supports GET requests (HEAD returns 405 which is EXPECTED), HA is an
external server at 192.168.68.123:8123 (not a Docker container), requires long-lived
access tokens for API access, and is protected by Cloudflare Access (Google OAuth).
Works with Home Assistant REST API, curl, and notification services.
majiayu000/claude-skill-registry 163
-
idb-state-persistence
IndexedDB patterns for local-first state persistence using the idb library. Use when implementing features that require persistent state across navigation and sessions. Covers data modeling, defaults, CRUD operations, state managers, and reset patterns. Integrates with web-components for reactive UI updates.
majiayu000/claude-skill-registry 163
-
Testing Blocks
Guide for testing code changes in AEM Edge Delivery projects including blocks, scripts, and styles. Use this skill after making code changes and before opening a pull request to validate functionality. Covers unit testing for utilities and logic, browser testing with Playwright/Puppeteer, linting, performance validation, and guidance on which tests to maintain vs use as throwaway validation.
majiayu000/claude-skill-registry 163
-
pwa-development
Progressive Web App development for installable, offline-capable web applications. Use when building PWAs, implementing service workers, or creating offline-first experiences.
majiayu000/claude-skill-registry 163
-
domain-name-generator
Generate creative domain names and check availability for branding, startups, and web projects
majiayu000/claude-skill-registry 163
-
service
Manage UnaMentis services via USM API (never via bash kill commands)
majiayu000/claude-skill-registry 163
-
playwright-writing
Write reliable Playwright E2E tests following official best practices. Prioritizes user-facing locators, web-first assertions, and test isolation. NEVER mock application data. Avoid explicit waits unless component-specific. Use when writing, reviewing, or debugging Playwright tests.
majiayu000/claude-skill-registry 163
-
clojure-ring-spec
Ring specification for HTTP server applications in Clojure. Use when working with: (1) Ring handlers (sync or async), (2) Ring request maps and their keys, (3) Ring response maps and their keys, (4) Ring middleware, (5) Ring adapters, (6) WebSocket responses and listeners, or when questions mention Ring spec, handler signatures, request/response map structure, or Ring protocols.
majiayu000/claude-skill-registry 163
-
moai-lang-kotlin
Kotlin 2.0+ development specialist covering Ktor, coroutines, Compose Multiplatform, and Kotlin-idiomatic patterns. Use when building Kotlin server apps, Android apps, or multiplatform projects.
majiayu000/claude-skill-registry 163
-
understand
深度分析当前项目的架构、Agent 配置及 MCP 集成，生成中文架构文档。
majiayu000/claude-skill-registry 163
-
model-explainability-tool
Build model explainability tool operations. Auto-activating skill for ML Training.
Triggers on: model explainability tool, model explainability tool
Part of the ML Training skill category. Use when working with model explainability tool functionality. Trigger with phrases like "model explainability tool", "model tool", "model".
majiayu000/claude-skill-registry 163
-
evaluating-new-technology
Create a Technology Evaluation Pack (problem framing, options matrix, build vs buy, pilot plan, risk review, decision memo). Use for evaluating new tech, emerging technology, AI tools, vendor selection, and tech stack decisions.
majiayu000/claude-skill-registry 163