Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
notification-trigger
Triggers notifications exclusively for VERY IMPORTANT priority tasks that are incomplete and due within 6 hours. Repeats every 10 minutes with duplicate prevention tracking in memory. Clears tracking when tasks complete or due times pass.
majiayu000/claude-skill-registry 163
-
manage-react-hook-tests
Create or update test files for React hooks. Use when user asks to "create hook tests", "test useMyHook", "generate tests for hook", "update hook tests", or mentions needing tests for a React hook. Generates vitest test files with renderHook, Fake context providers, and proper test structure.
majiayu000/claude-skill-registry 163
-
devcom
Invoke DEVCOM_RESEARCH for deep research, cross-disciplinary analysis, and novel problem solving. Use when exploring cutting-edge concepts or investigating patterns that require theoretical foundation.
majiayu000/claude-skill-registry 163
-
workflow-execution-rules
Execution workflow preferences including no dev servers, read-only information gathering, real data over mocks, and proper error handling over fallbacks. Use when executing code, running servers, testing, or handling data.
majiayu000/claude-skill-registry 163
-
markdown-tasks
Work with markdown-based task lists in .llm/todo.md files. Use when managing tasks, working with todo lists, extracting incomplete tasks, marking tasks complete, or implementing tasks from a task list.
majiayu000/claude-skill-registry 163
-
moai-design-systems
Design system patterns, W3C DTCG 2025.10 token architecture, WCAG 2.2 accessibility standards, and Figma MCP workflows for consistent, accessible UI development
majiayu000/claude-skill-registry 163
-
learning-capture
Recognize and capture reusable patterns, workflows, and domain knowledge from work sessions into new skills. Use when completing tasks that involve novel approaches repeated 2+ times, synthesizing complex domain knowledge across conversations, discovering effective reasoning patterns, or developing workflow optimizations. Optimizes for high context window ROI by identifying patterns that will save 500+ tokens per reuse across 10+ future uses.
majiayu000/claude-skill-registry 163
-
deployment-orchestrator
Automated deployment orchestration supporting multiple environments, infrastructure as code, CI/CD pipeline management, rollback procedures, and monitoring integration. Use when Claude needs to manage deployments, configure infrastructure, orchestrate release processes, or ensure deployment reliability across different environments.
majiayu000/claude-skill-registry 163
-
nuxt
Nuxt full-stack Vue framework with SSR, auto-imports, and file-based routing. Use when working with Nuxt apps, server routes, useFetch, middleware, or hybrid rendering.
majiayu000/claude-skill-registry 163
-
groups
Problem-solving strategies for groups in abstract algebra
majiayu000/claude-skill-registry 163
-
scalable-routing-and-code-splitting
Design routing and code-splitting strategies that scale to large applications with minimal load-time overhead.
majiayu000/claude-skill-registry 163
-
posthog-common-errors
Diagnose and fix PostHog common errors and exceptions.
Use when encountering PostHog errors, debugging failed requests,
or troubleshooting integration issues.
Trigger with phrases like "posthog error", "fix posthog",
"posthog not working", "debug posthog".
majiayu000/claude-skill-registry 163
-
documentation-structure-validator
Validate documentation structure, check for missing sections, verify markdown syntax, ensure consistency with templates. Use when user mentions docs validation, structure check, README review, documentation quality, or wants to verify documentation completeness.
majiayu000/claude-skill-registry 163
-
fiction
This skill should be used when the user asks to "write a chapter", "write prose", "continue the story", "develop a character", "review my chapter", "critique my manuscript", "write a synopsis", "summarize my story", "plan my novel", "outline my book", "check for consistency", or mentions fiction writing, novels, short stories, scenes, or narrative craft.
majiayu000/claude-skill-registry 163
-
thanos-harness
Route all OpenClaw user messages through Thanos orchestration.
majiayu000/claude-skill-registry 163
-
ai-model-web
Use this skill when developing browser/Web applications (React/Vue/Angular, static websites, SPAs) that need AI capabilities. Features text generation (generateText) and streaming (streamText) via @cloudbase/js-sdk. Built-in models include Hunyuan (hunyuan-2.0-instruct-20251111 recommended) and DeepSeek (deepseek-v3.2 recommended). NOT for Node.js backend (use ai-model-nodejs), WeChat Mini Program (use ai-model-wechat), or image generation (Node SDK only).
majiayu000/claude-skill-registry 163
-
scienceworld-planting-operation
Plants seeds into prepared containers with soil to initiate plant growth. Execute this when you have both seeds and properly prepared planting containers available. This skill handles the specific action pattern of transferring seeds from storage to growth containers to begin cultivation processes.
majiayu000/claude-skill-registry 163
-
fun-mode
Use when starting a session and wanting creative engagement, or when user says '/fun' or asks for a persona
majiayu000/claude-skill-registry 163
-
openai-image-gen
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
majiayu000/claude-skill-registry 163
-
infographic-syntax-generator
Generate AntV Infographic syntax outputs. Use when asked to turn user content into the Infographic DSL (template selection, data structuring, theme), or to output `infographic <template>` plain syntax.
majiayu000/claude-skill-registry 163
-
scholar-evaluation
Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.
majiayu000/claude-skill-registry 163
-
multi-model-research
Orchestrate multiple frontier LLMs (Claude, GPT-5.1, Gemini 3.0 Pro, Perplexity Sonar, Grok 4.1) for comprehensive research using LLM Council pattern with peer review and synthesis
majiayu000/claude-skill-registry 163
-
security-headers-configuration
Configures HTTP security headers to protect against XSS, clickjacking, and MIME sniffing attacks. Use when hardening web applications, passing security audits, or implementing Content Security Policy.
majiayu000/claude-skill-registry 163
-
miniapp-edit-testing
Test and debug the Dashboard “Edit with AI” mini-app editor flow (start edit session, build, history, close session) and write automated tests that simulate agent-driven mini-app edits like adding dark mode.
majiayu000/claude-skill-registry 163