Top Agent Skills

Expert tmux session, window, and pane management for terminal multiplexing, persistent remote workflows, and shell scripting automation.

Documentation and capabilities reference for Daily

Vector-powered CLI for semantic file search with a Claude/Codex skill

Guide for continuous improvement, error proofing, and standardization. Use this skill when the user wants to improve code quality, refactor, or discuss process improvements.

GDB debugging assistant for AI agents - analyze core dumps, debug live processes, investigate crashes and deadlocks with source code correlation

Write idiomatic PHP code with generators, iterators, SPL data structures, and modern OOP features. Use PROACTIVELY for high-performance PHP applications.

Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.

Practical patterns for using fp-ts with React - hooks, state, forms, data fetching. Works with React 18/19, Next.js 14/15.

Analyze and optimize individual pages for conversion performance.

Deep single-page SEO analysis covering on-page elements, content quality, technical meta tags, schema, images, and performance. Use when user says "analyze this page", "check page SEO", or provides a single URL for review.

Deploy web apps with backend APIs, database, and file storage. Use when the user asks to deploy or publish a website or web app and wants a public URL. Uses HTTP API via curl.

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files

Stop throwing everywhere - handle errors as values using Either and TaskEither for cleaner, more predictable code

Create and optimize popups, modals, overlays, slide-ins, and banners to increase conversions without harming user experience or brand trust.

Build full-stack web applications with SvelteKit — file-based routing, SSR, SSG, API routes, and form actions in one framework.

Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy. Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping.

Add persistent, intelligent memory to AI agents with Mem0 — add/search/update/delete memories per user/agent/session, supports vector + graph + key-value storage, integrates with LangChain, CrewAI, OpenAI Assistants, and any LLM.

Design and implement ML operations — model registry, serving patterns, deployment strategies (shadow/canary/blue-green), drift detection, feature stores, retraining triggers, and prediction monitoring. Use when asked to "deploy a model", "model registry", "MLflow", "feature store", "drift detection", "retrain trigger", "shadow mode", "model versioning", "serving infrastructure", or "ML pipeline". Do NOT use for: prompt engineering or RAG pipelines — see prompt-engineering and rag-architect skills. Do NOT use for: general API deployment without an ML component.

Use when asked to set up AI agent templates with coordinator mode, implement persistent agent memory, compress context for long-running agents, build multi-agent workflows with skills/agents/workflows structure, or use the .agents/ folder convention for AI-native editors. Triggers on: 'ag-kit', 'antigravity kit', 'coordinator mode agent', 'persistent agent memory', 'context compression agent', 'agent workflow template', 'multi-agent coordinator', '.agents folder', 'agent skills workflows', 'ag kit init', 'template đa agent', 'bộ nhớ agent lâu dài'.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Call 100+ LLMs through a single OpenAI-compatible interface with LiteLLM — use completion/acompletion/embedding with any provider (Anthropic, OpenAI, Google, Groq, Ollama, etc.), run a proxy server for team rate-limiting and cost tracking, load-balance across providers.

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.

ByteDance's open-source super agent harness — spawns parallel sub-agents, Docker sandbox execution, persistent long-term memory, modular skills (research/report/slides). Built on LangChain + LangGraph. Triggers on: 'deerflow', 'deer-flow', 'bytedance agent', 'super agent harness', 'LangGraph agent orchestration', 'multi-hour agent tasks', 'spawn sub-agents', 'agent sandbox docker', 'persistent agent memory', 'agent skills system', 'AI research orchestrator', 'long-running agent tasks', 'agent with memory', 'langgraph orchestrator', 'IM channel agent integration'.

Default entry point for any research request — a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants for NIH funding, litreview for academic literature, syllabus for course reading, patent for prior-art + IP landscape, dossier for entity research) or runs its own plan-decompose-multi-source-search-synthesize-cite fallback workflow when no specialist matches. Always surfaces the routing decision so users can override. Triggers — "research [topic]", "look into [topic]", "what do we know about [topic]", "investigate [topic]", "find me information on [topic]", "do some research on [topic]", "I need to understand [topic]", or any research request that doesn't obviously match a more-specific specialist skill. Output is a markdown briefing (default) or .docx document (on request) with full citations and an audit log.

Query the Yana AI codebase knowledge graph via codebase-memory-mcp. Use instead of grep/glob when exploring call chains, finding callers/callees, understanding architecture, or tracing impact of changes. Triggers on: 'who calls X', 'trace path', 'find callers', 'search graph', 'cbm', 'knowledge graph', 'what calls', 'call chain', 'what uses', 'where is X defined', 'architecture overview', 'impact of changing'.

Evidence-first mailbox triage, drafting, send verification, and sent-mail-safe follow-up workflow for ECC. Use when the user wants to organize email, draft or send through the real mail surface, or prove what landed in Sent.

Session-end memory garbage collector. Promotes valuable L2 session facts to L1 atomic memory, wipes L2, and rotates oversized audit logs. Run at end of session to prevent context inflation and storage bloat.

Recognize and extract text from images or PDFs using Surya OCR (datalab-to/surya). Use when a user uploads a document, screenshot, scan, or photo and wants the text extracted or analyzed. Surya supports 90+ languages and works on both images and PDFs without an internet connection.

Use when the user has UI screenshots or design exports that need batch conversion into Vue 3 components, especially with Vant, Element Plus, or Ant Design Vue.

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.

Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.

Eliminate generic-looking UI — anti-default checklist, custom hover states, precision typography, non-stock spacing, surface depth, and production-grade polish that separates professional from template. Use when asked to "make this look less generic", "UI looks Bootstrap-y", "looks like a template", "add polish", "impeccable UI", "production quality design", "make it look custom", "it looks like every other SaaS app", "remove default styles", or "design lacks personality". Do NOT use for: design system token architecture — see design-system-gen. Do NOT use for: animation timing specifics — see motion-design.

Self-hosted open-source collaboration platform — chat, bots, webhooks, plugins, AI integration, Slack/Teams alternative with full data control. Triggers on: 'mattermost', 'self-hosted slack alternative', 'open source teams alternative', 'mattermost bot', 'mattermost webhook', 'mattermost plugin', 'mattermost API', 'mattermost integration', 'AI agent mattermost', 'deploy mattermost', 'mattermost docker', 'mattermost kubernetes', 'enterprise chat self-hosted', 'mattermost AI features', 'mattermost incoming webhook', 'mattermost slash command'.

Use when provisioning a headless Windows 11 VM in Docker for testing, running Windows-only tools, or installing Claude Code on Windows. Triggers on: 'windows vm', 'windows docker', 'headless windows', 'windows 11 container', 'windows vm ssh', 'kvm windows', 'dockur windows', 'windows dev environment', 'windows claude code', 'windows test environment'.

AI code reviewer grounded in classic software engineering books for catching design smells, coupling issues, and architectural risks.

Read and extract content from any web page using a real Chrome browser — including SPAs, JavaScript-rendered sites, and complex dynamic pages. Use when fetching page content that headless tools can't render, searching the web, or reading fully rendered pages via your own browser.

Show or configure the OMX HUD (two-layer statusline)

Alias for $plan --consensus

Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)

将 Dayflow 数据库增量同步到 Obsidian。当用户说"同步 dayflow"、"sync dayflow"或"/sync-dayflow"时使用此 skill。

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

Run an agent loop until an exit condition is met. Use when the user says "loop", "babysit", "keep trying until", "check every X", "watch", or wants iterative autonomous execution.

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.

name: sync-minecontext

CC-Panes bundled skill: Spec 工作流

Evidence-first mailbox triage, drafting, send verification, and sent-mail-safe follow-up workflow for ECC. Use when the user wants to organize email, draft or send through the real mail surface, or prove what landed in Sent.

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

Run a comprehensive security review on code

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

基于配置和需求生成 Next.js 项目，支持 --quick 快速模式跳过 PRD 阶段

Autonomous memory system for persistent learning across sessions. Automatically saves architectural decisions, bugfixes, patterns, and insights. Use to recall context from previous work and build institutional knowledge.

Generates comprehensive questions about decisions before implementing. Explores requirements, constraints, success criteria, edge cases, and hidden assumptions in a SINGLE comprehensive prompt. Use when starting any significant work to surface unknowns early.

Generate comprehensive test suites ensuring requirements are met. Strategies for Unit, Integration, and E2E testing.

Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

Manage the project's core principles and ensuring alignment. Create or update the project constitution from interactive or provided principle inputs.

Transform the agent into a performance engineer. Apply methodologies for measuring, profiling, and optimizing code (caching, algorithm complexity, resource usage).

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

queue-usage

weline-sticker