All authors
Claude Skills by Kairos-ai-agent
github.com/Kairos-ai-agent572 skills0 installs15 views
- Imagegen Frontend MobileElite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortaVotes: 0GitHub stars: 2
- Imagegen Frontend WebElite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing pageVotes: 0GitHub stars: 2
- ImagegenGenerate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex shouldVotes: 0GitHub stars: 2
- Impeccable Asset ProducerProduces clean reusable raster assets from approved Impeccable mock references without redesigning the direction.Votes: 0GitHub stars: 2
- Impeccable Finish ReviewerReviews a finished Impeccable build against its direction contract, the approved comp, and the chosen world's quality bar, returning an ordered list of material fixes.Votes: 0GitHub stars: 2
- Impeccable Manual Edit ApplierApplies leased Impeccable live manual copy-edit batches to source and returns canonical Apply results.Votes: 0GitHub stars: 2
- ImpeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers weVotes: 0GitHub stars: 2
- Inspecting Hermes Desktop DomRead the live Hermes desktop DOM/CSS over CDP.Votes: 0GitHub stars: 2
- InstructorExtract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-teVotes: 0GitHub stars: 2
- Interview Designer 1.0.0Analyze resumes and design interview strategies using evidence-based methodology. Transforms interview prep from \"read resume → ask questions\" into \"define standard → forensic evidence → future simulaVotes: 0GitHub stars: 2
- Inventory ManagerTrack inventory levels, manage stock, forecast demand, and optimize replenishment. Use when building inventory management features, stock tracking, or demand planning systems.Votes: 0GitHub stars: 2
- Iot Product DesignIoT/传感器产品方案设计工作流。覆盖需求分析、可行性论证、传感器选型、 安装结构设计、硬件电路设计、嵌入式固件设计、模拟测试报告。 当用户需要设计基于传感器的智能硬件产品方案时使用。Votes: 0GitHub stars: 2
- Jupyter Live KernelIterative Python via live Jupyter kernel (hamelnb).Votes: 0GitHub stars: 2
- Kairos CanvasBuild and maintain Kairos Canvas — an infinite canvas SPA (single HTML) with node-based visual workflows for AI content generation (LLM, image, video, TTS, storyboarding). Use when modifying Kairos CaVotes: 0GitHub stars: 2
- Kairos Code OpsTroubleshoot Kairos_code: chat silent, 500s, restartVotes: 0GitHub stars: 2
- Kanban Codex LaneUse when a Hermes Kanban worker wants to run Codex CLI as an isolated implementation lane while Hermes keeps ownership of task lifecycle, reconciliation, testing, and handoff.Votes: 0GitHub stars: 2
- Kanban OrchestratorDecomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The \"don't do the work yourself\" rule and the basic lifecycle are auto-injected into every kanbaVotes: 0GitHub stars: 2
- Kanban WorkerPitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is wVotes: 0GitHub stars: 2
- Khazix Writer数字生命卡兹克（Khazix）的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于：写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。即使用户只是说\"帮我把这个写成文章\"或\"用我的风格写一下\"，只要上下文涉及内容创作和公众号输出，都应该触发。也适用于用户丢过来一个PDF、brief、新闻链接、语音转文字或任何素材说\"帮我写篇文章\"的场景。不要用于短内容（小红书帖子、推特、朋友圈）或纯标题摘要生成（那个用wechat-title skill）。Votes: 0GitHub stars: 2
- Landing Page GeneratorProfessional high-end Landing Page generation tool. Creates visually stunning, Awwwards-level web pages with cinematic hero sections, modern animations, and automatic deployment. Trigger keywords: lanVotes: 0GitHub stars: 2
- Legacy AnalystDeep-reads legacy codebases (COBOL, Java, .NET, Node, anything) to build structural and behavioral understanding. Use for discovery, dependency mapping, dead-code detection, and \"what does this systemVotes: 0GitHub stars: 2
- Lightweight Ps Xlsx AppPowerShell-based self-contained applications that combine an embedded TcpListener HTTP server, xlsx files as primary data store (no external libs), and a single-file HTML frontend. Use when building or maintaining any PowerShell + Excel + light-weight browser UI tool for Chinese SMB / attendance / ERM-style workflows. Covers the server loop, JSON config conventions (schedule-{YYYYMM}.json + holidays.json + schedule.default.json), the standard mark legend (✘半天 ▲事假 △病假 ☆婚假 〇旷工 √公休 /出勤 公公出), six...Votes: 0GitHub stars: 2
- LinearLinear: manage issues, projects, teams via GraphQL + curl.Votes: 0GitHub stars: 2
- Llama Cppllama.cpp local GGUF inference + HF Hub model discovery.Votes: 0GitHub stars: 2
- LlavaLarge Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, viVotes: 0GitHub stars: 2
- Llm Browser Gateway浏览器前端直连 LLM API 的端到端方案。当用户说\"前端调大模型\"、\"浏览器接 LLM\"、\"CORS 错误 Failed to fetch\"、\"前端用 LLM 解析文本\"、\"前端接入 OpenAI/Anthropic/MiniMax\"等时使用。 覆盖：(a) 跨平台 API 风格自动适配（OpenAI Chat Completions vs Anthropic Messages vs MiniMax Anthropic-compatible）；(b) 通用 CORS proxy 模板（FastAPI 10 行）；(c) 浏览器 fetch 写法模板；(d) 调试 / 错误诊断（完整 URL + 状态码 + 响应 body）。 不覆盖：后端 server-side 调用（用 OpenAI / Anthropic Python SDK 即可，无 CORS 问题）。不覆盖：流式响应 / function calling / tools schema（这些是更高阶用法，按需扩展）。Votes: 0GitHub stars: 2
- Llm Gateway SetupSetting up and operating local LLM gateway / aggregator / router services that route coding CLIs (Claude Code, Codex, Cursor, Cline, OpenCode) across multiple LLM providers and free-tier pools. Covers OmniRoute, LiteLLM proxy, OpenRouter self-host, Portkey, mimocode2api, and similar tools. Trigger when user mentions any of: OmniRoute, LiteLLM, OpenRouter, Portkey, mimocode2api, \"LLM gateway/router/proxy/aggregator\", \"free LLM tiers\", \"fallback chain\", \"quota-aware routing\"; OR asks wh...Votes: 0GitHub stars: 2
- Llm WikiKarpathy's LLM Wiki: build/query interlinked markdown KB.Votes: 0GitHub stars: 2
- Lm Evaluation Harnesslm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).Votes: 0GitHub stars: 2
- Local Ai GuiPackage local AI models (Flux, SD, LLMs) as standalone GUI apps with Gradio. Covers Windows setup, GPU memory optimization, China mirror config, batch launcher scripts, and smart environment bootstrapVotes: 0GitHub stars: 2
- Local Torch InferenceDeploy custom PyTorch AI pipelines on constrained Windows hardware (<=16GB RAM, <=8GB VRAM). Covers safetensors loading, INT8 dequantization, memory management, zombie process cleanup, and GPU performVotes: 0GitHub stars: 2
- Logic Analyzer当需要用 Saleae 逻辑分析仪在线采集数字波形并解码 I2C/SPI/UART/CAN 时使用，通过 Logic 2 自动化服务驱动硬件采集、添加协议解码器并导出数据。Votes: 0GitHub stars: 2
- Logo Icon DesignProfessional Logo and icon design expert. Helps with brand visual design, vector icon creation, app icon design, and trademark design. Supports the complete design flow from concept ideation to finalVotes: 0GitHub stars: 2
- M5 OnboardEnd-to-end onboarding for a freshly-plugged-in M5Stack ESP32 device (Cardputer, Cardputer-Adv, Core, CoreS3, Stick) — detect on USB, flash UIFlow 2.0 firmware, and install the Claude Buddy MicroPythonVotes: 0GitHub stars: 2
- Macos Computer UseDrive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the `computer_use` tool is available.Votes: 0GitHub stars: 2
- Manim VideoManim CE animations: 3Blue1Brown math/algo videos.Votes: 0GitHub stars: 2
- MapsGeocode, POIs, routes, timezones via OpenStreetMap/OSRM.Votes: 0GitHub stars: 2
- Markdown ViewerCreate rich diagrams, data visualizations, technical architecture views, and editorial content cards directly in Markdown using the Markdown Viewer Agent Skills pack. Use for Mermaid-like diagram requVotes: 0GitHub stars: 2
- Market Research 1.0.0Size markets, analyze competitors, and validate opportunities with practical frameworks and free data sources.Votes: 0GitHub stars: 2
- Math OlympiadSolve competition math problems (IMO, Putnam, USAMO, AIME) with adversarialVotes: 0GitHub stars: 2
- Mcp BuilderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Votes: 0GitHub stars: 2
- Mcp IntegrationThis skill should be used when the user asks to \"add MCP server\", \"integrate MCP\", \"configure MCP in plugin\", \"use .mcp.json\", \"set up Model Context Protocol\", \"connect external service\", mentions \"${Votes: 0GitHub stars: 2
- Meeting Action ItemsTurn meeting notes into cited decisions, owners, tickets.Votes: 0GitHub stars: 2
- Meme GenerationGenerate real meme images by picking a template and overlaying text with Pillow. Produces actual .png meme files.Votes: 0GitHub stars: 2
- Memory 1.0.2Infinite organized memory that complements your agent's built-in memory with unlimited categorized storage.Votes: 0GitHub stars: 2
- Memory ManagementAgent记忆管理skill。涵盖如何有效使用memory工具、session_search做跨会话召回、记忆优先级策略、何时保存vs何时不保存、技能沉淀规则。帮助Agent提升跨会话的持续学习能力。Votes: 0GitHub stars: 2
- MemoryInfinite organized memory that complements your agent's built-in memory with unlimited categorized storage.Votes: 0GitHub stars: 2
- Merge ReconcilerNeutral third-party resolution of agent merge conflicts.Votes: 0GitHub stars: 2
- Meta CognitionAgent元认知与自我进化skill。涵盖错误复盘、知识萃取、能力自评、刻意练习、学习闭环。帮助Agent在每次交互中持续迭代、变得更聪明。Votes: 0GitHub stars: 2
- Mindmap Ppt BuilderCreate or update content for the agegr/mindmap-ppt static presentation project from a prose draft, article, speech, report, or notes. Use when Codex needs to turn a written document into the project'sVotes: 0GitHub stars: 2