CLI 工具
命令行工具
drive-the-ui
langwatch
Drive the page the user has open through live UI actions. List the actions a page accepts, call them with typed payloads, and read the live state including unsaved edits. Use when the user is looking at a page you can operate, such as the evaluations workbench, and a change should happen in front of them rather than behind their back.
context-sweet-spot
langwatch
Investigates the context economics of your own coding-agent sessions in LangWatch. Reads real sessions to find where carrying a fat context stops paying for itself, measured in cache rebuilds, compactions and cost per turn, and delivers a report with the context size your sessions should stay under, with example sessions behind every claim. Use when coding-agent sessions feel expensive or degrade as they grow.
screenshot
0xDarkMatter
"Find and display recent screenshots. Triggers: screenshot, check screenshot, show screenshot, recent screenshot, last screenshot."
markitdown
0xDarkMatter
"Convert local documents to Markdown using Microsoft's markitdown CLI. Best for: PDF, Word, Excel, PowerPoint, images (OCR), audio. Can fetch URLs but Jina is faster for web. Triggers on: convert to markdown, read PDF, parse document, extract text from, docx, xlsx, pptx, OCR image, local file."
find-replace
0xDarkMatter
"Modern find-and-replace using sd (simpler than sed) and batch replacement patterns. Triggers on: sd, find replace, batch replace, sed replacement, string replacement, rename."
python-env
0xDarkMatter
"Fast Python environment management with uv (10-100x faster than pip). Triggers on: uv, venv, pip, pyproject, python environment, install package, dependencies."
strategic-compact
WorldFlowAI
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Verification Loop Skill
WorldFlowAI
Hooks catch issues immediately; this skill provides comprehensive review.
agentation-self-driving
benjitaylor
Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to "critique this page," "add design annotations," "review the UI," "self-driving mode," "auto-annotate," or wants an AI agent to autonomously add design feedback annotations to a web page via the browser. Requires the Agentation toolbar to be installed on the target page and agent-browser skill to be available.
model-council
michaelboeding
This skill should be used when the user asks for "model council", "multi-model", "compare models", "ask multiple AIs", "consensus across models", "run on different models", or wants to get solutions from multiple AI providers (Claude, GPT, Gemini, Grok) and compare results. Orchestrates parallel execution across AI models/CLIs and synthesizes the best answer.
sap-datasphere
secondsky
Comprehensive plugin for SAP Datasphere development with 3 specialized agents, 5 slash commands, and validation hooks. Use when building data warehouses on SAP BTP, creating analytic models, configuring data flows and replication flows, setting up connections to SAP and third-party systems, managing spaces and users, implementing data access controls, using the datasphere CLI, creating data products for the marketplace, or monitoring data integration tasks. Covers Data Builder (graphical/SQL views, local/remote tables, transformation flows), Business Builder (business entities, consumption models), analytic models (dimensions, measures, hierarchies), 40+ connection types (SAP S/4HANA, BW/4HANA, HANA Cloud, AWS, Azure, GCP, Kafka, Generic HTTP), real-time replication, task chains, content transport, CLI automation, catalog governance, and data marketplace. Includes 2025 features: Generic HTTP connections, REST API tasks in task chains, SAP Business Data Cloud integration. Keywords: sap datasphere, data warehouse cloud, dwc, data builder, business builder, analytic model, graphical view, sql view, transformation flow, replication flow, data flow, task chain, remote table, local table, sap btp data warehouse, datasphere connection, datasphere space, data access control, elastic compute node, sap analytics cloud integration, datasphere cli, data products, data marketplace, catalog, governance
before-and-after
vercel-labs
Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new", or needs to document UI changes. Accepts two URLs (file://, http://, https://) or two image paths.
Arduino CLI Usage Skill
wedsamuel1230
Arduino/embedded systems skills and maker tools.
arduino-serial-monitor
wedsamuel1230
Tools for reading and analyzing Arduino serial monitor output for enhanced debugging. Provides real-time monitoring, data logging, filtering, and pattern matching to help troubleshoot Arduino sketches using arduino-cli or Arduino IDE.
llm-cli
glebis
Process textual and multimedia files with various LLM providers using the llm CLI. Supports both non-interactive and interactive modes with model selection, config persistence, and file input handling.
telegram-telethon
glebis
This skill should be used for comprehensive Telegram automation via Telethon API. Use for sending/receiving messages, monitoring chats, running a background daemon that triggers Claude Code sessions, managing channels/groups, and downloading media. Triggers on "telegram daemon", "monitor telegram", "telegram bot", "spawn Claude from telegram", or any Telethon-related request. IMPORTANT: Use draft command for "драфт/draft", use send for "отправь/send"; if ambiguous, ASK before sending.
superlocalmemory
qualixar
"AI agent memory with mathematical foundations. Store, recall, search, and manage memories locally with zero cloud dependency."
google-cloud-recipe-onboarding
Guidance for a developer's first steps on Google Cloud, covering account creation, billing setup, project management, and deploying a first resource.
careful
garrytan
Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".
processon-mindmap-generator
ZJU-REAL
ProcessOn 官方研发的 AI 脑图生成工具，专注于将自然语言、Markdown、长文本、文档、网页、图片文字等内容，一键生成结构清晰、层级分明、可编辑的专业思维导图。 无论是文章总结、资料整理、文档拆解、知识点归纳、学习路径梳理，还是读书笔记、论文文献梳理、会议纪要提炼、工作报告总结、方案大纲生成、项目任务拆解、头脑风暴与创意发散，都可以通过本技能快速生成专业脑图，帮助用户把零散内容转化为清晰的结构化知识。 本技能支持思维导图、逻辑图、组织结构图、鱼骨图、时间轴、树形图、表格图等 7 种专业图形布局，并深度集成 ProcessOn 在线协同平台。生成后的思维导图可在线编辑、协作修改、高效复用，适合职场办公、学习复习、科研阅读、知识管理和方案策划等场景。 注意：本技能主要用于生成思维导图和知识结构类脑图，不适用于流程图、泳道图、时序图、系统架构图、ER 图、Mermaid 图等流程或技术图表生成场景。
dotnet-inspect-performance
richlander
Whole-assembly call-graph leverage ranking and performance triage for libraries (experimental).
dotnet-inspect-private-feeds
richlander
Inspect packages from private and custom NuGet feeds safely — select and map sources, use credential providers or explicit configuration, diagnose authentication failures, and reason about source-bound caches and offline operation.
dotnet-inspect-correctness
richlander
Judge whether code is sound and safe to call — its exception surface (throws, catches, exception types) and the unsafe operations in a method body.
dotnet-inspect-query
richlander
Output formats, -D/-S discovery and selection, -Q query-capability discovery, value projection, @ categories, and output limits shared across commands.