Skills
The best skills for Automation workflows.
Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility
Provides free, automated access to reliable US weather data, detailed forecasts, and official alerts from the National Weather Service API without requiring an API key.
Azure AI Transcription SDK for Python enables real-time and batch speech-to-text transcription with features like timestamps and speaker diarization.
Automatically transcribes audio recordings into structured Markdown documentation with summaries and metadata extraction.
An AI tool that automates playing Pokémon games via headless emulation and RAM reading to simulate gameplay without manual input.
An AI agent that automates playing Pokemon games via headless emulation and RAM state analysis.
Automates the management and validation of causal and temporal consistency in branched narrative plots and alternative timelines using event graphs.
An AI tool that automates task creation within a user's Notion workspace by managing project tasks and details systematically.
An AI skill that guides users through customized status workflows by interpreting configuration rules and delegating status transitions to automation tools.
一个自动撰写小红书笔记,自动生成图片,自动发布的 Skills
A fast, native browser automation CLI built from the ground up for AI agents, powered by Chrome DevTools Protocol. 63 commands covering navigation, interaction, screenshots, accessibility, network mocking, visual diffing, test generation, and more — all from a single binary.
Self-improvement system for Hermes Agent. Monitors performance, finds weak skills, fixes them with self-evolution, reports results.
Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration
Fact-checking and disinformation detection skill for Claude and Codex
self learning memory harness that works with your main harnesses; it's an ambient memory agent
Codex Skill for turning Douyin videos into evidence-based Markdown notes
Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.
微信公众号自动化运营 OpenClaw Skill - 内容采集、数据分析、互动管理
|
loki-mode is a multi-agent autonomous system that manages end-to-end software development lifecycle tasks from product requirements to production without human intervention.
Crawl websites locally with crawl4ai to extract contact emails. Accepts multiple URLs and outputs domain-grouped results for clear attribution. Uses deep crawling with URL filters (contact, about, support) to find emails on relevant pages. Use when extracting emails from websites, finding contact information, or crawling for email addresses.
Run local ComfyUI workflows via the HTTP API. Use when the user asks to run ComfyUI, execute a workflow by file path/name, or supply raw API-format JSON; supports the default workflow bundled in assets.
Automate Notion tasks via Rube MCP (Composio): pages, databases, blocks, comments, users. Always search tools first for current schemas.
Read Simon's latest AI Champions weekly task from #ai-champions Slack, implement it, and post a succinct human-readable result back to the channel as a single message.
Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning.
Write ML papers for NeurIPS/ICML/ICLR: design→submit.
Automate Ninox tasks via Rube MCP (Composio). Always search tools first for current schemas.
Implement and apply an approved change proposal
Auto-delegation, status truth, and cost-aware model routing for OpenClaw agents
Automates cloud platform operations for Render services, deployments, and projects to streamline management and deployment workflows.
Automate Multi-Locale asset creation for your iOS app.
Strava-cli allows users to interact with the Strava platform directly from the terminal, enabling scripting and automation of Strava tasks.
gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP. Gemini画图 MCP和sill,支持龙虾或任何agent使用٩(๑>◡<๑)۶
Use when starting a session and wanting creative engagement, or when user says '/fun' or asks for a persona
Total Recall — Autonomous Agent Memory. The only memory system that watches on its own. Five-layer observational memory for OpenClaw agents. ~$0.10/month.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
An AI tool that manages session context by orienting on previous session data and outlining the next task before proceeding.
Automates audio transcription and generates structured Markdown documentation with summaries and metadata for meetings and recordings.
An AI tool that automates playing Pokemon games via headless emulation and RAM analysis.
>-
A pipeline tool designed to preprocess and vectorize customer support conversations for semantic search, enabling nuanced retrieval with attention to privacy, chunking, and metadata filtering.
A tool for managing and maintaining canonical task state, enabling task creation, updates, transitions, and history tracking within an authoritative task ledger system.
A tool that converts WeChat official account articles to Markdown with features like anti-detection, automatic retries, batch processing, and image localization for streamlined automation.
extract-artifacts automates extraction and structuring of knowledge cards from various source files to update a knowledge base with deduplication and indexing.
An auditing tool designed to detect project drift, context shifts, task branching, and inconsistencies, providing diagnostics without modifying code for better project control.
Skill file: --- name: ask-questions-if-underspecified description: Clarify requirements before implementing. Do not use automatically, only when invoked explicitly. --- ## Goal Ask the minimum set of clarifying questions needed to avoid wrong work; do not start implementing until the must-have questions are answered (or the user explicitly approves proceeding with stated assumptions). ## Workflow ### 1) Decide whether the request is underspecified Treat a request as underspecified if after explo
Rememberall is a personal reminder system that automates task scheduling and notifications using cron jobs and natural language input.
An autonomous quality assurance testing agent that executes and diagnoses all types of tests without human intervention, applying fixes and recording results automatically.