Automation
Task automation and scripting
dev-task
by bentz
该技能用于指导复杂需求的开发流程，它帮助在多轮对话中澄清目标，在执行阶段组织任务与 todos
neuronclaw
by agentpilled
Self-improvement engine for OpenClaw agents. Autonomously captures complex task approaches as drafts, validates them over repeated use, promotes proven patterns to reusable skills, and manages the full lifecycle — patching, scoring, security scanning, and garbage collection. Activate after completing complex tasks, when reviewing skill health, or when a skill produces wrong results during use.
claude-code-via-openclaw
by zhangkaidhb
Drive Claude Code (or other ACP coding agents) through OpenClaw for long-running coding tasks with background execution, progress monitoring, and result reporting. Use when: (1) delegating coding work to Claude Code/Codex/Cursor via acpx CLI, (2) running multi-step development tasks that need background execution, (3) setting up progress monitoring with automatic notifications, (4) managing named Claude Code sessions across multiple turns. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (use sessions_spawn with runtime:"acp").
everclaw
by profbernardoj
Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the Morpheus decentralized network. Stake MOR tokens, access GLM-5, GLM-4.7 Flash, Kimi K2.5, and 30+ models with persistent inference by recycling staked MOR. Open-source first model router routes all tiers to Morpheus by default — Claude only kicks in as an escape hatch when needed. Includes Morpheus API Gateway bootstrap for zero-config startup, OpenAI-compatible proxy with auto-session management, automatic retry with fresh sessions, OpenAI-compatible error classification to prevent cooldown cascades, multi-key auth rotation v2 with proactive DIEM balance monitoring and reactive 402 watchdog, Gateway Guardian v5 with direct curl inference probes (eliminates Signal spam), proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver, three-shift cyclic execution engine (v2 with 15-minute execution loops), 24/7 always-on power configuration for macOS, bundled security skills, zero-dependency wallet management via macOS Keychain, x402 payment client for agent-to-agent USDC payments, ERC-8004 agent registry reader for discovering trustless agents on Base, and hardware-aware local Ollama fallback with auto model selection (Qwen3.5 family, 1.5B–72B based on available RAM/GPU).
comparative-analysis
by squirrel289
Structured, repeatable, objective comparative analysis for choosing between alternatives. Use when selecting skills, tools, architectures, workflows, or build-vs-buy options and when you need explicit criteria definition, metric-based scoring, cross-platform and current-platform success scores, and a deterministic recommendation with a concise decision record.
research-report-team
by chang2839338
Decision research and report-writing team workflow. Use when the user wants an AI team to clarify a decision goal, research a topic, compare options, draft a business or executive report, review evidence and logic, revise gaps, and deliver a decision-ready final document.
doc2ml-json
by usagi-epta
Ingest any document (PDF, EPUB, DOCX, TXT, HTML, Markdown) and convert it into structured, ML-ready JSON. Use when the user asks to: extract text from documents, convert documents to structured data, create ML datasets from documents, parse PDF/EPUB/DOCX content, chunk documents for RAG, or produce tokenizable JSON from unstructured documents. Triggers on file uploads of supported formats or requests mentioning document conversion, text extraction, dataset creation from documents.
markdown-mermaid-export
by andeya
Render Mermaid code blocks from Markdown files to high-quality SVG + PNG images using the MermaidChart theme. Use when the user wants to export, render, batch-convert, or screenshot Mermaid diagrams, or mentions mermaid-to-image, mermaid PNG, or diagram export.
python-async-workers
by lct1407
Generate Python background workers, cron jobs, message queue consumers. Use when creating scheduled tasks (APScheduler), Celery workers, RabbitMQ/Redis queue consumers, or async job processing. Follows project async patterns and integrates with existing services.
your-skill-name
by brianmsm
Reusable workflow for your task area. Use this skill when an AI agent needs this workflow repeatedly and consistently.
browser
by maxgent-ai
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
mcp-shrimp-execution-loop
by janjaszczak
Combine Shrimp task tracking with execution loops (plan → execute → verify → update status). Use for multi-step deliveries where progress tracking matters.
olakai-create-agent
by olakai-ai
Create a new AI agent with Olakai monitoring from scratch. AUTO-INVOKE when user wants to: build a new AI agent, create an AI workflow, set up a new chatbot or copilot, implement an autonomous agent, design an AI-powered feature, start a new project with AI observability, or add KPI tracking and governance to a new AI system. TRIGGER KEYWORDS: olakai, create agent, new agent, build agent, AI agent, AI workflow, chatbot, copilot, autonomous agent, agent architecture, agentic AI, assistive AI, observability setup, KPI tracking, governance, new AI project, AI monitoring setup, agent from scratch. DO NOT load for: adding monitoring to existing code (use olakai-add-monitoring), troubleshooting existing agents (use olakai-troubleshoot), or generating reports (use generate-analytics-reports).
cibus-auto-buy-windows — Clawpilot skill
by nadav2cohen
The OTP regex looks for verification code is: #### and bare 6-digit numbers; override with CIBUS_OTP_REGEX if Cibus changes the wording.
hubspot-whoami-nango
by contextware
Find out who you are in HubSpot using Nango.
pragmatic-programmer-workflow
by vnnkl
"Apply Pragmatic Programmer (Hunt & Thomas, 2019 edition) advice to software tasks and code reviews; use when the user asks to apply pragmatic tips, asks how to approach a task, or when performing a code review to map relevant chapters/tips to the current context."
shoqai-automation
by dysthayes
Automate browsing and article searching on shoqai.com with screenshot capture
self-subagent
by pc-style
Orchestrate parallel sub-tasks by spawning non-interactive instances of your own CLI as subagents. Use when you need to parallelize work across multiple files, run independent investigations simultaneously, or delegate heavy multi-step tasks. Works with ANY AI coding CLI agent (Amp, Claude Code, Codex, Cursor, OpenCode, aider, Cline, Roo, goose, Windsurf, Copilot CLI, pi, etc.). Triggers on "run in parallel", "subagent", "delegate", "fan out", "concurrent tasks", or any complex task that benefits from parallel execution.
biga
by kobenfang
A股智能分析与智能选股工具。维护动态股票池(最多30支),按高科技×中小市值×好业绩原则筛选,推送买卖信号。含独立技术面择时分(-10~+10)用于判断买卖时机。A股投资、股市分析、量化选股。
review-criteria
by DUTSTECH
Criteria for reviewing Codex worker outputs across 5 dimensions. Use when reviewing code submitted by workers before approval.
auto-updater
by Teylersf
Automatically update OpenClaw every night. Use when the user wants their agent to stay up-to-date with the latest OpenClaw version. Runs a cron job that stops the gateway, runs the update, and restarts. Triggered when user mentions: "update yourself", "auto update", "nightly update", "keep updated", "self update", or any variation of updating the agent.
Getting Started with Skills
by yousufjoyian
Claude agent skills and workspace configuration
notion-ops
by Alicoder001
Notion operations control-plane for AI and human delivery teams. Use when designing, setting up, auditing, or running Notion workspaces with task lifecycle governance, signatures, approvals, work logs, handoffs, context packets, and MCP client continuity.
clojure-write
by aiagentskills
Guide Clojure and ClojureScript development using REPL-driven workflow, coding conventions, and best practices. Use when writing, developing, or refactoring Clojure/ClojureScript code.