18 skills found
openclaw / lobsterLobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (s
block / goosean open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
lackeyjb / playwright-skillClaude Code Skill for browser automation with Playwright. Model-invoked - Claude autonomously writes and executes custom automation for testing and validation.
kenryu42 / claude-code-safety-netA coding agent plugin that acts as a safety net, catching destructive git and filesystem commands before they execute.
Agentfy-io / Agentfy🤖 Agentfy is a modular microservices architecture designed to process user requests and execute workflows across multiple social media platforms. ASK ONCE, LET THE AGENT DO THE REST!
elusznik / mcp-server-code-execution-modeAn MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.
log-bell / avakill🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, and MCP. She doesn't guard. She kills.
CumpsD / broker-as-a-serviceCross-chain cryptocurrency swaps via Chainflip. Get quotes, execute swaps, and track progress.
7tg / django-admin-mcpExpose Django admin models to MCP (Model Context Protocol) clients. Add a mixin to your ModelAdmin classes and let AI assistants like Claude perform CRUD operations, execute admin actions, and explore relationships—all respecting Django's permission system.
rhein1 / agoragentic-integrationsCapability router for autonomous agents. Call execute(task, input, constraints) and the router finds the best provider, handles fallback, and settles in USDC on Base L2.
JimmySadek / strategic-partnerEvery other tool executes. This one decides what to execute. Chief of Staff skill for Claude Code.
synaptiai / executeAgent Capability Standard is an open specification for composable AI agent capabilities. It defines 36 atomic capabilities across 9 cognitive layers, a type-safe workflow DSL, and grounded world modeling with trust-aware conflict resolution. Built on the Grounded Agency philosophy, it makes agent reliability structural—not optional.
visorcraft / handHand Hand executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, p
wepee / lobsterLobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (s
richard-devbot / lobsterLobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (s
Flexasaurusrex / lobsterCat Cat executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, pos
kopi-vm / md/md Fix markdown formatting issues. Steps to execute: 1. Run `bun format` to format markdown files
jpoley / planExecute planning workflow using project architect and platform engineer agents to create ADRs and platform design.
