website-debug
Website Debugging Skill
Lightweight, token-efficient browser debugging toolkit for frontend development. Uses CLI scripts instead of MCP servers to minimize context usage (~300 tokens vs 13k-18k).
Quick Start
Use the slash commands for easiest access:
/debug-page <url>- Start debugging session/screenshot- Take screenshot/pick-element- Interactive element selection/test-responsive- Test at all breakpoints/verify-changes- Verify after making changes
Or use scripts directly:
More from anthemflynn/ccmp
react-three-fiber
Build 3D applications with React Three Fiber (R3F), the React renderer for Three.js. Use this skill when building 3D scenes with React, using declarative JSX for 3D objects, integrating Three.js with React state/lifecycle, or using Drei helpers. Covers Canvas setup, hooks, Drei utilities, performance patterns, and state management for 3D React apps.
229openclaw-admin
Fix, configure, tune, or troubleshoot OpenClaw. Use for config changes, security fixes, performance tuning, doctor --fix, or when openclaw-doctor flags issues that need remediation.
30asset-pipeline-3d
Optimize and prepare 3D assets for web delivery. Use this skill when working with GLTF/GLB files, compressing 3D models, optimizing textures, setting up Blender exports, or preparing assets for Three.js/R3F. Covers GLTF workflows, Draco/meshopt compression, texture optimization, LOD generation, and performance profiling.
29openclaw-maintain
Keep OpenClaw running — daemon management, updates, log rotation, cron jobs, session cleanup, memory reindex, and sandbox management. Use for 'keep it healthy' tasks.
20claude-context-manager
Enables autonomous context management for codebases through claude.md files. Use when creating, maintaining, or synchronizing AI agent context. Provides tools and workflows for monitoring context health, detecting staleness, and updating intelligently. Helps Claude work proactively as a context manager.
17openclaw-doctor
Comprehensive OpenClaw diagnostic audit — an agent-on-agent health check. Use when asked to check system health, diagnose issues, or audit OpenClaw subsystems. Covers gateway, security, channels, models, memory, context, heartbeat, hooks, skills, workspace integrity, and network.
16