AI desktop agent — control any app on Windows/macOS from your OpenClaw agent. Send natural language tasks to the Clawd Cursor API and it handles everything:...
Generates a world model representation from state inputs using discrete wavelet transforms (DWT) to capture multi-resolution temporal and spatial features.
Handles full GitCode PR code reviews by automating security scans, manual analysis, selecting top issues, formatting results, and optionally posting review c...
Visualize interior design transformations using each::sense AI. Redesign rooms, change styles, update color schemes, and preview renovations from photos of y...
Generates and validates multi-layered, multi-modal creative narratives using recursive constraints inspired by Gödel, Escher, and Bach principles.
Intelligently modify agent core context files (AGENTS.md, SOUL.md, IDENTITY.md, USER.md, TOOLS.md, MEMORY.md, HEARTBEAT.md). Use when conversation involves changing agent behavior, updating rules, twe
USE FOR AI-grounded answers via OpenAI-compatible /chat/completions. Two modes: single-search (fast) or deep research (enable_research=true, thorough multi-s...
Codebase onboarding assistant that maps project architecture, identifies patterns, generates guides, and helps new developers understand any repository in mi...
Runs autonomous iterative AI loops for requirements, planning, or building phases using structured prompts and fresh context per iteration.
Create and configure custom agents in Microsoft Copilot Studio via a guided web app process, including triggers, knowledge, tools, topics, and publishing.
Routes LLM requests to the cheapest capable model across 8 providers (Anthropic, Google, OpenAI, DeepSeek, xAI, Moonshot, Mistral, Ollama) and 25+ models. Scores prompts on 8 dimensions in under 1ms,
--- name: accessibility-expert description: Tests and remediates accessibility issues for WCAG compliance and assistive technology compatibility. Use when (1) auditing UI for accessibility violations,
Query blockchain wallet data, token prices, and transaction history using the Zerion API via its MCP connector. Use this skill whenever the user asks about: crypto wallet balances, portfolio values, t
--- name: "dependency-auditor" description: "Dependency Auditor" --- # Dependency Auditor > **Skill Type:** POWERFUL > **Category:** Engineering > **Domain:** Dependency Management & Security
Delegate coding tasks to Sourcegraph Amp, an autonomous coding agent. Use when: multi-file changes, new features, bug fixes, test writing, or any coding task...
--- name: senior-software-engineer-software-architect-code-reviewer description: Principal-level AI Code Reviewer + Senior Software Engineer/Architect rules (SOLID, security, performance, Context7 + S
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
--- name: "pr-review-expert" description: "PR Review Expert" --- # PR Review Expert **Tier:** POWERFUL **Category:** Engineering **Domain:** Code Review / Quality Assurance --- ## Overview Struct
TTRPG Game Master for mature dark-themed campaigns. Use for Cyberpunk, Dark Fantasy, Horror, character-driven narratives with consequence tracking. Features dual-consequence system (World + Relationsh
# Prompt Name: Constraint-First Recipe Generator (Playful Edition) # Author: Scott M # Version: 1.5 # Last Modified: January 19, 2026 # Goal: Generate realistic and enjoyable cooking recipes derived s
Create or update project documentation in Markdown. Use when building a new project doc set, updating existing docs after a deploy or feature change, or esta...
Deploy a multi-agent SaaS growth team on OpenClaw with shared workspace, async inbox communication, cron-scheduled tasks, deep project code scanning (Deep Di...
Explore and compare multiple parallel solution designs ("universes") before coding, then converge on a single, well-justified approach. Use when problems are...
Parallel Review by Independent Specialist Models. Multi-agent review protocol that deploys 5+ specialist reviewers in parallel to eliminate confirmation bias...