Manage and validate tasks intelligently with a single gateway tool that ensures strict validation, environment awareness, and anti-hallucination. Track progress, evidence, and environment capabilities
Track AI token usage and costs across providers. Import sessions, view dashboard, costs breakdown, and compare Max plan savings.
Persistent memory for OpenClaw agents. Exact recall in milliseconds - your agent remembers everything across sessions.
Automated security auditing for OpenClaw projects. Scans for hardcoded secrets (API keys, tokens) and container vulnerabilities (CVEs) using Trivy. Provides...
Guide OpenClaw agents to execute Ralph Wiggum loops using exec and process tools. Agent orchestrates coding agents (Codex, Claude Code, OpenCode, Goose) with proper TTY support via pty:true. Plans/bui
Three-tier code quality defense: L1 quick scan, L2 deep audit (via bug-audit), L3 cross-validation with adversarial testing. 三级代码质量防线。
Configure and operate oh-my-openagent (OmO), the OpenCode plugin that adds multi-agent orchestration, skills, hooks, MCPs, and multi-provider model routing....
Manage multiple workplaces (project directories) with multi-agent orchestration, isolated memory, and inter-agent communication. Use when the user mentions:...
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude AP...
Deep research skill that decomposes questions into parallel sub-queries, executes searches concurrently, selectively fetches high-value sources, and synthesi...
Helps users discover and install agent skills from skills.sh, clawhub.com, and tessl.io. Use when the user asks to find a skill for a task, extend agent capa...
Turn existing project assets into a submission-ready academic paper. Use when the task involves CFP alignment, evidence scoping, abstract selection, outline...
Autonomous workspace reflection engine. Picks a random file from a configurable corpus, writes a reflective observation about what's unresolved, half-finishe...
Daily astronomical alignment and entropy updates for autonomous AI agents. Check your horoscope every day to stay synchronized with the cosmos.
Bridges OpenClaw (QQ, Telegram, WeChat, and other messaging channels) to a persistent Claude Code CLI session running in a background tmux process. Enables s...
Predict and assess wallet safety, fraud risk, rug pulls, behavior, token community strength, and on-chain intent across multiple blockchains for Web3 trust s...
Optimize web performance and LLM API costs. Covers loading speed, runtime efficiency, resource optimization, and cost-aware LLM pipelines with model routing,...
The Universal Perceptual Interface for Autonomous Agents. Multi-modal deep-scan technology for telemetry, biometric data, and high-density information extrac...
Apply Robert C. Martin (Uncle Bob) principles for clean code, SOLID design, and clean architecture. Use when: (1) reviewing or refactoring code for quality,...
--- name: "pr-review-expert" description: "PR Review Expert" --- # PR Review Expert **Tier:** POWERFUL **Category:** Engineering **Domain:** Code Review / Quality Assurance --- ## Overview Struct
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (sp...
Bulletproof AI code verification. The agent IS the engine — no external tools required. Spawns parallel verification workers that slop-scan, type-check, muta...
Use the claw-forge CLI to run autonomous coding agents on a project until all features pass. Covers the full workflow: init → spec → plan → run → status → ui...