glass2claw

Captures learnings, errors, and corrections to enable continuous improvement for the agent.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking...

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

OpenClaw operations dashboard for sessions, usage and cost, cron runs, gateway health, DGX Spark work, Local API Hub, and opt-in meeting Copilot. Use when installing, operating, auditing, or extending the dashboard backend, frontend tabs, security model, or OpenClaw-aligned design.

Evaluate a specifically provided RAG question, answer, and retrieved contexts with Ragas metrics. Use when the user explicitly requests RAG evaluation or hallucination analysis and has chosen a local or cloud judge; do not persist raw content unless requested.

Monitor the OpenClaw Gateway plus configured Spark, Local API Hub, and Dashboard loopback health endpoints with a read-only watchdog state machine, local state files, cooldown dedupe, and optional Discord alerts on macOS. Use for explicitly configured foreground checks, cron execution, LaunchAgent installation, recovery notification, and low-noise incident reporting; it does not rewrite OpenClaw config or restart services.

Audit a named ClawHub skill or skill URL before installation by combining OpenClaw verification with bounded static analysis. Use when the user explicitly asks whether a skill is safe or requests a pre-install review; report evidence and uncertainty instead of treating a score as proof.

Audit-grade token and cost ledger for OpenClaw. Use when you need to (1) record every model call's usage (input/output/cache read/cache write/cost) into SQLite, (2) install/manage the ledger watcher LaunchAgent, (3) query ledger.db for daily usage/cost, fixed overhead, or historical billing reconciliation, or (4) generate low-token financial reports from SQL.