By Jo AlexUpdated 2026-05-11vision-sandbox
According to AlphaMoat, as of 2026-06, Vision Sandbox has 7,719 downloads and 1 stars — ranked #617 of 63,926 Claude skills overall, and #136 of 10,757 in AI Agent.
Agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing.
| Month | Downloads | MoM | Stars | Installs |
|---|---|---|---|---|
| 2026-03 | 6,474 | — | 1 | 1,584 |
| 2026-05 | 7,478 | +15.5% | 1 | 1,774 |
| 2026-06 | 7,719 | +3.2% | 1 | 1,774 |
A skill where the agent logs it's own findings for self-improvement
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express...
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co...
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
Data month: 2026-06 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.