~/agentstafferAgentStaffer
Find, trial, compare, and govern AI agents before hiring
Roles / Technical Category
Review matching candidates
Next best action: Open a profile, compare evidence, then run a sandbox trial
Computer Use & Desktop
Agents that operate browsers, desktops, mobile devices, UI automation, or computer-use environments.
33total
33filtered
3page
3pages
Category fit
Which technical function should the agent perform?
Filter candidates by capability, protocol, trust, install readiness, and trial status.
- Operate browser or desktop workflows in a sandbox.
- Verify UI tasks with real viewport checks.
- Keep credentials out of first-run trials.
Recommended trials and bundles
github / workflow
simular-ai/Agent-S
Agent S: an open agentic framework that uses computers like a human
CLI
- Fit
- 63 / 100
- Trust
- High traction
- Install
- CLI likely
Review links
playbooks / skill
android-to-harmonyos-migration-workflow skill by openharmonyinsight/openharmony-skills
This skill orchestrates an iterative Android to HarmonyOS migration workflow with agents for analysis, planning, translation, validation, testing, and UI
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / tool
Computer Use MCP Server - spencerkinney/computer-use-mcp
Controls virtual computers via MCP to manage cloud desktops for Computer Use Agents
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
computer-use-agents skill by omer-metin/skills-for-antigravity
This skill helps you build AI agents that control computers and GUI elements securely and effectively across vision-based tasks.
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
gemini-computer-use skill by openclaw/skills
This skill automates web browser tasks using Gemini Computer Use with Playwright, providing an agent loop and optional safety confirmations.
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
marketing-seo-complete skill by vasilyu1983/ai-agents-public
Complete SEO skill for technical audits (Core Web Vitals, site speed, crawlability/indexation, robots/sitemaps/canonicals, structured data, mobile, security, internal linking), SEO marketing strategy (keyword research, content planning, competitive analysis, E-E-A-T), operational workflows (cross-team collaboration, OKRs), link building, local SEO, internat...
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
responsive_design skill by vuralserhat86/antigravity-agentic-skills
Build responsive, mobile-first layouts using fluid containers, flexible units, media queries, and touch-friendly design that works across all screen sizes. Use this skill when creating or modifying UI layouts, responsive grids, breakpoint styles, mobile navigation, or any interface that needs to adapt to different screen sizes. Apply when working with respo...
MCPHTTPCLI
- Fit
- 61 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
github / skill
skalesapp/skales
Local-first AI desktop agent for Windows, macOS, Linux & Android. Codework, multi-agent teams, desktop automation, 15+ AI providers. No Docker. No terminal. AI Companion. Agent Skills (SKILL.md). Migration-Importer, BYOK, from 6 to 60+. Recurring Autonomous AI Agent Tasks.
MCP
- Fit
- 59 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
claudemarketplaces / skill
godot-mcp-setup
This handles the setup and configuration of Godot's Model Context Protocol server so AI agents can programmatically build and modify scenes. It's specifically for when you want automated scene creation rather than manual workflows. The main piece is a tool script that generates the Claude Desktop config JSON you need to get MCP running with Godot. Don't exp...
MCP
- Fit
- 57 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
Review support
Open Category guide
Review links
Technical category pages stay focused on job browsing; complete review records and finalist profile resources stay linked here.
Supporting review linksLinks, review order, and page-specific notes remain available here.
Category guideTechnical role guideAgent inventoryResource mapReview guideAPI referenceSite contextSitemapProfile resources
33 matching candidates for Computer Use & Desktop. Open candidate profiles for fit, setup guidance, trust evidence, and sandbox trial planning.
- 01Site contextShared review rules
- 02Role categoryOpen the focused review record
- 03Agent inventoryBrowse the matching inventory
- 04Profile resourcesEvidence, setup, trust, trial, and history files
Use the links and review path below for role-category candidates, related playbooks, and finalist profile resources before action.
Review route: OpenAI review tools can start with openai.json; otherwise use site context and agent inventory before opening the finalist's complete review materials before install, hire, or promotion.