Delegates long-running research and analysis tasks to an autonomous AI agent that runs asynchronously with parallel processing. You create a task via API, get back a task_id, then poll until it's done. Works well for market research, stock analysis, product comparisons, or anything requiring multi-source synthesis and report generation. Tasks can take 1-10+ minutes and produce markdown reports, CSVs, and charts. The agent profiles scale from lite (quick lookups) to max (deep research with complex reasoning). Honest take: if you're building something that needs to kick off substantial research without blocking, this handles the async orchestration so you don't have to babysit a long-running process yourself.

skills.sh installs
398
GitHub stars
454
last updated
Aug 21, 2026

Install

$ npx -y skills add sanjay3290/ai-skills --skill manus --agent claude-code

Installs into .claude/skills of the current project.

Files

Manus

Manus is an autonomous AI agent that handles complex tasks asynchronously. Particularly strong at deep research with parallel processing, web browsing, and generating comprehensive reports with data visualizations.

When to Use Manus

  • Deep research - Market analysis, competitive landscaping, product comparisons
  • Stock/financial analysis - Company research, technical analysis, price charts
  • Product research - Feature comparisons across brands, specs analysis
  • Report generation - Creates markdown reports, CSVs, charts, and visualizations
  • Multi-source synthesis - Gathers and combines information from multiple websites
  • Long-running tasks - Anything taking 1-10+ minutes of autonomous work

Research Prompt Examples

Effective research prompts are specific about scope, sources, and desired output:

Product comparison:

Find the best 4K monitors for Mac with Thunderbolt connectivity and 120Hz+ refresh rate.
Focus on BenQ, Samsung, Dell, LG. Only include models released in the last year.
Compare specs, prices, and Mac-specific features. Output a comparison table.

Sponsors

Details

Repository
github.com/sanjay3290/ai-skills
Categories
AI & Agent Building, Data Science & ML, Automation & Workflows, Finance & Trading
License
Apache-2.0
First seen
Jun 3, 2026

More from sanjay3290/ai-skills

All 20
1mongodb avataratlas-stream-processingmongodb/agent-skillsManages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle operations, debugging392skills.sh installs
2oimiragieo avatarchrome-browseroimiragieo/agent-studioBrowser automation with two integrations - Chrome DevTools MCP (always available, performance tracing) and Claude-in-Chrome extension (authenticated sessions, G389skills.sh installs
3tondevrel avatarmatplotlibtondevrel/scientific-agent-skillsThe foundational library for creating static, animated, and interactive visualizations in Python. Highly customizable and the industry standard for publication-375skills.sh installs
4wasp-lang avatarwasp-plugin-initwasp-lang/wasp-agent-pluginsAdds Wasp knowledge, LLM-friendly documentation fetching instructions, and best practices to your project's CLAUDE.md or AGENTS.md file363skills.sh installs
5nicepkg avatarresource-scoutnicepkg/ai-workflowSearch and discover Claude Code skills and MCP servers from marketplaces, GitHub repositories, and registries. Use when (1) user asks to find skills for a speci359skills.sh installs
6sanjay3290 avatargoogle-chatsanjay3290/ai-skillsInteract with Google Chat - list spaces, send messages, read conversations, and manage DMs. Use when user asks to: send a message on Google Chat, read chat mess347skills.sh installs