foryourhealth111-pixel/vibe-skills

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 34 minutes ago
Added to GitGenius on September 20th, 2026
Created on February 22nd, 2026
Open Issues & Pull Requests: 42 (+0)
GitHub issues: Enabled
Number of forks: 294
Total Stargazers: 3,381 (+0)
Total Subscribers: 87 (+0)

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 37
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 74 days
Stale 30+ days: 32
Stale 90+ days: 11

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • ready-for-agent (25)
  • documentation (3)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Vibe Skills is an agent framework that provides intelligent skill routing and workflow orchestration for AI agents.

The tool addresses the challenge of efficiently directing AI agents to appropriate skills and coordinating complex workflows. It uses a routing mechanism that intelligently selects which skills an agent should employ for a given task, combined with orchestration capabilities that manage the execution flow across multiple skills. This approach reduces unnecessary token consumption while improving task completion quality, as demonstrated through performance benchmarks on skill selection tasks.

Developers building multi-agent systems or agentic applications should consider this tool when they need to optimize both the accuracy of skill selection and the efficiency of token usage. It suits projects where agents must choose from a diverse set of available skills and coordinate their execution in structured workflows. The framework integrates with large language models and is designed for scenarios where reducing computational overhead while maintaining or improving output quality is important.

The project shows active development with regular commits addressing core functionality and performance improvements. Work spans multiple areas including the routing logic itself, integration with different model backends, and refinement of the orchestration system. The codebase receives updates that balance feature expansion with optimization of existing components.