basecamp/fizzy-cli

Fizzy CLI and Agent Skills

Owned by Basecamp

View on GitHub ↗Jump to charts ↓Open shareable report →

basecamp/fizzy-cli has 200+ stars and 30+ forks on GitHub, is written in Go, and was last pushed on Oct 13, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 22 minutes ago
Added to GitGenius on October 12th, 2026
Created on December 10th, 2025
Open Issues & Pull Requests: 5 (+0)
GitHub issues: Enabled
Number of forks: 30
Total Stargazers: 247 (+0)
Total Subscribers: 3 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 1.3 hours
Mean response time: 11.7 days
90th percentile: 39.1 days
Tracked items: 20

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 1
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 34 days
Stale 30+ days: 1
Stale 90+ days: 0

Recent activity

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

Top labels

  • upstream-api-change (3)
  • bug (1)

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Fizzy CLI is a command-line tool that enables developers to build and manage agent skills for AI-powered automation workflows.

The tool addresses the challenge of creating reusable, composable capabilities for AI agents by providing a structured framework for defining, testing, and deploying skills. Fizzy CLI allows developers to write skills in a standardized way that can be discovered and executed by AI agents, abstracting away the complexity of agent integration and skill orchestration. The approach centers on making skills first-class components that can be versioned, shared, and combined to build sophisticated automation systems.

Developers should adopt Fizzy CLI if they are building AI agent systems that require extensible, modular capabilities or if they want to create a marketplace of reusable skills for agent-based workflows. The tool is suited for teams working on automation platforms, AI assistants, or systems where multiple agents need access to a common set of well-defined operations. It works best in environments where skill reusability and standardization across different agents or workflows is a priority.

The project shows active development with regular commits addressing bug fixes and feature improvements. The codebase demonstrates attention to code quality through consistent refactoring and cleanup efforts. Documentation is maintained alongside code changes, indicating a commitment to keeping guidance current with implementation. The project accepts external contributions and processes pull requests, suggesting openness to community involvement in its evolution.