Symphony helps you turn project work into isolated autonomous coding runs. Instead of watching an agent code, you define tasks and let agents complete them. Each task gets its own branch and proof of work like CI status and PR reviews. You manage work instead of supervising agents.
Teams can integrate Symphony with a work tracker like Linear. Agents spawn automatically for each task. They implement the code, open a pull request, and show proof of completion. Engineers then review the results, not the agent sessions. This makes coding workflows faster and less hands-on.
Global
mkdir -p ~/.claude/skills/openai-symphony-autonomous-agentsProject
mkdir -p .claude/skills/openai-symphony-autonomous-agentsSource Repository
Lark Drivelarksuite/cli
Organize Lark cloud files import export manage permissions and versions
Lark Eventlarksuite/cli
Stream Lark events in real time with simple CLI commands
Lark Workflow Meeting Summarylarksuite/cli
Turn your Lark meeting notes into organized weekly summaries with ease
Lark Approvallarksuite/cli
Easily manage Lark approval instances and tasks from your command line
Executing Plansobra/superpowers
Load a plan review critically then execute each task with verifications
Subagent Driven Developmentobra/superpowers
Execute plans with fresh subagents per task and thorough reviews for fast iteration
Churn Preventioncoreyhaines31/marketingskills
Reduce customer churn with smart cancel flows and failed payment recovery
Baoyu Danger X To Markdownjimliu/baoyu-skills
Save X tweets and articles as markdown files with YAML front matter