This AI agent helps you build code by following a specific plan step by step. It makes sure you only do what the plan says and nothing else. That stops you from adding extra features or changes that were not planned.
The agent checks off each task in the plan as you finish it. You can see your progress clearly. It also runs build or test commands to make sure everything works correctly.
When you reach the end of the plan, the agent stops and gives control back to you. This keeps your work focused and exactly on track.
Global
mkdir -p ~/.claude/skills/structured-autonomy-implementProject
mkdir -p .claude/skills/structured-autonomy-implementSource 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
Implementmattpocock/skills
Implement PRD or issue tasks with TDD tests typechecking and review
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