Sounder25

This skill prunes repository context to relevant files based on focus topics, reducing noise and preserving essential code.

This skill rapidly ingests llms.txt documentation to provide fast, accurate context for libraries and APIs.

This skill safely removes build artifacts like bin and obj, respects gitignore, and frees disk space while avoiding source deletion.

This skill creates isolated swarm sub-workspaces and prepares task-specific prompts and context for parallel worker agents to execute immediately.

This skill enforces a deterministic planning phase by generating and validating PLAN.json with objectives, steps, verification, and rollback guidance.

This skill validates high-stakes actions before execution, preventing data loss by ensuring safety rules align with the current plan.

This skill generates a red-team critique of recent code to reveal weaknesses, edge cases, and overlooked assumptions before finalization.

This skill detects drift across multiple git repositories, reports ahead/behind status, and optionally applies safe sync actions.

This skill records and analyzes failures to identify root causes and preventive rules, ensuring durable postmortems and reduced recurrence.

This skill generates comprehensive dependency maps across codebases to identify single points of failure and reveal impact chains for safer refactoring.

This skill generates a complete workspace profile with git signals and build configs, enabling downstream tools to verify forensics completeness.

This skill detects and prevents state-visibility violations across execution contexts within a transaction to ensure consistent code and storage visibility.

This skill exposes an MCP server interface to Antigravity, enabling external agents to invoke skills as native tools.

This skill updates standardized breadcrumbs across sessions by maintaining NEXT.md and STATE.json to preserve context and streamline agent work.

This skill safely renames a .NET solution, projects, and namespaces, with planned and recovery modes to prevent data loss.

This skill enables mid-task course correction by monitoring FEEDBACK.md and applying user guidance without restarting.