engine/antigravity_engine/skills/agent-repo-init/SKILL.md
Bootstraps a new multi-agent repository from the Antigravity template via `init_agent_repo`. Supports quick scaffold and full runtime profile setup including MCP toggle, swarm preference, sandbox type, and optional git init. LLM configuration is handled later by ag-setup.
npx skillsauth add study8677/antigravity-workspace-template agent-repo-initInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill bootstraps a new multi-agent repository from the Antigravity template.
When asked to initialize a fresh repository from this template, call init_agent_repo.
quick: Fast clean scaffold.full: Quick scaffold plus runtime profile setup (.env, mission, context profile, and init report).init_agent_repo(project_name, destination_root=".", mode="quick", enable_mcp=False, enable_swarm=True, sandbox_runtime="local", init_git=False) -> dict<destination_root>/<project_name>.full mode, review .context/agent_runtime_profile.md after generation./ag-setup in the generated project to choose and write the LLM endpoint.tools
One-click initialization of a multi-agent repository from the Antigravity template. Use this skill when users want to scaffold a new project quickly (`quick` mode) or with runtime defaults (`full` mode) including MCP toggle, swarm preference context, sandbox type, and optional git init. LLM configuration is handled later by ag-setup.
research
Performs deep research on a topic via `deep_research`. Simulates a multi-step research process and returns a comprehensive research result as a string.
development
High-level deployment wrapper over Antigravity core with graph-first knowledge injection and all-file support. Exposes `refresh_filesystem` and `ask_filesystem` for building and querying the knowledge graph.
tools
Exposes graph-based retrieval as a tool capability via `query_graph`. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.