ReddRadar
Agent skill
agent-repo-init
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 LLM provider profile, MCP toggle, swarm preference context, sandbox type, and optional git init.
Install this agent skill to your Project
npx add-skill https://github.com/study8677/antigravity-workspace-template/tree/main/skills/agent-repo-init
SKILL.md
Agent Repo Init
Initialize a new project from this repository template with two modes.
Modes
quick: Fast scaffold with clean copy and minimal setup.full:quickplus runtime profile setup (.env, mission, context profile, init report) and optionalgit init.
Run via Script
Use the portable script in this skill directory:
python skills/agent-repo-init/scripts/init_project.py \
--project-name my-agent \
--destination-root /absolute/path \
--mode quick
Full mode example:
python skills/agent-repo-init/scripts/init_project.py \
--project-name my-agent \
--destination-root /absolute/path \
--mode full \
--llm-provider openai \
--enable-mcp \
--disable-swarm \
--sandbox-runtime microsandbox \
--init-git
Expected Output
- New project at
<destination_root>/<project_name> - Clean copy without local runtime state
- Initialization report at
artifacts/logs/agent_repo_init_report.md - Script is self-contained and does not import project
src/modules
Notes
- Keep destination outside the current template repository.
- For
fullmode, review.context/agent_runtime_profile.mdafter generation.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
study8677/antigravity-workspace-template
graph-retrieval
study8677/antigravity-workspace-template
agent-repo-init
study8677/antigravity-workspace-template
research
study8677/antigravity-workspace-template
knowledge-layer
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
davila7/claude-code-templates
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Didn't find tool you were looking for?