Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.
The English summary is being prepared. Showing the original description.
VectorSpaceLab/AREX-Skill338Updated Sep 3, 2026
FreePublished on GitHub
agent-starter-pack
Routes Agent Starter Pack tasks to the right workflow for creating, maintaining, and deploying generated agent projects.
The English summary is being prepared. Showing the original description.
Works withGemini
See how to installFiles included (23)
- SKILL.md2.6 KB
- references/cli-reference.md2.4 KB
- references/package-overview.md2.0 KB
- references/repo-provenance.md677 B
- references/repo-routing-metadata.json508 B
- references/template-catalog.md2.4 KB
- references/troubleshooting.md2.7 KB
- scripts/check_agent_starter_pack.py3.3 KB
- sub-skills/deployment-ops/references/ci-cd-reference.md1.8 KB
- sub-skills/deployment-ops/references/data-ingestion.md1.3 KB
- sub-skills/deployment-ops/references/gemini-enterprise.md1.3 KB
- sub-skills/deployment-ops/references/generated-project-commands.md1.6 KB
- sub-skills/deployment-ops/references/observability.md1.2 KB
- sub-skills/deployment-ops/references/troubleshooting.md1.7 KB
- sub-skills/deployment-ops/references/workflows.md2.1 KB
- sub-skills/deployment-ops/SKILL.md3.0 KB
- sub-skills/project-maintenance/references/troubleshooting.md2.1 KB
- sub-skills/project-maintenance/references/workflows.md2.7 KB
- sub-skills/project-maintenance/SKILL.md2.3 KB
- sub-skills/project-scaffolding/references/remote-templates.md2.3 KB
- sub-skills/project-scaffolding/references/troubleshooting.md1.7 KB
- sub-skills/project-scaffolding/references/workflows.md2.3 KB
- sub-skills/project-scaffolding/SKILL.md3.0 KB
SKILL.md (original)
Review the instructions the agent will receive before you install.
Agent Starter Pack
Use this repo skill for the agent-starter-pack Python package and CLI. It helps future agents choose templates, generate projects, maintain generated output, and wire projects into deployment and Gemini Enterprise workflows.
First check
If you only need to confirm that the package is installed and importable, use the bundled helper first:
python scripts/check_agent_starter_pack.py
For a quick command discovery check, also run:
agent-starter-pack --help
Route map
| User intent | Go here |
|---|---|
| Create a new project, compare templates, or parse a remote template | sub-skills/project-scaffolding/SKILL.md |
| Enhance, extract, or upgrade an existing generated project | sub-skills/project-maintenance/SKILL.md |
| Set up CI/CD, deploy a generated project, inspect observability, configure data ingestion, or register with Gemini Enterprise | sub-skills/deployment-ops/SKILL.md |
Read these shared references
references/package-overview.mdfor package identity, install guidance, and the command family map.references/cli-reference.mdfor the command-to-subskill mapping.references/template-catalog.mdfor the built-in agent/template list.references/troubleshooting.mdfor cross-cutting install, import, and CLI issues.references/repo-provenance.mdfor the source snapshot used to build this skill.
How to navigate
- Identify whether the user is starting from a blank slate or an existing project.
- Decide whether the question is about template selection, project maintenance, or cloud deployment.
- Read the owning sub-skill’s workflow reference before giving command details.
- If the user asks about a cloud prerequisite or generated Makefile target, switch to deployment-ops instead of staying in the root router.
What this skill is not
- It is not a runtime agent framework.
- It is not a source-repo maintenance guide for the ASP checkout itself.
- It does not import or execute the generated skill here.
Safety notes
- Generated projects can vary by language, deployment target, and template family.
- Remote templates and cloud setup may require network or credentials; do not treat those as default-safe checks.
- Do not assume the same commands exist in every generated project; use the template catalog and generated-project references to confirm.
Reviews
No reviews yet. Tell others what you thought.
Comments
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
More skills from this repository
3ddfa
FreeGuide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.
The English summary is being prepared. Showing the original description.
VectorSpaceLab/AREX-Skill338Updated Sep 3, 2026
3ddfa-v2
FreeRoutes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.
The English summary is being prepared. Showing the original description.
VectorSpaceLab/AREX-Skill338Updated Sep 3, 2026
ab3dmot
FreeOperate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.
The English summary is being prepared. Showing the original description.
VectorSpaceLab/AREX-Skill338Updated Sep 3, 2026
accelerate
FreeUse Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model inference/offload, checkpointing, tracking, and troubleshooting.
The English summary is being prepared. Showing the original description.
VectorSpaceLab/AREX-Skill338Updated Sep 3, 2026
acme
FreeRoute Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.
The English summary is being prepared. Showing the original description.
VectorSpaceLab/AREX-Skill338Updated Sep 3, 2026