Menu
Professional bootstrapper for Vercel-style Agentic Repositories using compressed AGENTS.md manifests.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Persistent SQLite-based cognitive layer for cross-session interaction logging and insight distillation.
Design lead for C4 structural documentation, Mermaid.js diagrams, and Architecture Decision Records (ADRs).
Specialist in core AWS infrastructure: EC2 compute, IAM identity, VPC networking, and RDS/Aurora databases.
5-phase migration engine for transitioning workloads from Google Cloud Platform to AWS architecture.
AI/ML infrastructure expert for SageMaker fine-tuning, HyperPod cluster management, and dataset evaluation.
Developer for event-driven AWS architectures using Lambda, Step Functions, EventBridge, and API Gateway.
| name | skill-agentic-initializer |
| description | Professional bootstrapper for Vercel-style Agentic Repositories using compressed AGENTS.md manifests. |
This skill automates the creation of a high-performance AGENTS.md manifest. Inspired by Vercel's research, it prioritizes "retrieval-led reasoning" over model pre-training by embedding a compressed documentation index directly into the repository root.
{PROJECT_DIR}/docs/) using {SKILL_DIR}/scripts/scanner.py.AGENTS.md that acts as the primary cognitive guide for LLM agents, ensuring they always have access to version-matched documentation.# Initialize a repository with Vercel-style AGENTS.md
python3 {SKILL_DIR}/scripts/logic.py <target_path> <project_name> [docs_dir]
{SKILL_DIR}/references/vercel-agents-md.md for the original research findings by Jude Gao (Next.js/Vercel).