Cristian Ruiz Jr
Community@cxxxxdxxxf
Rutgers '27 | Swift & Python Dev. Building Rhythm and automation tools.
Agent Skills by Cristian Ruiz Jr
Showing 34 vetted skills indexed across 1 GitHub repositories.
CxxxxDxxxFcontext-engineering-collection
Guide context engineering for AI agents covering compression, memory, and evaluation.
CxxxxDxxxFllmfit-advisor
Analyze local hardware to recommend LLMs with quantization and speed estimates.
CxxxxDxxxFask-user-question
Ask users questions through interactive UI modals with selectable options.
CxxxxDxxxFcomplete_task
Report task completion status with success, blocked, or partial summaries.
CxxxxDxxxFdev-browser
Automate browser interactions for web scraping, form submission, and UI testing.
CxxxxDxxxFsafe-file-deletion
Require explicit user consent before deleting files or directories.
CxxxxDxxxFskill-template
Create new Agent Skills using a standardized template with mandatory and optional sections.
CxxxxDxxxFdigital_brain
Manage personal knowledge, content creation, relationships, and productivity with JSONL, YAML, and Markdown files.
CxxxxDxxxFreasoning-trace-optimizer
Analyze AI agent reasoning traces to detect failure patterns and optimize prompts.
CxxxxDxxxFbook-sft-pipeline
Convert books into SFT datasets and train LoRA models.
CxxxxDxxxFcomprehensive-research-agent
Orchestrate web searches, URL reads, and file operations with validation checkpoints.
CxxxxDxxxFmulti-agent-patterns
Implement supervisor, swarm, and hierarchical patterns for multi-agent systems.
CxxxxDxxxFbdi-mental-states
Implement BDI cognitive architectures using formal ontologies and RDF.
CxxxxDxxxFcontext-degradation
Diagnose context degradation patterns like lost-in-middle and context poisoning in AI models.
CxxxxDxxxFcontext-compression
Compress LLM conversational context using iterative summarization and opaque compression.
CxxxxDxxxFmemory-systems
Compare production memory frameworks and design persistence architectures for agent memory systems.
CxxxxDxxxFadvanced-evaluation
Evaluate LLM outputs with LLM-as-a-judge pipelines and bias mitigation.
CxxxxDxxxFcontext-fundamentals
Explain context engineering principles for AI agent systems.
CxxxxDxxxFproject-development
Guide LLM project planning, pipeline design, cost estimation, and development.
CxxxxDxxxFevaluation
Create multi-dimensional rubrics and stratified test sets for AI agent evaluation.
CxxxxDxxxFcontext-optimization
Compact conversations, mask observations, optimize KV-cache, and partition context for LLM token limits.
CxxxxDxxxFfilesystem-context
Manage dynamic agent context by offloading outputs to filesystem files.
CxxxxDxxxFtool-design
Design clear tool APIs and error messages for AI agents.
CxxxxDxxxFhosted-agents
Deploy remote sandboxed agent execution environments using pre-built container images.