Agent Skills Hub

pytorch-lightning

PyTorch Lightning skill for scalable deep learning: automates model training, multi-GPU orchestration, data pipelines, and distributed training strategies like DDP, FSDP, and DeepSpeed.

quality

Expert code reviewer for Rust projects. Performs comprehensive quality, security, performance, and architectural analysis using Bazel and project-specific conventions.

CCOS MCP Tools

Reference for all MCP tools exposed by the CCOS server, enabling capability discovery, session management, and governed RTFS execution for autonomous agent workflows.

multi-agent-patterns

Architect multi-agent systems to overcome context limits, using patterns like supervisor, swarm, and hierarchical models to manage complex workflows.

solana

Expert Solana Anchor development: build programs, manage PDAs, implement SPL tokens, handle security audits, and perform fuzz testing with Trident.

implementation

Structured, template-driven workflow for end-to-end feature development including coding, automated testing, verification, and session-based improvement.

design-review

Designer's eye QA: detects and automates fixes for visual inconsistencies, spacing, hierarchy, and UI polish issues. Iteratively verifies with before/after screenshots.

flutter-errors

Diagnoses and resolves common Flutter runtime and layout errors such as RenderFlex overflow, unbounded constraints, and state management issues.

xss-testing

Automated security skill for identifying and validating XSS vulnerabilities, including Reflected, Stored, and DOM-based attacks across various contexts.

Data Optimizer Pro

A security scanner for Claude Skills to detect malicious code, data exfiltration risks, and unauthorized system access before installation.

task-breakdown

Break down complex development requests into sequenced, actionable tasks for multi-agent delegation in Claude Code environments.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.