Agent Skills Hub

loading-insurance-data

Load, validate, and preprocess weekly insurance policy CSV data with intelligent period detection and standardization.

context-degradation

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

code-search-selector

Intelligent tool selector for code search. Routes queries between semantic (claudemem) and native tools (Grep/Glob) to optimize efficiency, token usage, and search accuracy.

sync-docs

Synchronize project documentation with codebase changes. Detect stale docs, version mismatches, missing exports, and update the CHANGELOG automatically.

skills-hub

Manage, sync, and apply AI agent skills, kits, and presets using the Skills Hub CLI. Streamline your project setup by browsing catalogs, inspecting configurations, and deploying curated instruction policies and skill packages.

strategy-scaling-architecture

Architectural planning and scaling for spectre-build, covering GUI, server layers, multi-model support, and industrial pipeline orchestration.

design-md

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files to serve as a source of truth for AI-driven UI generation.

rxswift-memory-check

Swift memory leak detection for iOS: identifies missing dispose bags, retain cycles, and strong self references in RxSwift code.

code-review-expert

Expert code review agent that performs systematic audits of git changes for SOLID violations, security vulnerabilities, performance regressions, and architectural smells.

root-cause-tracing

Systematic debugging skill to trace errors backward through call stacks, identify original triggers, and implement layered defenses instead of patching symptoms.

self-reviewer

Implements an autonomous, critical self-verification layer for AI agents to validate code quality, security, and requirement alignment before task completion.

speckit-workflow

A constitution-driven, spec-first development workflow for Claude Code and Codex, automating feature planning, implementation, and quality assurance through structured agentic loops.