By viktorbezdek
Patterns for recognizing and mitigating context failures in LLM agents. Covers lost-in-middle, context poisoning, distraction, confusion, clash, and empirical degradation thresholds by model.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub viktorbezdek/skillstack --plugin context-degradationBelief-Desire-Intention cognitive architecture for LLM agents. Formal BDI ontology, T2B2T paradigm, RDF integration, SPARQL competency queries, and neuro-symbolic AI integration patterns.
Apply systems thinking principles including feedback loops, leverage points, and system dynamics to analyze complex problems.
Comprehensive prompt optimization system for LLMs. Design effective AI interactions, evaluate prompt quality, and perform iterative refinement for any LLM platform.
Comprehensive Test-Driven Development skill implementing Red-Green-Refactor cycle across Python, TypeScript, JavaScript, and Emacs Lisp. Covers pytest, Vitest, Playwright, ERT, and Zod.
Design content models with types, fields, relationships, and governance rules for structured content systems.
Skill memory layer for Claude Code — auto-capture, learn, and reuse skills from Acontext
AI agent skill pipeline: plan-interview, intent-framed-agent, context-surfing, simplify-and-harden, self-improvement, and agent-teams-simplify-and-harden. Prevents scope drift, context degradation, rough code, and repeated mistakes.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Memory compression system for Claude Code - persist context across sessions
Editorial "Web Designer" bundle for Claude Code from Antigravity Awesome Skills.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.