Context Engineering Pipeline

Diagnostic-and-fix pipeline for systematic context engineering — fix agent context, context engineering, context optimization pipeline, diagnose context problems. Chains context-fundamentals (attention, budgeting), context-optimization (KV-cache, partitioning, observation masking), context-compression (summarization, anchored iterative, tokens-per-task), context-degradation (lost-in-middle, poisoning, clash diagnosis), and filesystem-context (scratch pads, plan files, dynamic loading). Use when an agent's context is degrading, token costs are bloated, the agent forgets instructions mid-session, output quality drops in long conversations, or building a new agent and wanting context right from the start. NOT for prompt engineering — use prompt-engineering. NOT for agent architecture — use build-ai-agent.

viktorbezdek Updated 14 repo stars

File contents

viktorbezdek/skillstack commit 3ab1620df3 Runs: viktorbezdek/context-fundamentalsviktorbezdek/context-optimizationviktorbezdek/context-compression

Frequently asked questions

npx get-skill add viktorbezdek/context-engineering-pipeline