Context Window Engineer
$2.99OfficialOptimize how context is assembled for LLM calls: system prompt design, few-shot example selection, context pruning, and token budget management.
Model requirements
advanced
33k tokens
Preview
When to use
Use this skill when the user needs to improve an agent's performance by optimizing what goes into its context window: "the agent forgets instructions," "it's not following the format," "context is too long and expensive," "which examples should I include?" Trigger phrases: context engineering, system prompt, few-shot, context window, token budget, prompt assembly, context pruning.
Do NOT use it for building RAG (that's retrieval), agent memory (that's cross-session recall), or for tuning a single prompt's wording in isolation (that's prompt tuning). Context engineering is about the architecture of what fills the window for each call: the structure, selection, ordering, and
…
🔒 Buy this skill once ($2.99) to unlock the full playbook and install it anywhere — or get everything with Pro.