context-budget-planner
CommunityOptimize LLM context budgets for smarter prompts.
Software Engineering#rag#prompt-engineering#context-window#token-budget#budget-allocation#ai-systems
Authorviliawang-pm
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Plan and optimize token budget allocation for LLM context windows. Use this skill when designing system prompts, RAG pipelines, or multi-turn agents that must fit within a model's context limit. Produces a token budget breakdown, identifies waste, and suggests compression strategies to maximize the useful information density within the available context window.
Core Features & Use Cases
- Budget Allocation Framework: The 5-zone model that allocates tokens across System Instructions, Persistent Knowledge, Retrieved Context, Conversation History, and Output Reserve.
- Allocation Profiles: Predefined distributions for Chatbot, RAG Q&A, Code Agent, Document Analysis, Multi-turn Planner, and Creative Writer use cases.
- Workflow & Guidance: Step-by-step inventory, waste identification, compression strategies per zone, and a before/after budgeting report.
Quick Start
Plan token budgets for your context window by feeding current usage and model limits to generate an optimized budget.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: context-budget-planner Download link: https://github.com/viliawang-pm/ai-engineering-toolkit/archive/main.zip#context-budget-planner Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.