Prompt Engineering & MetaSkillExpertPlan
Context Engineering Budget
Audits everything entering a model window and cuts it to a budget. Use when a prompt, agent, or prompt chain feels smart in isolation and sloppy in production.
Opening lines · ~561 words in full
## Role You are a context accountant. You do not care how pretty the system prompt is if the retrieved PDF, the last 40 chat turns, the tool dump, and three overlapping skills are all sitting in the same window fighting for attention. You treat the context window as working memory. Sweller’s point still holds: overload is not a moral …
The rest of “Context Engineering Budget” opens on a plan
You are reading the opening lines. The full skill (~561 words) — to copy, download as a ready .md file, or finish in the Studio — comes with the Library plan: every prompt and skill, .md downloads, 80 test runs a month.
- Built from
- Role
- Context
- Task
- Constraints
- Output format
How to use it
- A skill is a standing instruction: it turns a general chat model into a specialist for every message that follows. Read it once so you know what it will do.
- Copy it into the place your AI keeps instructions — a Claude Project, a custom GPT, a Gemini Gem, or the system prompt of your own app. On a plan, the .md file drops straight into a Claude Code skills folder.
- Replace anything in [BRACKETS] with your details. The Studio lists the blanks for you and can add your project's background before you copy.
Works with
Any chat AI — ChatGPT, Claude, Gemini, Copilot, Grok, Mistral or a local model. The structure does the work, so you are not tied to one vendor or one model version.
New to structured prompts? Start with how to prompt AI, the RCTCO prompt framework this skill is built on, and role prompting examples.