Use prompt-caching-advisor

Analyzes a prompt or conversation structure and identifies the highest-value cache breakpoints

Analyzes a prompt or conversation structure and identifies the highest-value cache breakpoints — where to insert cache_control checkpoints to minimize repeated token processing.

Reach for it when designing or optimizing a Claude API integration that uses prompt caching, when input costs are dominated by a static system prompt or few-shot block, or when a multi-turn conversation reprocesses the same context on every turn.

Install it

npx skilldrop-cli install prompt-caching-advisor                 # Claude Code, your user folder
npx skilldrop-cli install prompt-caching-advisor --project       # Claude Code, this repo
npx skilldrop-cli install prompt-caching-advisor --ide cursor    # or kiro, codex, antigravity, copilot

It is part of the API builder pack: --pack api-builder installs it with its neighbours.

Ask for it

Say it the way you would to a colleague. Requests like these route to it:

• "Where should I put cache_control in this messages array?"
• "Our input costs are dominated by a static 10k-token system prompt — how do we cache it?"
• "Every turn of our chat agent reprocesses the same docs; help me place cache breakpoints"
• "Why is our prompt cache hit rate near zero? Here's the request structure"

Requests like these belong to a different skill, so it shouldn't answer them:

• "Estimate how many tokens per session our research agent will use and what drives it"
• "Set a per-agent spending cap and kill switch for our autonomous agents"
• "Size max_tokens for each component of this agentic workflow"

If another skill answers instead, ask for this one by name: "use prompt-caching-advisor".

Check what you get

A good result:

• Never cache dynamic content. A user query, a timestamp, a database result retrieved per-request — these must not appear in a cached block. If the user's structure embeds dynamic content in an otherwise static block, flag it before recommending the cache.
• One breakpoint per logical boundary. A system prompt with three sections (instructions, reference docs, examples) can have up to three breakpoints. More than four breakpoints on a single request is a signal the structure needs rethinking.
• The last block caches everything before it. This is the most common misunderstanding — the cache breakpoint is not a marker for just that block, it's a marker for the entire prefix up to that point.

Next

• SKILL.md, the instructions the agent reads
• Its page on the site
• Related: token-budget-estimator

Edit this page on GitHub · View source