AC prompt-caching-strategy
Optimize LLM prompt caching hit rate to reduce API costs and improve latency. Analyzes prompt structure, identifies cacheable vs non-cacheable content, and recommends restructuring to maximize cache reuse. TRIGGER when: user says "prompt cache", "cache hit rate", "reduce LLM cost", "optimize token usage", "cheaper LLM calls", or asks about prompt caching strategies for OpenAI/Anthropic/other providers. DO NOT TRIGGER when: user just wants to optimize a single prompt's quality (use prompt-optimizer instead), or asks about general caching infrastructure.
This skill teaches your AI agent to analyze prompt structure and squeeze maximum value from OpenAI and Anthropic caching. It promises to cut API costs and latency by restructuring content—separating static parts (which cache) from dynamic ones (which change per request).
Data shows grade A and quality_score 89. Single file, no syntax errors, no critical findings. Never ran on models. Supports nine platforms including Claude and Cursor. The logic is straightforward: if your prompt contains large context that repeats across requests, caching saves tokens and money. Without sandbox testing, accuracy of restructuring recommendations remains unclear.
Install if you repeatedly send identical system prompts through APIs and pay per token. Skip it if your calls are heterogeneous or you've already hand-optimized caching.
Optimize LLM prompt caching hit rate to reduce API costs and improve latency.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
The same skill appears in 1 more place: everything-claude-code
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2352 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 558: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.