AB prompt-caching
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation)
The skill covers three caching approaches: Anthropic's built-in prompt caching, response caching, and CAG. Contains 3362 tokens of instructions with no critical errors, quality score 87/100. No vulnerabilities found (safety 100), but process score sits at 75—likely missing examples or depth. Positioned as an 'analyzer' and claims support across 12 platforms from Claude to DeepSeek.
In reality, this is a guide to prompt optimization via caching, not executable code. No sandbox tests or model runs happened, so actual caching gains remain unverified. Worth installing if you already understand why caching matters and can adapt examples to your platform.
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation)
As a process B 75/100 · Nearly there — weak spots: when it triggers, failures and branches
The same skill appears in 1 more place: agentic-awesome-skills
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 75/100
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 32 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3362 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (10 tags): a typed call is more reliable
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 125: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.