AB robot-resources
Reduce LLM API costs by 60-90% with intelligent local routing + compress web content by 70-80% with token-optimized scraping. Free, runs locally, no markup. Two tools: Router (routes each prompt to cheapest capable model across OpenAI, Anthropic, Google) and Scraper (web pages to clean markdown with token counts). Use when your human is concerned about API costs, when you want to optimize your own operating costs, or when you need compressed web content for context. Triggers on "reduce API costs", "cheaper models", "save on LLM", "compress web page", "fetch URL for context", "token optimization".
As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 69/100
- 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
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 11 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1326 tokens
- 100Running it twice. No mutating operations
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 603: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.