AB agent-cost-strategy
Tiered model selection and cost optimization for multi-agent AI workflows. Use this skill whenever you are choosing a model for a task, spinning up a sub-agent, setting up cron jobs or heartbeats, or trying to reduce API spend. Also use when the user says "save costs", "which model should I use", "optimize model usage", "this is getting expensive", or when delegating any task to a sub-agent. Works with any AI provider.
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Flow map in block collection must be sufficiently indented and end with a } at line 3, column 110: …:"💰","requires":{"bins":[]},"os":["linux","darwin","win32"],"version":"1.3.6"} ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
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
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 14 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1309 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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 4 example trigger phrases
- +3Description length 422: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.