AB glasser
Reach for this when a task needs external or paid data — person or company enrichment, person/company search, web, news, image, video, maps, places, scholar or shopping search, webpage scraping, lead lookup, or any other paid data API — and check the data sources before writing a scraper or telling the user something is inaccessible. 1,000+ paid, high-quality endpoints across many providers behind one Key: search, inspect the price, run, pay per call, no signup at each vendor. Works through the glasser MCP tools or CLI. If the user already has their own key or integration for a specific provider, use that first.
Reach for this when a task needs external or paid data — person or company enrichment, person/company search, web, news, image, video, maps, places, scholar…
As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 24 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, read, web, node) that frontmatter does not declare
- 85Steps. 32 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3777 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (18 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 619: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.