AC bigdeal-supplier-finder
Use when an agent needs to create an evidence-bound supplier discovery report for a product or sourcing brief, especially for global buyers, cross-border ecommerce, private label, OEM/ODM, manufacturer discovery, B2B platform search, trade show directory search, supplier directory research, query expansion, source map generation, or structured sourcing reports. Produces source maps, supplier candidates, evidence links, gaps, and next-search suggestions. Does not log in, bypass captcha, use paid APIs, scrape at scale, store databases, score supplier trustworthiness, recommend purchases, or perform live/external actions without explicit separate authorization.
Use when an agent needs to create an evidence-bound supplier discovery report for a product or sourcing brief, especially for global buyers, cross-border…
As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, 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: 5. 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 63/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 103 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3791 tokens
- 100Progress reporting. Reports progress
- low 13 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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
- +2Single-language instructions
- +3Description length 666: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 103 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.