AB amazon
Search Amazon products, retrieve known product details, and collect product reviews through the official Gecho Bridge MCP tools. Use for marketplace discovery, catalog research, product comparison, review analysis, and ASIN-level research.
As a process B 75/100 · Nearly there — no weak spots found
AnalyzerGitHubAI and agentsInfrastructureCommercetype and topics are labelled automatically from the skill text
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
For the model run — optional
- 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
description-long-hermesdescription is 239 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 75/100
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Consistency. The Hermes dialect needs category and tags
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4420 tokens
- 100Steps. 103 steps
- 100Failures and branches. 10 branches, has a failure section
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 18 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
- +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 239: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 103 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.
External checks
ClawHub: clean
This skill is a clearly scoped Amazon research connector that uses Gecho's MCP tools and logged-in browser setup to read product and review data, with no artifact evidence of hidden mutation or exfiltration behavior.
LLM: benign (high) · VirusTotal: · 22 Aug 2026