AB mail-agent
Set up AI-powered Gmail monitoring in OpenClaw. Watches inbox via Google Pub/Sub and pushes important emails to Telegram. Use when the user wants to install mail-agent, set up email notifications, configure Gmail monitoring, or troubleshoot why email alerts aren't arriving.
As a process B 71/100 · Nearly there — weak spots: result and completion, consistency
ProcedureGmailTelegramInfrastructureAI and agentstype and topics are labelled automatically from the skill text
How to improve
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: 6. 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 71/100
- 0Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (mail-agent) differs from the folder (openclaw-mail-agent)
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 4 steps
- 100Execution cost. Instruction body is 889 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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
- +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 274: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (19 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.
External checks
ClawHub: suspicious
This Gmail monitor appears purpose-built, but it needs review because it forwards email-derived data to external services and its install step may fetch code that does not match the reviewed artifact.
LLM: suspicious (high) · VirusTotal: · 29 May 2026