BD openclaw-health-monitor
Cross-platform diagnostics for OpenClaw gateways. Checks gateway health, event loop degradation, WhatsApp connectivity, service state, stuck background subagents, prewarm blocking, and generates diagnostic bundles for bug reports. See SECURITY.md for privacy disclosures. Use when: (1) Gateway feels slow or unresponsive, (2) CLI health checks take unusually long, (3) WhatsApp is not receiving messages, (4) Agent responses are delayed, (5) After OpenClaw version upgrades, (6) Routine system health check.
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
net-credential-useSKILL.md:131Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -H "Authorization: Bearer $OPENCLAW_GATEWAY_TOKEN" --max-time 10 "http://127.0.0.1:18789/health"
security skill -
low Exfiltration
net-credential-useSKILL.md:135Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)# Invoke-RestMethod -Uri "http://127.0.0.1:18789/health" -Headers @{"Authorization"="Bearer $token"} -TimeoutSec 10security skill
Files scanned: 2. 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: Nested mappings are not allowed in compact mappings at line 3, column 14: description: Cross-platform diagnostics for OpenClaw gateways. Checks gateway h… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (openclaw-health-monitor) differs from the folder (windows-health-monitor)
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 100Steps. 36 steps
- 100Execution cost. Instruction body is 2324 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +3Description length 507: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (15 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.