BC iaiops
Vendor-neutral, governed industrial/OT data tap + intelligent troubleshooting. Read (and, gated, write) PLCs, controllers, machine tools and IIoT brokers over OPC-UA, Modbus-TCP, Siemens S7comm, Mitsubishi MC, Omron FINS, MTConnect, MQTT/Sparkplug B, Allen-Bradley EtherNet/IP, EtherCAT (pysoem/SOEM), SECS/GEM (semiconductor / display fab equipment over HSMS), PROFINET (DCP discovery), the building edition (BACnet/IP), and Phoenix Contact PLCnext vPLC — plus cross-protocol diagnostics ("no-data" dataflow diagnosis, OPC-UA connection self-diagnosis, subscription health, ISA-18.2 alarm bad-actors, tag/historian health, and the AI downtime root-cause copilot) and analytics (OEE/downtime, asset inventory, OPC-UA HDA, change-of-value). Use when the task names any industrial protocol, a PLC/SCADA/HMI/historian/CNC/RTU/IED, a semiconductor/display fab or SECS/GEM equipment, an electrical substation, an opc.tcp:// or mqtt:// endpoint, OEE/downtime, downtime root-cause, or OT asset inventory. Routes to the iaiops MCP server. Read-first; writes are MOC-gated (high risk, dry-run + double-confirm). Do NOT use for IT/network gear, Kubernetes, hypervisors, or backups — those are separate AIops tools.
Vendor-neutral, governed industrial/OT data tap + intelligent troubleshooting.
As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Shorten the description to 1024 characters.
- 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
- error
description-longdescription is 1204 chars, limit 1024
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1342 tokens
- 100Running it twice. No mutating operations
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
- +3Description length 1204: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 7 headings
- +3Step-by-step instructions: 15 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.