SKILLEMALL.ai

BF iaiops-energy

Vendor-neutral, governed, READ-ONLY energy/substation telecontrol data tap — the energy edition (变电/电力) of Industrial-AIOps. Monitor-direction telemetry over IEC 60870-5-104 (IEC-104: RTU link status, general interrogation, single monitored-point reads by IOA — 遥测/遥信), DNP3 / IEEE 1815 (outstation link status, Class 0/1/2/3 integrity poll), and IEC 61850 MMS (IED logical-device directory, model browse, data-attribute reads) — plus the base cross-protocol brain (dataflow diagnosis, alarm bad-actors, data-quality scorecards, OEE, asset inventory, compliance self-assessment) mounted on the same server. Use when the task names IEC 60870-5-104 / IEC-104 / 104规约, DNP3 / IEEE 1815 / outstation, IEC 61850 / MMS / IED / GOOSE (GOOSE and Sampled Values are NOT supported — MMS reads only), a substation / 变电站 / RTU / SCADA gateway / telecontrol front-end, energy / power / utility SCADA telemetry, or 遥测遥信 / 电力监控. Routes to the iaiops-energy MCP server. Monitor-only by design: no control/operate (CROB, setpoints, select-before-operate, IEC-104 command ASDUs) is exposed. Do NOT use for factory/building/process protocols (OPC-UA, Modbus, S7, BACnet, MQTT …) — those live in the base iaiops server — nor for IT/network gear, Kubernetes, hypervisors, or backups.

ClawHub Agent Skills author: wei zhou v0.1.12 MIT-0 2 files body ≈ 2 022 tokens Open the sourceclawhub.ai analyzed 2 d ago

Vendor-neutral, governed, READ-ONLY energy/substation telecontrol data tap — the energy edition (变电/电力) of Industrial-AIOps.

As a process F 36/100 · Will not run — References files that are not bundled: scripts/build_pydnp3.sh

ProcedureKubernetesInfrastructureAI and agentsSecuritytype and topics are labelled automatically from the skill text
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
100
Quality 40%
54
Run on models
none yet
Process rating
F
36/100
Will not run
References files that are not bundled: scripts/build_pydnp3.sh
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
  2. The text references files that are not there: add them or drop the references.
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: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1262 chars, limit 1024
  • warning missing-ref reference to a missing file: scripts/build_pydnp3.sh

Process rating: all ten parameters 36/100

Will not run. References files that are not bundled: scripts/build_pydnp3.sh
  • 0Tools and files. 1 referenced file(s) missing: scripts/build_pydnp3.sh
  • 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
  • 30Running it twice. 3 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 100Steps. 13 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2022 tokens
  • 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
  • +3Description length 1262: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 13 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.

External checks

ClawHub: clean
This skill is a clearly scoped, read-only energy telemetry integration, though users should treat live substation access and the external pip package as sensitive.
LLM: benign (medium) · VirusTotal: · 2 Aug 2026