AC superwise-drift-detection-skill
Detects feature drift in tabular ML models using Superwise Compare Distribution policies (Jensen-Shannon divergence for categorical columns). Handles everything: Superwise dataset creation, training data upload, drift policy setup, inference ingestion, and Telegram alerts via OpenClaw's existing Telegram connection. Use when: user says "set up drift detection", "detect model drift", "monitor my model for drift", "check if my model is drifting", or "add drift detection to my model".
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Exfiltration
net-redirectable-api-keyskill.py:77Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Dangerous commands
cmd-background-processSKILL.md:142Starts a background / autostarted processnohup python -c "..." &> drift_check.log &
-
low Exfiltration
exfil-webhook-urlskill.py:343Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)f"https://api.telegram.org/bot{token}/sendMessage",vendor-hostquoted
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 11 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 22 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1990 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 486: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 22 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.