SKILLEMALL.ai
GitHub ↗ RU Sign in

AC llm-regression-monitor

Use this skill when the user wants to monitor LLM behavior over time and get alerted when outputs change unexpectedly. Triggers on requests like "set up LLM regression monitoring", "alert me when my prompts start behaving differently", "watch my LLM for regressions", "run behavioral tests on my AI outputs on a schedule", or "detect when my model starts drifting". Handles first-time setup, baseline capture, scheduled monitoring, and alert configuration via WhatsApp, Slack, Discord, or email.

ClawHub Agent Skills author: Swanand33 v1.1.0 MIT-0 9 files body ≈ 1 128 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

AnalyzerSlackDiscordWhatsAppAI and agentsInfrastructureData and analyticstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
91/100
safety, quality, tests
Safety 60%
88
Quality 40%
96
Run on models
none yet
Process rating
C
53/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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".

For the author

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

    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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Exfiltration net-redirectable-api-key scripts/capture_baseline.py:87
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • medium Exfiltration net-redirectable-api-key scripts/run_monitor.py:86
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • low Exfiltration exfil-webhook-url SKILL.md:148
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      ALERT_SLACK_WEBHOOK="https://hooks.slack.com/services/..."
      placeholder
    • low Exfiltration exfil-webhook-url SKILL.md:151
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      ALERT_DISCORD_WEBHOOK="https://discord.com/api/webhooks/..."
      placeholder

    Files scanned: 9. 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 53/100

    • 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. 7 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 75Steps. 3 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1128 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)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 5 example trigger phrases
    • +3Description length 495: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 3 items
    • +4Has examples (11 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)
    • +3All 4 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.

    External checks

    ClawHub: clean
    This skill performs disclosed LLM regression monitoring with local reports and user-configured alerts, with some privacy and dependency hygiene caveats.
    LLM: benign (high) · VirusTotal: · 2 Sept 2026