SKILLEMALL.ai
GitHub ↗ RU Sign in

DC astrill-watchdog

(no description)

Not recommendedlow grade D
ClawHub Agent Skills author: LittleJakub v2.0.0 6 files · 2 scripts body ≈ 573 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

ProcedureInfrastructuretype 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
D
53/100
safety, quality, tests
Safety 60%
88
Quality 40%
0
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
When it triggers w 12
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. Add a description to the frontmatter: without it the skill never triggers.
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 · 12

✓ No critical or high findings

Medium and low: 12
  • low Dangerous commands cmd-background-process _meta.json:5
    Starts a background / autostarted process (detector / deny-list definition; string literal in code, not executed)
    "description": "Monitors Astrill StealthVPN on Ubuntu and auto-restarts it when the tunnel drops. Uses tun0 + ping detection and setsid relaunch with full Wayland environment. No sudo required.",
    detectorcode literal
  • low Dangerous commands cmd-background-process _meta.json:8
    Starts a background / autostarted process (detector / deny-list definition; string literal in code, not executed)
    "requires": ["ping", "ip", "pgrep", "pkill", "setsid"],
    detectorcode literal
  • low Dangerous commands cmd-background-process astrill-watchdog.sh:7
    Starts a background / autostarted process (code comment)
    # Astrill restart: pkill + setsid /autostart. Astrill auto-connects to the
    comment
  • low Dangerous commands cmd-background-process astrill-watchdog.sh:17
    Starts a background / autostarted process (detector / deny-list definition; code comment)
    #   - Tools: ping, ip, pgrep, pkill, setsid (Ubuntu defaults). No sudo.
    detectorcomment
  • low Dangerous commands cmd-background-process astrill-watchdog.sh:43
    Starts a background / autostarted process (code comment)
    # setsid gives Astrill its own session so it can initialize its GUI/Wayland
    comment
  • low Dangerous commands cmd-background-process astrill-watchdog.sh:127
    Starts a background / autostarted process (string literal in code, not executed)
    log "INFO" "  → Restarting Astrill via setsid /autostart"
    code literal
  • low Dangerous commands cmd-background-process astrill-watchdog.sh:137
    Starts a background / autostarted process (string literal in code, not executed)
    env "${DESKTOP_ENV[@]}" setsid "$ASTRILL_BIN" /autostart &>/dev/null &
    code literal
  • low Dangerous commands cmd-background-process CHANGELOG.md:17
    Starts a background / autostarted process (quoted — discussed, not commanded)
    The new single method: `pkill astrill` + `setsid /autostart` with the full
    quoted
  • low Dangerous commands cmd-background-process setup.sh:46
    Starts a background / autostarted process (detector / deny-list definition)
    for tool in ping ip pgrep pkill setsid; do
    detector
  • low Dangerous commands cmd-background-process setup.sh:49
    Starts a background / autostarted process (detector / deny-list definition; string literal in code, not executed)
    ok "Required tools present (ping, ip, pgrep, pkill, setsid)."
    detectorcode literal
  • low Dangerous commands cmd-background-process SKILL.md:9
    Starts a background / autostarted process (quoted — discussed, not commanded)
    - `setsid /autostart` relaunches Astrill with the full desktop environment (`DISPLAY`, `DBUS`, `WAYLAND_DISPLAY`) so it can initialize its GUI/Wayland stack from a systemd service context
    quoted
  • low Dangerous commands cmd-background-process SKILL.md:17
    Starts a background / autostarted process (detector / deny-list definition)
    - `ping`, `ip`, `pgrep`, `pkill`, `setsid` (Ubuntu defaults)
    detector

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error frontmatter SKILL.md: no YAML frontmatter block found
  • error name-missing SKILL.md: frontmatter has no `name`
  • error description-missing SKILL.md: no `description` — the skill can never trigger

Process rating: all ten parameters 63/100

  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. No external tools needed
  • 100Steps. 6 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 573 tokens
  • 100Progress reporting. Reports progress

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)
  • +3Description length 0: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 6 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.

External checks

ClawHub: clean
This skill is a disclosed user-level Astrill VPN watchdog that monitors connectivity and restarts Astrill when the tunnel appears down.
LLM: benign (high) · VirusTotal: benign · 28 May 2026