SKILLEMALL.ai
GitHub ↗ RU Sign in

BC watchclaw

Auto-recovery watchdog for OpenClaw gateway. Monitors health, detects bad config changes, and recovers via git stash/revert. Supports native and Docker restart modes with pluggable alerts.

modbender/skill-library-mcp Agent Skills author: modbender MIT 3 files · 1 script body ≈ 534 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Auto-recovery watchdog for OpenClaw gateway.

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

IntegrationDockerSoftware developmentInfrastructuretype 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
B
87/100
safety, quality, tests
Safety 60%
97
Quality 40%
72
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Dangerous commands cmd-pipe-to-shell-known-host install.sh:2
    Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)
    # watchclaw installer — curl -fsSL https://raw.githubusercontent.com/jarvis4wang/watchclaw/main/install.sh | bash
    comment
  • low Exfiltration exfil-webhook-url README.md:198
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    ALERT_WEBHOOK_URL="https://hooks.slack.com/services/T.../B.../xxx"
    placeholder
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:15
    Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)
    "command": "curl -fsSL https://raw.githubusercontent.com/jarvis4wang/watchclaw/main/install.sh | bash",
    quoted

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 5 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 8 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 534 tokens

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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 188: enough signal without eating the budget
  • +4Structure: 7 headings
  • +3Step-by-step instructions: 8 items
  • +4Has examples (3 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.