SKILLEMALL.ai

CB Server

Runs web and application services on a host: process supervision, ports and sockets, worker sizing, restarting without dropping requests. Use when a service will not start, dies after logout, restart-loops, or vanishes on reboot; when a port is already in use, or it answers on localhost but refuses connections from outside; when a request returns 502, 504, 413, 499, or a redirect loop between proxy and app; when wiring nginx, Caddy, Traefik, HAProxy, systemd, PM2, or php-fpm; when sizing workers and threads, tuning keepalive and timeouts, or a box runs out of file descriptors or memory under load; when shipping a release and rolling it back; when serving large uploads, WebSockets, or gRPC through a proxy; and when self-hosting apps or media servers. Not for nginx directive tuning (`nginx`), certificate issuance (`ssl`), host OS failures (`linux`), image building (`docker`), Kubernetes (`k8s`), CI/CD pipelines (`deploy`), or provisioning the machine (`vps`).

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Iván v1.0.2 MIT-0 19 files body ≈ 7 026 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice

ProcedureDockerKubernetesInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
C
73/100
safety, quality, tests
Safety 60%
78
Quality 40%
66
Run on models
none yet
Process rating
B
66/100
Nearly there
Inputs and preconditions w 11
0
Running it twice w 4
30
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Concealment
If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 5

  • high Concealment en-hide-from-user deployment.md:117
    Instruction to hide actions from the user
    - Deploy by **digest**, not by tag: `image: app@sha256:…`. A moving tag means two boxes silently run different code, and "roll back to `latest`" is meaningless (`containers.md`).
Medium and low: 4
  • low Dangerous commands cmd-background-process containers.md:101
    Starts a background / autostarted process (quoted — discussed, not commanded)
    `unless-stopped` only survives a reboot if the container runtime's own service is enabled at boot. On a systemd host: `systemctl is-enabled docker`. This is the container equivalent of `systemctl enab
    quoted
  • low Risky intent intent-offensive-security maintenance.md:43
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    **Where** — the 3-2-1 shape, stated plainly: at least one copy **off the box**, and at least one copy the box's own credentials cannot delete. Ransomware and a bad `rm -rf` both walk every path the se
    quoted
  • low Dangerous commands cmd-background-process processes.md:33
    Starts a background / autostarted process (quoted — discussed, not commanded)
    Apply: `systemctl daemon-reload`, then `systemctl enable --now api`. **`enable` is what makes it start at boot; `start` alone does not** — the most common way a service "randomly disappears" months la
    quoted
  • low Dangerous commands cmd-background-process processes.md:128
    Starts a background / autostarted process (quoted — discussed, not commanded)
    `api@.service` with `%i` as the instance name runs N copies from one file: `systemctl enable --now api@8001 api@8002`, then load-balance across them in the proxy. This is how you use every core with a
    quoted

Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 7026 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "changelog"

Process rating: all ten parameters 66/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 39 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 7026 tokens
  • 100Steps. 40 steps
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 13 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Description length 971: 120–800 characters recommended
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 40 items
  • +3Output format is stated explicitly

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: clean
This skill is a disclosed server-operations guide that stores local infrastructure notes and asks for confirmation before service-affecting actions.
LLM: benign (high) · VirusTotal: · 27 Jul 2026