SKILLEMALL.ai
GitHub ↗ RU Sign in

CD mother-of-all-openclaw-backup-restore-skills

The definitive, self-improving, community-wisdom-infused backup/restore skill. British dry humour + canine wisdom. Tested in production. Evolving with every use.

ClawHub Hermes author: stefanferreira v2.2.1 MIT-0 2 files body ≈ 8 429 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ReferenceInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
C
73/100
safety, quality, tests
Safety 60%
80
Quality 40%
63
Run on models
none yet
Process rating
D
39/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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.

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:316
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -fsSL https://cli.openclaw.ai/install.sh | sh
    vendor-host
  • medium Dangerous commands cmd-privilege SKILL.md:343
    Privilege escalation / world-writable permissions
    sudo chmod +x /usr/local/bin/openclaw
  • medium Dangerous commands cmd-privilege SKILL.md:358
    Privilege escalation / world-writable permissions
    sudo chmod +x /usr/local/bin/openclaw
  • medium Dangerous commands cmd-privilege SKILL.md:374
    Privilege escalation / world-writable permissions
    sudo chmod +x /usr/local/bin/openclaw

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 161 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning body-long SKILL.md body ≈ 8429 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "title"
  • note frontmatter-key unknown frontmatter key "personality"
  • note frontmatter-key unknown frontmatter key "trigger"
  • note frontmatter-key unknown frontmatter key "prerequisites"
  • note frontmatter-key unknown frontmatter key "pitfalls"
  • note frontmatter-key unknown frontmatter key "created"
  • note frontmatter-key unknown frontmatter key "updated"
  • note frontmatter-key unknown frontmatter key "status"
  • note frontmatter-key unknown frontmatter key "published"
  • note frontmatter-key unknown frontmatter key "style"

Process rating: all ten parameters 39/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 15 mutating operations with no state check
  • 40Consistency. Frontmatter name (mother-of-all-openclaw-backup-restore-skills) differs from the folder (openclaw-complete-backup-delete-fresh-install-restore-cycle)
  • 40Execution cost. Instruction body is 8429 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 65Failures and branches. 3 branches
  • 85Steps. 49 steps, 1 vague phrases
  • low 18 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
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 161: enough signal without eating the budget
  • +4Structure: 44 headings
  • +3Step-by-step instructions: 49 items
  • +4Has examples (26 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.

External checks

ClawHub: suspicious
This is a coherent OpenClaw backup and restore runbook, but it gives users high-impact destructive and privileged commands without enough safeguards.
LLM: suspicious (high) · VirusTotal: · 29 May 2026