SKILLEMALL.ai

BF persistent-sshfs

Bash tool that brings up SSHFS mounts and retries the initial mount until it connects. Spawns one background worker per mount that waits for key-based SSH auth (retrying forever, no password fallback), then mounts with `sshfs -o reconnect`. IMPORTANT — it is NOT a live watchdog: each worker `break`s and exits once its mount is up, so once all mounts succeed the process exits 0 (it only blocks forever if a host's key auth never succeeds). Transient-drop survival comes from `sshfs -o reconnect` itself, not this script; nothing re-mounts a mount that fully dies unless you RUN THE SCRIPT AGAIN (its "mount whatever's currently down" logic makes re-running the real recovery mechanism — schedule it via cron/timer for that). Mounts are defined one-per-line in a plain-text file (`local_dir:user@host:port:remote_dir`), no other config. Use when the user wants SSHFS mounts brought up reliably at boot/login with retry-until-connected + sshfs reconnect for blips.

ClawHub Agent Skills author: Ciprian Mandache v1.0.6 MIT-0 3 files body ≈ 1 386 tokens Open the sourceclawhub.ai analyzed 2 d ago

Bash tool that brings up SSHFS mounts and retries the initial mount until it connects.

As a process F 44/100 · Will not run — References files that are not bundled: references/setup.md

ProcedureAI and agentsSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
100
Quality 40%
60
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: references/setup.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
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 · 0

✓ No critical or high findings

Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Bash tool that brings up SSHFS mounts and retries the initial moun… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning missing-ref reference to a missing file: references/setup.md
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: references/setup.md
  • 0Tools and files. 1 referenced file(s) missing: references/setup.md
  • 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
  • 50Failures and branches. 0 branches, has a failure section
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 15 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1386 tokens
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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 964: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +1No license
  • +2Single-language instructions
  • +4Structure: 6 headings
  • +3Step-by-step instructions: 15 items
  • +4Has examples (3 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

External checks

ClawHub: clean
This skill is a clearly disclosed SSHFS mounting helper, but users should verify the fetched script and only mount trusted hosts.
LLM: benign (high) · VirusTotal: · 1 Aug 2026