CC sshx
Operate remote servers with the `sshx` CLI — inspect hosts, dissect remote logs with `sshx text`, run commands over SSH, transfer files over SFTP, apply a single remote file, manage named hosts, store SSH/sudo passwords in the OS keyring or local vault, and run guarded SQL. Use when the user wants structured host discovery, log/exception triage, remote command execution, safe config file changes, upload/download, host management, or safe production database changes. Prefer `--json`. Do not wrap grep/journalctl in `sshx run` when `sshx text` fits.
Operate remote servers with the sshx CLI — inspect hosts, dissect remote logs with sshx text, run commands over SSH, transfer files over SFTP, apply a single…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
✓ Guard found no suspicious behaviour. 3 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8219 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 112, 141, 185, 514): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 62/100
- 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
- 40Execution cost. Instruction body is 8219 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 43 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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
- low 21 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (11 tags): a typed call is more reliable
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 552: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (21 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.