SKILLEMALL.ai
GitHub ↗ RU Sign in

AC grok

Delegate coding to xAI Grok Build CLI (features, PRs).

NousResearch/hermes-agent Hermes author: NousResearch MIT 1 file body ≈ 3 333 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Delegate coding to xAI Grok Build CLI (features, PRs).

As a process C 63/100 · Has gaps — weak spots: when it triggers, running it twice

IntegrationGitHubSoftware developmentAI and agentstype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
A
91/100
safety, quality, tests
Safety 60%
95
Quality 40%
85
Run on models
none yet
Process rating
C
63/100
Has gaps
When it triggers w 12
20
Running it twice w 4
30
Failures and branches w 10
50
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

    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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Dangerous commands cmd-pipe-to-shell SKILL.md:37
      Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
      - The official installer `curl -fsSL https://x.ai/cli/install.sh | bash` also
      quoted

    Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 254): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 63/100

    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 4 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 60Consistency. The Hermes dialect needs category and tags
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 40 steps
    • 100Execution cost. Instruction body is 3333 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 11 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (7 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)
    • +3Description length 54: 120–800 characters recommended
    • +2Single-language instructions
    • +4Structure: 21 headings
    • +3Step-by-step instructions: 40 items
    • +3Output format is stated explicitly
    • +4Has examples (11 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.