SKILLEMALL.ai

AB litellm-vertex-codex

Configure OpenAI Codex CLI to use Vertex AI Gemini models via LiteLLM. A guide for translating strict Codex requests for Gemini compatibility.

ClawHub Hermes author: bhrum v1.0.0 MIT-0 3 files body ≈ 883 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process B 66/100 · Nearly there — weak spots: when it triggers, running it twice, progress reporting

IntegrationSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
80
Run on models
none yet
Process rating
B
66/100
Nearly there
Progress reporting w 2
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 142 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)

Process rating: all ten parameters 66/100

  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 3 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, 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. 7 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Execution cost. Instruction body is 883 tokens

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)
  • -2localhost URLs: will not work for another user
  • +2Single-language instructions
  • +3Description length 142: enough signal without eating the budget
  • +4Structure: 7 headings
  • +3Step-by-step instructions: 7 items
  • +3Output format is stated explicitly
  • +4Has examples (4 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

External checks

ClawHub: clean
This is a documentation-only setup guide for routing Codex through a local LiteLLM proxy to Vertex AI, with persistent configuration steps that are disclosed and purpose-aligned.
LLM: benign (high) · VirusTotal: · 29 May 2026