SKILLEMALL.ai

AB au-bas-gst-advisor

Triage Australian BAS preparation issues and GST classification questions — explain every BAS field (G1–G11, 1A, 1B, W1–W5, T1–T8), categorise supplies as taxable, GST-free, or input-taxed, flag common anomalies and ATO audit triggers, and guide Australian businesses through lodgement cycles, penalties, and correction steps.

ClawHub Agent Skills author: Arbaz Asif v1.0.0 MIT-0 3 files body ≈ 9 539 tokens Open the sourceclawhub.ai analyzed 2 d ago

Triage Australian BAS preparation issues and GST classification questions — explain every BAS field (G1–G11, 1A, 1B, W1–W5, T1–T8), categorise supplies as…

As a process B 67/100 · Nearly there — weak spots: inputs and preconditions, execution cost

ProcedureFinancetype and topics are labelled automatically from the skill text
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
76
Run on models
none yet
Process rating
B
67/100
Nearly there
Inputs and preconditions w 11
0
Execution cost w 6
40
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

  1. 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 · 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 body-long SKILL.md body ≈ 9539 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 67/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 9539 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 60Steps. 194 steps, 5 vague phrases
  • 60Result and completion. Output format stated, no completion criterion
  • 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
  • 100Progress reporting. Reports progress
  • 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 326: enough signal without eating the budget
  • +4Structure: 35 headings
  • +3Step-by-step instructions: 194 items
  • +3Output format is stated explicitly
  • +4Has examples (0 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: clean
This is an instruction-only Australian BAS/GST guidance skill with no executable code, credentials, APIs, persistence, or hidden runtime behavior.
LLM: benign (high) · VirusTotal: · 30 May 2026