SKILLEMALL.ai

AB accounting-skill

Process accounting documents — invoices (hóa đơn GTGT), purchase orders, and bank statements. Extract structured data from PDF (digital and scanned), JPG, and PNG files using OCR. Output Excel tracking sheets and JSON backups. Classify unknown documents and route to the correct extractor. Supports Vietnamese and international formats. Use when asked to extract, process, classify, or track invoices, POs, bank statements, or accounting documents.

ClawHub Agent Skills author: DVNghiem v0.1.0 MIT-0 13 files body ≈ 878 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 67/100 · Nearly there — weak spots: when it triggers, consistency, running it twice

ProcedureFinancetype and topics are labelled automatically from the skill text
JSON
Technical rating
A
98/100
safety, quality, tests
Safety 60%
100
Quality 40%
94
Run on models
none yet
Process rating
B
67/100
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

    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: 13. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 67/100

    • 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
    • 40Consistency. Frontmatter name (accounting-skill) differs from the folder (vn-accounting-skill)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 10 steps
    • 100Execution cost. Instruction body is 878 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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 448: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 10 items
    • +3Output format is stated explicitly
    • +4Has examples (8 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)
    • +3All 6 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.

    External checks

    ClawHub: suspicious
    The skill is mostly a coherent local accounting OCR tool, but its documented batch workflow can execute attacker-controlled shell commands through `eval`.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026