SKILLEMALL.ai

AC paddle-ocr-vl

GPU-accelerated document parsing and OCR via PaddleOCR-VL. Detects layout, recognizes Chinese/English text, tables, charts, and seals in images. Use when the user asks to OCR an image, extract text from a document, parse a screenshot, or recognize text in photos. Supports vertical classical Chinese text, modern newspaper layouts, and mixed-content documents.

ClawHub Agent Skills author: Jessy-Huang v1.0.0 MIT-0 3 files body ≈ 618 tokens Open the sourceclawhub.ai analyzed 21 h ago

GPU-accelerated document parsing and OCR via PaddleOCR-VL.

As a process C 60/100 · Has gaps — weak spots: result and completion, failures and branches, progress reporting

AnalyzerDockerInfrastructureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
100
Quality 40%
84
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
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: 3. 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 60/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 12 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 618 tokens
    • 100Running it twice. No mutating operations
    • 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)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 360: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 12 items
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: suspicious
    This OCR skill is purpose-aligned, but it gives a Docker container broad local and network access while the documentation understates that risk.
    LLM: suspicious (high) · VirusTotal: · 28 May 2026