AC PDF OCR using Gemini LLM
Extract text from PDFs using Google Gemini OCR. Use when extracting text from PDFs, performing OCR on scanned documents, or processing image-based PDFs.
As a process C 50/100 · Has gaps — weak spots: result and completion, failures and branches, consistency
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
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 50/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (PDF OCR using Gemini LLM) differs from the folder (geminipdfocr)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 6 steps
- 100Execution cost. Instruction body is 380 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 152: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.
External checks
ClawHub: clean
This skill does the stated OCR task and clearly discloses that PDF pages are uploaded to Google Gemini, but users should treat it as cloud processing for potentially sensitive documents.
LLM: benign (high) · VirusTotal: · 29 May 2026