BB vlm-ocr
OCR scanned or image-only corpora with vision-language models, in three phases. Use `evaluate` to compare candidate OCR systems against stratified human ground truth and pick one on measured CER/WER, `run` to build the production pipeline (model selection, image handling, prompts, architecture, batching, accuracy evaluation, reproducibility), and `clean` to correct raw OCR text with LLM and rule-based passes, quality diagnostics, multilingual handling, and span-level provenance. Not for born-digital documents with a text layer — those go to $doc-to-markdown.
OCR scanned or image-only corpora with vision-language models, in three phases.
As a process B 67/100 · Nearly there — weak spots: inputs and preconditions, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 12084 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 12084 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 166 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 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
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
- high The skill tells the model to perform an irreversible action with no human approval
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 564: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 166 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.