CC image-ocr
Read text, numbers, and math expressions from image files using local OCR (chi_sim/eng), fully offline. Use for text embedded in images/scans only - screenshots or pages whose text can be selected/copied directly should NOT go through this skill. Use whenever the user attaches an image or a scanned/multi-page PDF and asks what it says, wants content extracted, needs a worksheet or questions read from a photo, or wants image text converted to editable text. Accepts several images or PDFs in one call. Also use to preprocess low-quality images before OCR. Provides text extraction only, not scene understanding.
Read text, numbers, and math expressions from image files using local OCR (chisim/eng), fully offline.
As a process C 54/100 · Has gaps — References files that are not bundled: assets/tessdata/
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/tessdata/
Process rating: all ten parameters 54/100
- 0Tools and files. 1 referenced file(s) missing: assets/tessdata/
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 70When it triggers. States when to use, but not when not to
- 85Steps. 41 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1409 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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
- +4No input/output examples
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 614: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 41 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.