study-img — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited study-img (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Output language: ALL learner-facing content MUST be Simplified Chinese.
Use the available image-reading capability directly when possible.
One failed native attempt per session is enough evidence; do not retry every image.
python3 ~/.claude/skills/study-img/scripts/recognize.py <image> --mode <mode>First-use configuration: ask for provider type, base URL/API key, and vision model. Store config in ~/.config/study-img/config.json, chmod 600, and never repeat the full API key in conversation.
| Scenario | Mode | Required output |
|---|---|---|
| Scanned textbook page / photographed paper / handout | --mode ocr | Structured Markdown transcription; formulas as LaTeX; figures as [图：...] placeholders with enough detail to locate them. |
| Textbook/courseware figure, coordinate plot, table image, flowchart, chart | --mode figure | Teaching-grade description complete enough to redraw or convert into a lecture figure/table. Include axes, labels, variables, trends, data rows, and the conclusion. |
| Learner handwritten answers | --mode answer | Verbatim transcription; preserve errors; LaTeX formulas; use 【?】 for illegible characters. |
| Unsure | no mode | Comprehensive recognition. |
extract_pdf.py --render-scanned, recognize, and merge into internal/textbook/chapter-XX.md.extract_pptx.py --render-images, recognize, and merge into internal/textbook/chapter-XX.md.[图：...], chart, curve, or table is important for understanding, recognize it with --mode figure; then study-teach must include the useful visual/table/formula in the lecture JSON with source_ref.--mode answer, show uncertain parts to the learner, then hand to study-quiz for grading.Vision output can misread formulas and numbers. Cross-check against surrounding text, dimensions, and internal consistency before teaching or grading from it. If a figure/table remains doubtful, say so and ask the learner to confirm from the original.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.