Menu
SkillsMP has collected 7 skills from danielrosehill/Claude-Image-Annotation-Plugin. Open a skill to review its source and details.
Showing 7 of 7 collected skills.
Apply annotations to an image — arrows, text callouts, boxes, highlights, numbered markers — driven by a JSON spec. Originals are never modified; output goes to <input_dir>/annotated/<stem>_annotated<ext> by default.
Bundle a set of (typically annotated) images into a single PDF — for tutorials, bug reports, step-by-step guides, or printable documentation. Preserves order, leaves source images untouched, and uses img2pdf for lossless inclusion when available.
Batch-convert images to WebP for web-optimised output. Originals are left untouched; converted files land in <dir>/webp/<stem>.webp by default. Supports lossy quality control or lossless mode.
One-shot orchestrator — take a screenshot and immediately apply annotations. Combines the screenshot and annotate skills for the common "grab this region and draw an arrow at it" workflow.
Install the CLI tools this plugin depends on — ImageMagick, Pillow, img2pdf, cwebp, and at least one screenshot backend (spectacle, grim+slurp, or flameshot). Idempotent setup script that detects distro and desktop session and installs only what is missing.
Privacy redaction — pixelate (default), blur, or solid-fill rectangular regions of an image to hide sensitive content (faces, names, tokens, IPs, PII). Originals are never modified; output goes to <input_dir>/redacted/<stem>_redacted<ext>. EXIF is stripped on…
Capture a screenshot on Linux — fullscreen, region, active window, or delayed. Auto-selects the best backend for the session (spectacle on KDE, grim+slurp on wlroots Wayland, flameshot fallback). Saves to a user-specified path or a sensible default.