メニュー
Computer vision and media processing: CLI interface stability, coordinate alignment (row-major vs column-major), shape consistency after transformations, and output validation. Use for image processing, video analysis, object detection, segmentation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Smart commit with Conventional Commits: groups logical changes, infers type + scope from file paths, and generates messages in `<type>(<scope>): <description>` format.
Iterative quality gate hardening loop — run the gate, parse failures, fix each failing category with a fresh-context delegate, re-run until all gates pass or diminishing returns are hit.
Relentless quality loop: alternate between a fresh-context implementer and a fresh-context reviewer until only diminishing-return issues remain. The reviewer is advisory-only (no state changes). The implementer starts fresh each cycle, unanchored from prior attempts. Terminates when max severity ≤ 3 for two consecutive cycles or the severity trend is flat.
Compact the current conversation into a handoff document for a fresh agent to pick up next session. Includes current phase, workspace state, memory state, and suggested skills.
Investigate a question against primary sources (official docs, arXiv papers, Semantic Scholar, source code, specs, first-party APIs) using the web_search tool. Writes structured findings as a Markdown file. Use when the user wants a topic researched, docs gathered, API facts investigated, or reading legwork delegated. Maps to P1 Explore phase.
Meta-cognitive improvement loop: reflect on errors, learn patterns, codify guardrails. The skill that rewrites skills. Always loaded.
| name | vision-media |
| description | Computer vision and media processing: CLI interface stability, coordinate alignment (row-major vs column-major), shape consistency after transformations, and output validation. Use for image processing, video analysis, object detection, segmentation. |
Leading word: alignment — coordinates, dimensions, channels, and color spaces must be aligned between input and output. A misaligned pixel is a silent bug.
ffmpeg, ImageMagick, OpenCV CLI), verify the output format before further processing. Don't assume the tool produced what you asked for.pip install opencv-python pillow matplotlib numpy
Output validation procedures: references/output-validation.md
SKILL vision-media
INPUTS:
mediaType: string // image, video, mask, segmentation
inputFormat: string // png, jpg, mp4, nifti, dicom
processingOp: string // transform, detect, segment, classify
dimensions?: object // Expected width, height, channels
OUTPUTS:
processedMedia: binary // Processed image/video data
validationReport: object
// dimensions_match: bool
// color_channels: int
// file_integrity: bool
coordinateSystem: string // row-major or col-major, y-up or y-down
PRECONDITIONS:
- Input file integrity confirmed before processing
- Coordinate system explicitly declared
- Output format compatible with intended use
POSTCONDITIONS:
- Output dimensions match expected specification
- Color channels preserved or explicitly converted
- File integrity verified after processing
- Coordinate convention consistent between input and output
ERROR_HANDLING:
- Input file corrupt → abort with integrity report
- Dimension mismatch → reshape or error with details
- CLI tool produces unexpected output → re-verify format