Skip to content

Latest commit

 

History

History
35 lines (28 loc) · 3.12 KB

File metadata and controls

35 lines (28 loc) · 3.12 KB

Skills

mq-image-analyze provides visual reasoning skills for AI agents and automated workflows.

The table below is generated from SKILL.md frontmatter by ./scripts/check-skills.sh --fix. Do not edit it by hand. Per-skill phase and status metadata lives in each SKILL.md's frontmatter.

Skill Description
cli-maintainer Use when changing mq-image CLI commands, flags, output, doctor checks, serve commands, or command documentation.
docs-maintainer Use when keeping mq-image-analyze README, docs, examples, CLI docs, MCP docs, schema docs, release docs, or integration docs consistent with code.
image-quality-audit Use when scoring an image for composition quality, clarity, and visual hierarchy.
json-contract-maintainer Use when changing mq-image-analyze JSON output schemas, analysis result fields, compare output, UI analysis output, exhaustive mode, or stable integration contracts.
mcp-tools-maintainer Use when changing mq-image-analyze MCP server, MCP tool schemas, tool safety, read-only behavior, or mq-mcp/mq-agent integration.
model-setup-maintainer Use when changing mq-image-analyze model setup, YOLO weights, Ollama/OpenAI vision backends, doctor readiness checks, or model documentation.
release-readiness Use when preparing mq-image-analyze for release by checking version sync, docs, tests, CLI, MCP tools, model safety, examples, and Git state.
repo-aware Use when inspecting, explaining, planning, reviewing, or changing mq-image-analyze with repository-specific context.
reverse-prompt Use when turning an image into a reusable prompt for image generation, visual design, or cinematic direction.
screenshot-ui-review Use when reviewing screenshots of apps, terminals, dashboards, websites, or GitHub pages for layout and usability.
visual-architecture-analysis Use when adding or changing mq-image-analyze features for architecture diagrams, infrastructure topology screenshots, terminal screenshots, OCR pipelines, or visual observations consumed by mq-mcp.
visual-reasoning Use when analyzing an image for objects, palette, composition, mood, visual hierarchy, and prompt intent.
web-ui-maintainer Use when changing mq-image-analyze web UI, FastAPI web server, packaged web assets, serve command, local ports, upload flow, or browser review workflow.

Integration

These skills are designed to be consumed by:

  • mq-agent (skill dispatch)
  • mq-mcp (MCP tool wrapping)
  • Claude Code / Codex (direct invocation)

Each skill has a SKILL.md that defines inputs, outputs and constraints.