my-image-parser

Export deterministic component-level OCR evidence for one transparent or semi-transparent image by splitting alpha-connected components, writing a component table, and running OCR on each component. Use when bounded component evidence must be exported before any downstream refinement or caption rerun.

Extract bounded OCR evidence from local image files with macos-ocr-mcp, using macOCR only as a fallback reference when MCP coverage is insufficient. Use when downstream refinement or review needs visible-text evidence, not final semantic decisions.

Wrap object-isolation correction as a repo-specific workflow. Use when a local image already exists, the current isolation result is imperfect, and the next step is to choose between ImageSorcery-first, imagegen-first, or a hybrid correction path with a bounded correction packet and worker run.

Promote a bounded parser raw sidecar artifact into the canonical Table -> Row -> Cell schema. Use when a parser MCP returned markdown plus nested JSON sidecars and the project must normalize that output before any downstream wrapper, worksheet, or RAG consumer reads it.

Triage a bounded batch of PPT-extracted images to find the small subset that is mechanically sufficient for alpha-only component splitting. Use when conservative preprocessing is required and only review-gated deterministic candidates should advance beyond the full-image baseline.

Operate an existing markdown review surface in VS Code with fabriqa for same-page image editing and Foam for backlinks and graph navigation, without redefining machine-truth semantics.

Dispatch one-image-per-worker jobs for the presentation image pipeline. Use when you need to register image jobs, fan out isolated Codex subagents, and keep MCP state as the source of truth.

Audit completed image jobs and export frozen comparison bundles from evidence-backed records. Use when you need approval candidates, retry candidates, comparison summaries, or auto-eval outputs without mutating upstream artifacts.

Process exactly one image in isolation. Use when a single image needs caption generation, status updates, and candidate rename preparation through MCP-backed state.

Render an Obsidian-friendly markdown review surface from caption ledgers and local image assets. Use when generated caption records must be exported into a human-readable review view with embedded images, without defining machine-truth semantics or refinement state.

Close a dormant or candidate table-parser branch through one evidence-first bounded activation slice. Use when the project must prove a parser path with ordered artifacts such as triage, boot smoke, real-image parse, canonical normalization, and downstream wrapper consumption before any wider rollout.

Apply only approved rename and metadata changes for image jobs. Use when audited and human-approved records are ready to be committed through filesystem and ExifTool MCPs.

Run the local OpenAI caption runner on extracted images or a prepared dataset JSONL to produce bounded caption evidence for downstream refinement or review, usually as a smoke test first and then as a resumable batch, not final machine-truth closure.

Capture per-slide screenshots for PPTX cross-validation. Use when a presentation needs slide-level screenshots captured through a simulator-visible viewer surface, then reused as image inputs for caption validation.

Canonical owner-family entrypoint for workspace vendored third-party MCP lifecycle integrity. Use when a third-party MCP must be vendored under vendor/mcp, launched through a thin wrapper, registered in Codex and VS Code config, recorded in inventory, and verified through bounded smoke evidence before being treated as active. Also use when ongoing launcher/config/inventory/setup-doc alignment for a vendored MCP needs to be verified or restored.