caidish

Detect individual material layers (graphite, graphene, bottom hBN, top hBN) from their optimal source images. Use when segmenting specific materials in a van der Waals heterostructure stack from microscope images.

Register source microscope images to the full_stack coordinate system using SIFT (same-substrate) or Chamfer+DE (cross-substrate) alignment. Use when aligning bottom_part, top_part, or other source images to the full_stack reference image for van der Waals stack detection.

Transform detection results into the common full_stack coordinate system, build unified traces.json, and draw overlay images. Use after align and detect steps are complete.

Align microscope stack images to a GDS fabrication template using lithographic marker detection. Computes image→GDS transform and commits warped image + material contours to KLayout.

Orchestrate end-to-end nanodevice design from user query through optional flake detection, material analysis, device geometry creation, routing, evaluation, and save. Device-agnostic methodology -- the agent derives physics rules from device type and available materials.

Route nanodevice contacts to bonding pads with multi-window EBL support. Use this skill when the user needs to place bonding pads, route leads from device contacts to pads, set up multi-window EBL routing with different line widths per window, or add boundary connection patches between EBL write fields. Also trigger for "fan out", "route to pads", "bonding pads", "EBL windows", "multi-pass lithography", "connection patches".

Detect and map van der Waals heterostructure flake boundaries from microscope images into KLayout polygons. Split workflow with 5 sub-skills (align, detect, combine, commit, review) for agent-orchestrated stack detection. Use this skill when the user wants to detect flakes from multiple source images, align cross-substrate images, segment hBN/graphene/graphite stacks, or run the full stack detection pipeline.

Capture the current KLayout layout as a PNG image for visual inspection. Use this skill whenever the user wants to see, view, screenshot, preview, or visually inspect the current layout. Also trigger when the user asks "what does it look like", "show me the layout", "take a screenshot", "capture the design", or needs a visual check of their GDS geometry.

Revise an academic paper sentence by sentence with the author, stripping AI writing tells (stop-slop) while preserving the author's own voice. Use this whenever the user wants to polish, tighten, edit, proofread, or "de-slop" a paper, manuscript, draft, abstract, or thesis chapter — especially when they want careful interactive sentence-level revision rather than a one-shot rewrite. Trigger on requests like "help me revise my paper", "clean up my draft", "make my writing sound less AI", "go through my abstract line by line", or when they hand over a .tex/.md/.txt paper to improve.

Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini operations.

Scan this machine for the Miasma / Phantom Gyp ("TeamPCP") npm supply-chain compromise that plants backdoors in Claude Code (~/.claude/settings.json) and VS Code (.vscode/tasks.json). Use when the user asks to check if their PC/machine is infected, compromised, or affected by the npm/Claude Code backdoor attack, credential-stealing worm, or Shai-Hulud campaign.

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, code review, or automated editing

Collaborative multi-agent fix workflow using codex, gemini-cli, and an independent subagent. Use when the user asks to "collab fix", "multi-agent fix", or wants several AI tools to jointly analyze and fix a bug or task with cross-review.

Test-Driven Development debug workflow combined with multi-agent collab-fix. Use when the user asks to "TDD debug", "reproduce and fix with a test", or wants a bug fixed with a failing test written first and verified after the fix.

Drucker-inspired leadership framework for managing agent teams. Invoke when coordinating multi-agent work, delegating tasks, or making strategic decisions as team lead.