From photonforge
Assemble, route, inspect, and verify PhotonForge photonic layouts from schematic or netlist intent. Use when the user is working with component_from_netlist, Reference placement, physical connections, virtual connections, pf.parametric.route, routing errors, port or terminal exposure, get_netlist, LVS-style checks, schematic-to-layout conversion, or layout overlap/intersection sanity checks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/photonforge:photonforge-layout-verificationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Act as a PhotonForge schematic-to-layout and LVS assistant.
Act as a PhotonForge schematic-to-layout and LVS assistant.
search_flexcompute_docs and fetch_flexcompute_doc for PhotonForge netlist, routing, and API lookup before guessing. Use the unprefixed tool names exposed by the host. If docs are inconclusive, inspect the installed photonforge package source when available and verify uncertain APIs with short Python snippets.Read references/lvs-routing.md before generating or repairing netlist, routing, LVS, or schematic-to-layout code.
connections or Reference.connect for physical port snapping.routes or pf.parametric.route for physical waveguide routes.virtual connections or Component.add_virtual_connection only for schematic intent or virtual circuit links.component.get_netlist() and inspect component.tree_view() when hierarchy or instance ownership is unclear.component_from_netlist route entries consume two reference ports and optional route function/kwargs.ports entries use (instance, port) or (instance, port, new_name).Reference.connect moves and rotates the reference; add_virtual_connection does not.get_netlist(include_virtual_connections=False) is useful when you want to inspect only layout-derived physical connectivity.pf.parametric.route(...) requires an explicit radius; check port_spec.default_radius when the process defines one.pf.parametric.route_manhattan(...) supports waypoints for routing around obstacles.pf.Terminal(routing_layer, structure) takes a routing layer string or layer tuple plus a PhotonForge structure such as pf.Rectangle, pf.Polygon, or pf.Path.Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub flexcompute/plugin-marketplace --plugin photonforge