// Export live CLI-first Nexus tool schemas as JSON. Use when the user wants every tool schema, a subset by selector, or an artifact that reflects the current runtime command/argument shape instead of source parsing.
| name | nexus-tool-schemas |
| description | Export live CLI-first Nexus tool schemas as JSON. Use when the user wants every tool schema, a subset by selector, or an artifact that reflects the current runtime command/argument shape instead of source parsing. |
Use this skill when the task is to generate or refresh JSON exports of the plugin's CLI-first tool schemas.
scripts/generate-tool-schemas.mjsToolCliNormalizer.buildCliSchema() runtime pathThis is the source of truth for the exported shape. Do not hand-assemble schema JSON unless the script is broken and you are fixing it.
Run:
npm run schemas:tools
This writes the default full export to:
docs/generated/cli-first-tool-schemas.json
Use --selector with the same selector grammar as getTools:
npm run schemas:tools -- --selector "storage"
npm run schemas:tools -- --selector "storage move, content read"
npm run schemas:tools -- --selector "prompt generate-image"
Use --output to control the destination:
npm run schemas:tools -- --selector "task" --output docs/generated/task-tool-schemas.json
npm run schemas:tools -- --selector "web-tools capture-to-markdown" --output -
--output - prints JSON to stdout instead of writing a file.
--selector and --output as needed.npm run sync:skills
getTools.Version bump and GitHub Actions release for the Nexus Obsidian plugin. Use when the user wants to cut a release, bump the version, or publish a new version after stable changes are ready.
Version bump and GitHub Actions release for the Nexus Obsidian plugin. Use when the user wants to cut a release, bump the version, or publish a new version after stable changes are ready.
Run or update the Nexus LLM eval harness for arbitrary provider/model matrices. Use when comparing models in the real vault-like tool environment, changing eval configs, adding eval scenarios, or debugging eval reports.
Add, update, or verify Nexus LLM provider model definitions. Use when adding newly released models, changing OpenAI/OpenRouter/Codex/GitHub Copilot/Anthropic/Google model metadata, updating provider defaults, or live-testing whether a model ID works through the reusable provider smoke test.
Create or update standalone UI mockups for Nexus before implementation. Use when the user asks for a new view, modal, workflow, layout refactor, or other substantial UX change that should be reviewed in `docs/mockups/` before production code.