whiteboard

How to run the periodic standing-codebase-health audit in the whiteboard repo — fan out auditors across health dimensions, adversarially verify, triage into Tasks/tmp-issues. Use when scheduling or running a periodic review (after a fold, weekly, pre-milestone) for unwired/incomplete features, architecture debt, maintainability, contract drift, test gaps, and dev-experience friction. Not for reviewing a single diff (that is the review workflow).

How to run the whiteboard repo's per-diff change-review gate — args, return contract, and the externalized-criteria mechanism for review.workflow.mjs. Use when running a standalone review gate (pre-merge, pre-un-draft, ad-hoc) or when authoring/tuning the review workflow that dev-loop composes.

Local-private task/ticket management for the whiteboard repo across workflows and agents, without GitHub Issues. Defines the tmp/ workspace buckets, the tmp/issues frontmatter convention, and the bridge between the native Task list (live board) and tmp/issues (durable backlog). Use when triaging findings, tracking in-flight work across dev-loop/review/dogfood-triage/reconcile/plan-initiative, or recording/resolving a follow-up.

Conventions and hard-won gotchas for authoring/maintaining the whiteboard repo's Dynamic Workflows (.claude/workflows/*.workflow.mjs) — dev-loop, review, dogfood-triage, reconcile. Use when editing or adding a Workflow script, debugging args not arriving, composing workflows, or running parallel dev-loops.

Monitor and triage the POST-PUSH automated-review surface for the whiteboard repo — GitHub Actions CI, CodeRabbit, AccessLint, the WIP app, CodeQL, and Dependabot — into Tasks/tmp-issues. Use after the integrator pushes, when CI/PR checks complete or a review bot comments, to decide what is real and file/fix it. Complements the local lefthook pre-push gate (which runs before push); this covers what only the cloud sees.

Triage, review, and merge Dependabot dependency-bump PRs + clear Dependabot security alerts for the whiteboard repo. Security-first, semver x ecosystem classification, verify-CI + `pnpm audit --prod` gate awareness, conflict-cascade-safe batch merging by the single integrator. Adapted for this repo's constraints — NO GitHub Issues (backlog -> Tasks/tmp-issues), release-please conventional commits, npm-published runtime-dep priority. Pairs with the dependabot-triage workflow (which does the read-only analysis fan-out).

When and how to update the whiteboard project's docs alongside a code change — the trigger→target map, Diátaxis quadrants, doc locations, the honesty rule, and doc-image regeneration. Use when a change has a user-visible effect, alters an API/contract/config, or when triaging a docs gap.

How to pick the nearest test layer in the whiteboard repo (mcp-node / mcp-jsdom / mcp-browser / web-browser / E2E) and the commands to run each. Use when writing the red test for a change, or deciding where a regression belongs.

A skill that standardizes whiteboard MCP and daemon verification. Use it after changing tools, routes, WebSocket behavior, daemon startup, checkpoints, export, or viewport logic when you need to decide what must be restarted and run the right smoke checks. Also use it when the user asks to verify behavior, run smoke tests, confirm things without restarting, or check whether MCP is broken.

Use this after changing Excalidraw MCP to choose and run the right repo-specific smoke test for startup verification, tool wiring, checkpoint restore, templates, and Claude/Codex subprocess paths. It helps decide which `scripts/mcp-*.mjs` or `pnpm smoke:*` command to use, while keeping sandbox and quota constraints in mind and choosing the smallest effective verification path.

How to keep Zod as the single source of truth for any contract that crosses a process boundary in the whiteboard repo (MCP tool input/output, Hono routes, persisted JSON, websocket/daemon payloads). Use when adding or editing an MCP tool, a route response, or a persisted-JSON parser, or when fixing a schema-vs-runtime drift. Covers the create_frame bug pattern and the mutation-check recipe.

Draw and annotate visuals with your AI agent on a shared Excalidraw canvas. Use it when screen layout, structure, flow, or comparison still feels too ambiguous in text alone.

Audit Excalidraw workspaces and canvases to detect orphaned workspaces, tombstone-heavy canvases, and cache/disk mismatches. Use when workspaces are piling up, sync looks suspicious, or you want to check for stale artifacts before creating new canvases.

Evolve Excalidraw visuals collaboratively through structured context gathering, frame-by-frame refinement, and fresh-viewer testing. Use when visuals feel misunderstood, under-explained, or need tightening together.