waldo1001

Fast pre-deploy sanity check that boots the real SWA + Functions stack locally against Azurite and exercises the critical-path routes end-to-end. Use before pushing to main (which auto-deploys) and whenever the API composition roots or static-web-app config change. Never touches real storage.

Start the full LexiQuest local development environment (Azurite + Vite + SWA CLI). ALWAYS kills any existing dev processes first, then starts clean — never tries to attach to a running stack. Use when the user wants to run the app locally, test a feature in the browser, or diagnose a runtime error that unit tests cannot catch.

Kill all LexiQuest local dev processes (Azurite + Vite + Functions host + SWA CLI) and free their ports. Idempotent — safe to run when nothing is running. Use when the user wants a clean slate, when orphaned background processes are holding ports, or as a teardown after a debug session.

Trigger and monitor a LexiQuest deploy to Azure Static Web Apps. Runs after `/local-smoke` passes. Push-to-main auto-deploys via GitHub Actions; this skill watches that run, tails logs, and probes the live URL until green. Never pushes force. Never rotates secrets.

Update the /docs folder at the end of a coding task. Use immediately after a `/tdd-cycle` completes (or any meaningful workspace change) to refresh the changelog, setup, getting-started, user guide, and PROGRESS as needed. Invoke proactively — documentation staleness is a bug.

Scan the LexiQuest workspace for secrets, credentials, and common security leaks. Runs as a mandatory step in every /tdd-cycle (after COVER, before UPDATE DOCS) and also on-demand when the user asks for a security check. Blocks the cycle if anything is found — never "note and continue".

Run the LexiQuest TDD cycle for a coding task. Use at the start of ANY code change (feature, bug fix, refactor) to write and get approval on a plan, then produce the RED test list, confirm failing tests, scaffold testable seams, implement to GREEN, refactor, and verify tier-appropriate coverage + requirement traceability. Invoke proactively — never write production code without running this first.

Spec authoring workflow for BC Telemetry Buddy (SDD Phase 0). Takes a GitHub issue number, drafts a behavior spec with acceptance criteria under docs/specs/, and gates the TDD cycle. Use when: picking up a feature/bug/tech-modernization issue, before any plan or code. Not for knowledge-base issues (use /kb-article-creation).

Knowledge Base article creation workflow for BC Telemetry Buddy. Automates: GitHub issue intake → validation prompt generation → article creation from validated report → index regeneration → issue closure. Use when: creating new KB articles from GitHub issues, validating telemetry event schemas, writing playbooks/query-patterns/event-interpretations.

Test-Driven Development workflow for BC Telemetry Buddy. Enforces the PLAN → FRAME → TESTS → PROVE RED → SCAFFOLD → IMPLEMENT → VERIFY → SECURITY SCAN → DOCUMENT cycle. Requires an approved spec (SDD Phase 0 — /spec-authoring) before the PLAN phase. Use when: adding features, fixing bugs, refactoring code, implementing new MCP tools, extension commands, or shared-lib modules. Mandatory before any code change.

Release one or both components (extension + MCP) with version bumps, CHANGELOG updates, git tags, and push

Security scan for BC Telemetry Buddy. Invoked from Phase 8 of the TDD workflow and before any release. Scans for real tenant GUIDs, bearer tokens, AAD secrets, customer identifiers in fixtures/snapshots/logs, untracked secret files, and high/critical npm audit findings. A finding BLOCKS the cycle — never "note and continue". Use when: finishing a TDD cycle, preparing a release, reviewing a PR, or any time before code leaves the machine.

Deploy waldo.WTF to the Mac mini (waldomacmini1) native LaunchDaemon — no Docker. Runs tests + local-smoke, refreshes deps, restarts the launchd service, re-asserts Tailscale Serve, and smoke-checks HTTPS health + the MCP tool surface. Use whenever shipping code changes to the running Mac mini server, OR when running a data migration from docs/migrations/. Flags; `--migrate <name>` to run a registered migration, `--dry-run` to print the plan without executing.

Fast pre-deploy sanity check against a throwaway SQLite DB and a non-default port. Exercises the CLI (add/list/toggle/remove + validation errors) and boots the MCP HTTP server long enough to confirm it listens and `tools/list` returns the full tool surface. Use before `/deploy-local` to catch boot-time regressions that `npm test` doesn't. Never touches real lake data.

Update the /docs folder at the end of a coding task. Use immediately after a `/tdd-cycle` completes (or any meaningful workspace change) to refresh the changelog, setup, getting-started, or user guide as needed. Invoke proactively — documentation staleness is a bug.

Run the waldo.WTF TDD cycle for a coding task. Use at the start of ANY code change (feature, bug fix, refactor) to produce the RED test list, confirm failing tests, scaffold testable seams, implement to GREEN, refactor, and verify ≥90% coverage + requirement traceability. Invoke proactively — never write production code without running this first.

Scan the workspace for secrets, credentials, PII, and common security leaks. Runs as a mandatory step in every /tdd-cycle (after COVER, before UPDATE DOCS) and also on-demand when the user asks for a security check. Blocks the cycle if anything is found — never "note and continue".

Convert AI agent chat sessions (Copilot Studio, GitHub Copilot Chat, ChatGPT, Claude, or any pasted/exported conversation) into self-contained, sanitized HTML files that replay the chat for live presentation. Use this skill whenever the user wants to "show a chat", "replay a conversation", "demo an agent session", "turn a chat into HTML", "make a chat for my talk", or needs to present an AI conversation to an audience without doing it live. Also use for sanitizing chat transcripts before sharing, or building reusable demo chats for conference talks, internal training, or sales demos. Strongly prefer this skill over manually constructing HTML or markdown when the goal is to present a chat session.

Build HTML presentation decks styled like the BC TechDays 2026 brand — a LIGHT cool-grey canvas, RED Montagu Slab slab-serif titles (#F7514F), Corbel body, full-bleed indigo/coral/magenta colour "moment" panels, the real BC TechDays scan-line "glitch wave" + wireframe-roster motif and torn-ticket "BC/NAV TECH DAYS 2026 · mibuso.com" logo (both inlined from the official PowerPoint), and the full pattern engine (claim-stack prov, centered tc-context, six-pillar tc-map, MCP hub, animated bridge, df-day timeline, htrack stage-tracker, agents-team grid, pb-hero playbook bridge, three-node storylines, pipeline analyzer, hub-and-spokes CSP, hands-up audience cards, replay overlay for embedded chat replays, inline presenter notes, View Transitions / element morph, a persistent dogsled trail progress tracker with build-trail overview morph, print-pdf export mode, click-to-zoom vocabulary cards, terminology grid, strap list, photo/instruction splits, image galleries, a retro C/AL window skin, in-flow replay row, extend

Build HTML presentation decks styled like the iFacto.be brand — green-on-black, Poppins, light-weight headlines with one accent word, photographic/animated dark hero, alternating dark/light slides, pill buttons, "Meer …" chevron links. Trigger whenever the user asks for an iFacto deck, iFacto slides, an iFacto-branded presentation, a deck for an iFacto session, or any HTML presentation that should match the iFacto.be visual language. Also trigger when the user is working in the "Agentic Development at iFacto" project folder and asks for slides, even if they don't say "iFacto" explicitly — that folder is iFacto-branded by default.

Pull skill updates from the user-level Claude skills folder (~/.claude/skills/) back into this repo's skills/ directory. Use whenever the user says "sync skills", "pull skills", "update skills from user folder", "bring my skill edits back", or after they've been editing a skill live in another project and want the changes reflected here. Only applies inside the waldo.AISkills repo.

Release a new version (patch, minor, or major). Use when: user asks to release, bump version, publish, cut a release, do a patch/minor/major release, tag a version.

Commit and push changes to the remote repository. Use when: user explicitly asks to commit, push, commit and push, ship it, send it, or push changes. NEVER commit or push without the user asking.

Run, start, or launch the Teams Chat Notifier Electron app in development mode. Use when: user asks to run the app, start the app, launch dev mode, or open the application locally.

Test-Driven Development workflow for this project. Use when: writing new code, implementing features, fixing bugs, adding functionality, creating new modules, refactoring. ALWAYS apply TDD: write tests first, verify they fail, implement code, verify tests pass. Use when: any code change, new feature, bug fix, refactoring.

Work the Where's waldo backlog (docs/implementation-handoff.md) with strict TDD plus a mandatory code + security review gate per task. "parallel N" runs up to N isolated coding agents concurrently while respecting task dependencies; a task ID (e.g. B2) runs only that task; no args = sequential loop. Use when the user invokes /dev-loop or asks to work through / implement the backlog tasks.