worldarchitect

Plugin worldarchitect from marketplace jleechan-skills in jleechanorg/jleechan-skills. Commands read from the repo's manifest — yesterday.

Skills (21)

• bq-evidence-reading

  Use this when reviewing WorldArchitect PR evidence that claims real LLM request/response logging, token counts, RAG/shadow comparison, or BigQuery provenance.

• character-creation-modal-exit

  Enforce the WorldArchitect.AI character-creation modal exit protocol and routing lock.

• dice-roll-audit

  Audit campaign dice rolls for fairness, anomalies, mechanics validation, and evidence.

• field-ownership-contracts

  Prevent the undefined field semantic failure mode where multiple writers assume different meanings for the same dict field.

• firebase-prod-campaigns

  Query and reason about production Firestore campaign and user data for WorldArchitect.AI.

• generatetest

  Evidence-based E2E test generator for your-project.com (Real Mode Only). Use for the /generatetest slash command — generates self-contained MCPTestBase test files under testing_mcp/ with built-in evidence bundle generation (git provenance, checksums, request/response JSONL). No mocks, no TESTING=tru

• level-up-validation

  Validate that level-up flows are complete, auto-selected, editable, and evidenced with real LevelUpAgent output.

• levelup

  Trigger and monitor the level-up organic test (testing_mcp/core/test_level_up_organic.py) against the PR's deployed preview server.

• local-dev-server

  How to start a local development server for Your Project

• mobile-investigations

  Use for mobile browser investigations in this repo, especially Firebase/Google auth, iOS Safari or Chrome iOS, Incognito/Private Browsing, storage partitioning, redirect flows, and user-visible mobile-only failures.

• pr-preview-servers

  Find and validate rotating GCP Cloud Run preview servers for PR branches.

• repro-copy

  Copy a real campaign to <test-user-email>, replay a reported issue against a real local server + real LLM, and capture evidence that can survive review

• repro-twin-clone-evidence

  Canonical /repro workflow for copy+targeted bug repro, twin clones, evidence exports, same-symptom verdicts, and red/green provenance.

• smoke-local

  Run /smoke-local — boot the real local MCP backend through the test harness, route all LLM calls through the agy CLI provider (never mock, never direct Gemini), play a new campaign to character level 4, and probe combat/spell/inventory/NPC-dialog narrative liveness. Use when the user says /smoke-loc

• smoke-test-local

  Reproduce WorldArchitect.AI CI smoke-test failures in a clean local environment.

• testing-infrastructure

  Use shared testing utilities, debug protocols, and CI/local parity for WorldArchitect.AI.

• user-story-worldai

  Resolve WorldArchitect-specific user-story guidance from the target repository and pair it with the portable general user-story skill.

• worldai-agent-routing

  Apply WorldArchitect.AI agent-routing priority, modal-lock, and stale-state guard patterns.

• worldai-auth

  Authenticate with the WorldAI Firebase project for Your Project

• worldarchitect-codebase-sherpa

  Orientation guide for navigating the WorldArchitect.ai repository and tooling

• zfc-leveling-roadmap

  ZFC Level-Up architecture alignment — file boundaries, API contracts, pre-flight checks, and milestone status. Read this BEFORE any level-up/rewards/XP code change.

Slash commands (6)

• /worldarchitect:bq

  BigQuery evidence verifier for real LLM request/response and RAG shadow claims

• /worldarchitect:generatetest

  /generatetest - Evidence-Based Test Generator (Real Mode Only)

• /worldarchitect:levelup

  Trigger level-up organic tests against the current PR's preview server

• /worldarchitect:repro_copy

  /repro_copy - copy a real campaign to the test user and replay the issue against a real local server + real LLM

• /worldarchitect:smoke-local

  /smoke-local - REAL local server + agy LLM smoke: new campaign → level 4 + combat/spell/inventory/dialog

• /worldarchitect:zfclevel

  ZFC leveling alignment check — verify PR/work conforms to ZFC leveling principles, roadmap, and doc sync