القائمة
Orientation guide for navigating the WorldArchitect.ai repository and tooling
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/jleechanorg/claude-commands --skill worldarchitect-codebase-sherpaيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
Token-efficient second opinion slash command /advice. Extracts decision point + artifact (≤150 lines), then fans out in parallel: (1) Opus subagent reviewer with fallback chain codex→agy→cursor, (2) /research on the decision topic, (3) /secondo multi-model opinion. Use instead of advisor() which ships the full conversation uncached.
Use this skill when working in repositories managed by Agent Orchestrator or when the user asks how to use `ao` properly. Covers the default AO workflow: bootstrap with `ao start`, dispatch work with `ao spawn`, inspect progress with `ao status` or `ao session ls`, steer sessions with `ao send`, and recover or clean up sessions safely. Includes strict parameter fidelity, pre-spawn cap cleanup, quota-wall fallback, and post-spawn verification.
Generate a full agento PR status report — draft readiness, canonical /green, zero-touch rate, inline display, and Slack summary.
استنادا إلى تصنيف SOC المهني
عرض SKILL.md
| name | worldarchitect-codebase-sherpa |
| description | Orientation guide for navigating the WorldArchitect.ai repository and tooling |
| type | usage |
| scope | project |
Equip Claude with a quick-start orientation for the WorldArchitect.ai repository so it can answer navigation, onboarding, and architecture questions without deep prompting.
mvp_site/ houses the Flask backend, MCP servers, templates, static assets, and tests. Frontend variants live in mvp_site/frontend_v1/ and mvp_site/frontend_v2/.world/ and world_reference/. Campaign prompts live under prompt_archive/.scripts/ plus top-level run_*.sh helpers.docs/, roadmap/, analysis/, and GENESIS.md capture requirements, planning notes, and retros..claude/, claude_command_scripts/, and mcp_servers/ define MCP behaviors and bot orchestration.pip install -r requirements/base.txt.env.example to .env; ensure TEST_MODE=mock for local work../vpython mvp_site/main.py serve
# or
./run_local_server.sh
./scripts/install_mcp_servers.sh claude or ./start_game_mcp.sh depending on the workflow../kill_dev_server.sh cleans up hanging processes../run_tests.sh, ./run_tests.sh --integration, ./run_tests_with_coverage.sh./run_lint.sh, pre-commit run -a./run_ui_tests.sh./deploy.sh, ./deploy_mcp.shsource scripts/oracle_helpers.sh then use helpers like oracle_arch_preview (dry-run bundle), oracle_arch (architecture review), oracle_ai_debug (AI pipeline bug with optional report path), oracle_diff_review (reviews git diff), oracle_ui_debug (frontend triage). Playbook at docs/oracle_playbook.md.mvp_site/main.py broker requests to modular MCP servers under mcp_servers/.world/ and selectors defined in mvp_site/services/persona_service.py.firestore_service.py and mvp_site/services/firestore/ modules.mvp_site/tests/; cross-system flows sit in mvp_site/test_integration/ and top-level tests/.docs/vision/ and docs/company/.docs/product/game_loop.md and GENESIS.md.roadmap/ for upcoming milestones.