メニュー
Change or review the Python agentic_ai subsystem or Codex-facing MCP integration for this repository. Use when work touches agentic_ai/, the LangGraph pipeline, the mcp_server package, .mcp.json, or cloud adapters for the agentic pipeline.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use this skill when working anywhere in the SynthoraAI monorepo and you need the repository-specific operating model: which service owns what, which commands are canonical, which wrappers are stale, how to choose tests, and which paths are generated or risky to edit.
Audit this repository for docs-to-code drift, broken paths, stale wrappers, inconsistent environment assumptions, or other mismatches between implementation and operational guidance. Use when Codex needs to verify whether repo docs, scripts, schedules, Dockerfiles, or MCP guidance still match the code.
Use this skill when working on the Python agentic_ai subsystem or Claude Code MCP integration for this repository, including the LangGraph pipeline, local MCP server, cloud adapters, and the project .mcp.json configuration.
Use this skill when you want Claude Code to audit this repository for docs-to-code drift, broken paths, stale scripts, inconsistent environment assumptions, or mismatches between implementation and operational docs.
Change or review the backend API, auth, controllers, models, sitewide chat backend, Gemini integration, Pinecone integration, or backend maintenance scripts in this repository. Use when work touches backend/ routes, controllers, services, models, scheduled handlers, or vector sync logic.
Change or review the Next.js frontend in this repository. Use when work touches frontend/pages, frontend/components, frontend/services, auth UX, article detail flows, sitewide chat UI, browser-only state, or Pages Router behavior.
| name | agentic-pipeline-mcp |
| description | Change or review the Python agentic_ai subsystem or Codex-facing MCP integration for this repository. Use when work touches agentic_ai/, the LangGraph pipeline, the mcp_server package, .mcp.json, or cloud adapters for the agentic pipeline. |
Treat agentic_ai/ as a separate Python project.
mcp_server/app.py, mcp_server/tools/, mcp_server/resources/, mcp_server/prompts/, config/settings.py, and core/pipeline.py together.references/pipeline-map.md for runtime paths and known drift.