Menu
MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具，让 AI 助手连接外部能力。仅在用户显式要求 MCP server / MCP 工具开发时调用，不要抢占 MoviePilot 主业务路线。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use this skill when the Agent needs to decide where a capability, rule, workflow, runtime anchor, script, job, document, persona change, plugin asset, or repository maintenance item should live. It provides a layered map of the Agent's durable assets so requests to “落实到 all”, “整理自身框架”, or “细化自身” do not bloat memory or scatter files.
Use this skill when the user asks to 自检自身、重新蒸馏、进化版 Agent、增强回去、避免死循环处理、能力增益评估，或在瘦身与增强之间取舍。它先盘点已处理对象、能力风险和真正增益点，再决定增强、修复、拆分、瘦身或停止，不把行数减少当成默认目标。
Use this skill when the Agent needs an executive-control layer before acting: classify user intent, decide direct execution vs read-only inspection vs button confirmation vs clarification, avoid over-asking, and keep work moving to the smallest safe completed state. Trigger especially when the user says 继续、落地、放开手脚、接管、自己判断、按方案推进，or complains about typing confirmations that should be buttons.
Use this skill when the Agent needs to read feedback signals before deciding whether to act, correct itself, distill a lesson, or ask for clarification. It treats user wording, repeated failures, tool errors, missing evidence, and activity context as sensory inputs, then routes to the right organ without overreacting.
Use this skill when the Agent needs to turn experience into a repeatable growth loop: observe signals, decide whether learning is needed, distill reusable lessons, place them into the right asset layer, verify the change, and keep future behavior lighter rather than heavier. Trigger when the user asks to 主动成长、持续进化、经验闭环、复盘后改进, or when repeated failures show a missing habit rather than a one-off bug.
Use this skill when the Agent needs to distinguish safe self-improvement from high-risk mutation. It guards credentials, destructive actions, MoviePilot core files, downloads, restarts, external service changes, and over-broad memory edits while still allowing authorized low-risk /config/agent and /config local plugin work to proceed.
| version | 3 |
| name | mcp-builder |
| description | MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具，让 AI 助手连接外部能力。仅在用户显式要求 MCP server / MCP 工具开发时调用，不要抢占 MoviePilot 主业务路线。 |
这是显式触发型参考技能。仅当用户明确要求 MCP Server、MCP 工具开发、Tools / Resources / Prompts 设计、MCP Inspector 调试或 MCP 发布部署时使用。
不要让本技能抢占 MoviePilot 媒体、站点、下载、订阅、转移、插件管理、Agent Git 或系统排障路线。MoviePilot 内部能力优先使用现有 MCP 工具、slash command、插件 API 和 MoviePilot 专用技能。
生产级 MCP Server 的目标是：工具可被 AI 正确选择、参数清晰、错误可恢复、权限最小、测试可证明、部署可复现。
MCP 原语选择：
users://{id}/profile。判断口诀：执行操作用 Tool，读取数据用 Resource，引导流程用 Prompt。
工具要让 AI 一眼选对：
snake_case，动词开头，如 search_issues、create_ticket、delete_file。示例描述：
search_users: 根据姓名或邮箱搜索用户。返回 ID、姓名、邮箱。模糊匹配，最多 50 条，无副作用。
isError: true，并说明用户或 AI 下一步能做什么。../ 路径穿越。execFile / 参数数组，避免 shell 注入。测试分三层：
每个 Tool 至少覆盖：正常路径、参数错误、权限错误、资源不存在、外部服务失败、超时或边界值。
吸收 MCP 集成候选时保持显式触发：
项目结构、stdio 调试、部署说明和完整 build checklist 见同目录 REFERENCES.md。
When a MoviePilot plugin, Agent tool, or MCP candidate overlaps, choose the native owner first:
Do not build an MCP wrapper around a MoviePilot action that already has a stable MCP tool, slash command, plugin command, or direct Agent tool path.
回答时只给与用户请求相关的 MCP 设计、实现、测试或部署建议，不要展开整套手册。若修改了 Agent 能力资产，完成后执行结构验证，并提醒是否需要同步仓库。