
深度调研 - 当需要检索真实世界细节、推演复杂逻辑、获取风格参考时触发。关键词:调研、检索、搜索、参考、素材。
Get current weather and forecasts (no API key required).
# Discord Message Guard Middleware skill that filters and guards Discord messages before they reach agents. ## Capabilities - Filter spam and unwanted messages - Rate limiting per user/channel - Content moderation hooks - Pattern-based message blocking ## Usage This skill is automatically loaded when configured. No manual invocation needed.
Automates browser interactions for social media management across Instagram, LinkedIn, and X. Handles posting, DMs, connection requests, lead scraping, and monitoring. Use when the user needs to navigate, interact with, or extract data from approved websites.
小说记忆系统 - 基于工作区文件的持久化记忆,管理角色设定、章节摘要、伏笔追踪等。关键词:记忆、存储、查询、设定、知识管理。
OpenViking 集成 — 浏览器自动化与 Web 搜索工具
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Search and browse Hacker News with API access to stories, comments, users, and hiring threads.
Notion API for creating and managing pages, databases, and blocks.
章节归档 - 每章写完后的持久化操作,包括摘要生成、记忆更新和状态报告。关键词:归档、摘要、持久化、章节完成。
以明朝内阁制为蓝本的多 Agent 协作系统
翰林院 OpenViking 记忆增强 — 将小说写作 pipeline 的设定、摘要、伏笔接入 OpenViking 语义记忆。若你从属于翰林院,当你看到这个skill时,务必加载这个skill。
小说写作技法 - 当需要逐章执笔创作小说正文时触发。关键词:写作、执笔、章节、正文、创作。
小说章节审核 - 当需要校对、审核小说章节质量时触发。关键词:审核、校对、审稿、检查、质量评估。
小说架构设计 - 当用户需要设计小说大纲、人物档案、世界观、伏笔台账时触发。关键词:大纲、世界观、人物设定、架构设计、故事规划。
Manage Quadrants tasks and projects via natural language. Use when the user wants to create, view, complete, or organize tasks on the Eisenhower Matrix. Supports listing projects, adding tasks (single or bulk), viewing priority tasks, completing tasks, and getting project overviews. Triggers on mentions of "quadrants", "tasks", "to-do", "eisenhower", "priority matrix", or task management requests.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.