Total 43,917 skills
Showing 12 of 43917 skills
Python expert for stdlib, packaging, type hints, async/await, and performance optimization
Feishu Cloud Document Tool. Supports document creation, reading, and updating, including Lark-flavored Markdown syntax. **Use this Skill when**: (1) You need to create a Feishu Cloud Document (2) You need to read/retrieve document content (3) You need to update existing document content (4) The user mentions "document", "doc", "document", or "wiki"
Feishu message output rules. Valid at all times in Feishu conversations.
Expert knowledge for Modern Java (21+) development, including Virtual Threads, performance tuning, and idiomatic clean code. Use for deep Java language/logic questions.
Docker containerization best practices and patterns
Search and manage Alma's memory and conversation history. Use when the user asks about past conversations, personal facts, preferences, or anything that requires recalling information ("do you know my...", "we talked about before...", "do you remember...", "help me find what we said about..."). Also used to store new memories and search through archived chat threads.
Manage AI agent memory files (AGENTS.md/CLAUDE.md). Supports update and restructure modes. Use this when users need to sync, update, or restructure agent memory files. Triggered by keywords such as "记忆文件", "memory file", "AGENTS.md", "更新记忆", "重构记忆", "memory sync", "memory restructure".
Data analysis expert for statistics, visualization, pandas, and exploration
Machine Payment Protocol (MPP) for keyless, pay-per-query access to the Codex Supergraph GraphQL API. Use when the user has no API key and wants to pay per query via the 402 challenge flow at https://graph.codex.io/graphql.
Use this when you are exploring the codebase. It lets you ask the AI who wrote code questions about how things work and why they chose to build things the way they did. Think of it as asking the engineer who wrote the code for help understanding it.
Skill: react
Autonomous SDLC router. Takes a job, classifies complexity, executes the appropriate lev-* workflow (from trivial fix to full epic), and returns "done" with runnable instructions. One shot to full auto: spec/bd/poc/impl. Subagent returns completion artifact. Triggers: "sidequest", "side quest", "just do it", "autonomous", "one shot"