全部技能
38,472 Skills
搜索范围为本次公开目录;榜单和数量均为记录时的数据。
poster-style-transfer
Analyze an uploaded or local reference poster, extract its reusable design system, and transpose that system to an original poster with a new theme, title, subtitle, or campaign copy.
linuxdo-topic-capture
Capture Linux.do / L站 topic list titles, links, ids, categories/tags, reply/view/update snippets from the Codex in-app browser login session. Use when the user asks to 抓L站, linux.do帖子名, L站话题列表, 最近话题, or wants only titles to decide what to read. Default is list-only capture; do no
telegram-chat-capture
Capture, incrementally merge, summarize, and organize Telegram/飞机 chat records using the user's local Telethon setup. Use when the user asks to 抓飞机, 抓Telegram聊天记录, 抓归档聊天, 抓频道/群组/个人, 从上次抓取后拉取飞机消息, or add Telegram to the QQ/Discord/L站 chat-record workflow. Do not use for QQ, Discor
agent-architecture-design
Guides designing the control loop, state/memory model, and tool boundaries for an LLM-driven agent. Use when a user asks to "design an agent architecture," choose between a ReAct loop / plan-and-execute / finite-state agent, decide on single-agent vs multi-agent decomposition, de
agent-cost-and-latency-spike-investigation
Guides rapidly triaging a sudden cost or latency spike affecting one specific agent workflow — scoping it, correlating it against recent changes, and applying a fast, safe stopgap — before launching a full optimization pass. Use when a user asks "why did our LLM bill jump overnig
agent-evaluation-and-guardrails
Guides building evaluation harnesses, regression test suites, and runtime guardrails for LLM agents. Use when a user asks to "evaluate this agent," "write test cases for a prompt change," "set up an eval harness," "add guardrails to prevent unsafe output," "detect prompt injectio
agent-tool-call-loop-diagnosis-and-circuit-breaking
Guides diagnosing an active or recurring runaway agent tool-call loop and stopping it safely with a bounded retry policy and a hard ceiling — distinct from raising the iteration limit. Use when a user asks to "figure out why the agent is stuck calling the same tool," "safely kill
code-knowledge-graph-tools-for-ai-agents
Compares GitNexus, Graphify, and CodeGraph — tools that precompute a structural knowledge graph of a codebase and expose it to AI coding agents via MCP, replacing repeated grep/file-read exploration with direct impact-radius, call-chain, and dependency queries. Use when a user as
complete-ai-agent-stack-deployment-cloud-managed-from-scratch
Sequences a complete, end-to-end AI agent stack deployment built on managed cloud services from scratch — a cloud landing zone, agent control-flow architecture, an LLM gateway routing across managed provider APIs (vendor-neutral: Anthropic/OpenAI/Azure OpenAI/Bedrock/ Vertex AI),
complete-ai-agent-stack-deployment-self-hosted-from-scratch
Sequences a complete, end-to-end, fully self-hosted AI agent stack deployment from scratch — GPU procurement/sizing for open-weight model serving, self-hosted LLM serving (vLLM/TGI), agent control-flow architecture, a self-hosted vector database for RAG, self-hosted MCP servers f
langchain-and-langgraph-agent-orchestration
Guides building LLM applications with LangChain's chain/agent abstractions and, for stateful multi-step agents, LangGraph's graph-based orchestration (nodes, edges, cycles, checkpointed persistence, human-in-the-loop interrupts). Use when a user asks to "build this with LangChain
目录记录日期:2026-11-21