跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。

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。

设计与 UI

fluss

gordonmurray

Design, deploy, and operate Apache Fluss streaming storage for sub-second real-time analytics. Use for Fluss log or primary-key table design, bucket sizing, tiering to Paimon, Iceberg, or Lance, Flink integration and Delta Join, $changelog and $binlog virtual tables, Spark access

价格待确认
设计与 UI

iceberg

gordonmurray

Design, migrate, tune, and maintain Apache Iceberg tables across query engines. Use for Iceberg schema and partition evolution, v2 to v3 upgrades, catalog selection, time travel and rollback, row-level deletes, snapshot expiry, orphan file cleanup, small-file compaction, or slow

价格待确认
设计与 UI

iggy

gordonmurray

Deploy, configure, and build clients against Apache Iggy (Incubating), a Rust-native message streaming platform. Use for Iggy server deployment via Docker, Compose, or Kubernetes, stream, topic, and partition design, retention and consumer group setup, transport choice across QUI

价格待确认
设计与 UI

lance

gordonmurray

Design, index, query, and tune Lance datasets and LanceDB tables for ML and AI workloads. Use for vector index selection such as IVF_PQ or IVF_HNSW_FLAT, ANN recall and latency tuning, full-text and hybrid search, scalar indexes and prefiltering, dataset versioning and compaction

价格待确认
设计与 UI

paimon

gordonmurray

Design, ingest into, tune, and operate Apache Paimon tables for streaming lakehouses. Use for Paimon primary-key or append-only table design, bucket sizing, changelog producer choice, Flink CDC ingestion, compaction backlog, lookup join performance, PyPaimon, Spark reads, Iceberg

价格待确认
图像与绘图

poster-style-transfer

jiemianduan

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.

价格待确认
搜索与研究

linuxdo-topic-capture

sammielisha425-design

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

价格待确认
浏览器与自动化

telegram-chat-capture

sammielisha425-design

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

价格待确认
设计与 UI

agent-architecture-design

selvarajmurugesan90

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

价格待确认
AI 与知识库

agent-cost-and-latency-spike-investigation

selvarajmurugesan90

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

价格待确认
安全

agent-evaluation-and-guardrails

selvarajmurugesan90

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

价格待确认
设计与 UI

agent-tool-call-loop-diagnosis-and-circuit-breaking

selvarajmurugesan90

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

价格待确认
开发与测试

code-knowledge-graph-tools-for-ai-agents

selvarajmurugesan90

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

价格待确认
AI 与知识库

langchain-and-langgraph-agent-orchestration

selvarajmurugesan90

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

价格待确认

目录记录日期:2026-11-21