4273 个 · 按相关度排序
This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
中文简介正在准备中。当前显示原文说明。
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
中文简介正在准备中。当前显示原文说明。
Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.
中文简介正在准备中。当前显示原文说明。
When the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' 'who is my target audience,' 'describe my product,' 'ICP,' 'ideal customer profile,' or wants to avoid repeating foundational information across marketing tasks. Use this at the start of any new project before using other marketing skills — it creates `.agents/product-marketing-context.md` that all other skills reference for product, audience, and positioning context.
中文简介正在准备中。当前显示原文说明。
Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.
中文简介正在准备中。当前显示原文说明。
按项目保存Claude Code中的工作进度、决策和后续步骤，在其他会话中读取摘要，接着上次中断的位置继续工作，也可在会话开始时自动加载。
Create TypeScript scaffolding for a domain aggregate, a group of objects governed by shared business rules. Generate its main entity, value objects, repository interface, domain events, and unit test stubs inside an existing context.
中文简介正在准备中。当前显示英语简介。
Retrieve compacted ReasoningBank context for cost-analysis queries and summarize retrieved memories, reported token savings, cache hit rate, and package availability. The savings figure is an estimate from the integration, not a measured comparison against a baseline.
中文简介正在准备中。当前显示英语简介。
Search current library documentation and code examples with Context7 CLI, a command-line tool. Find API usage and configuration guidance, select available version-specific documentation, and prioritize examples in the programming language you use.
中文简介正在准备中。当前显示英语简介。
Create and maintain a shared product marketing document covering the product, audience, differentiation, and brand voice. Draft it from existing project materials or guided questions, then preserve revisions and tested lessons for other marketing skills.
中文简介正在准备中。当前显示英语简介。
Build and troubleshoot C#/.NET MCP servers that expose tools and information to AI agents. Guidance targets the official 2.x SDK and covers transport setup, authentication, interactive features, basic clients, and migration issues caused by changed defaults.
中文简介正在准备中。当前显示英语简介。
Investigate Spring configuration and Beans, the objects Spring manages, using Arthas. Check configuration sources, find registered objects by name or type, and inspect registration details while prioritizing read-only queries.
中文简介正在准备中。当前显示英语简介。
Route codebase exploration, file analysis, and web research through context-mode tools in Antigravity CLI. Process large outputs outside the conversation and return focused findings, with indexed content available for later searches.
中文简介正在准备中。当前显示英语简介。
Plan how an AI agent uses limited input space through reusable prompt prefixes, shorter tool outputs, summaries, and task splitting. Measure token use, response quality, and latency to choose optimizations that provide a net benefit.
中文简介正在准备中。当前显示英语简介。
Add business knowledge missing from a Wren project's database definitions. Compare source documents with existing context, then add explanations, rules, SQL examples, and proposed metrics through guided questions or an automatic mode with an audit report.
中文简介正在准备中。当前显示英语简介。
Diagnose why an AI workflow becomes inconsistent despite receiving extensive information. Through guided questions, define what to retain, retrieve when needed, or exclude, and develop a memory structure and a research-to-implementation process with focused context.
中文简介正在准备中。当前显示英语简介。
Gather business context before analysis by checking connected or provided sources for metric definitions, recent changes, and decision background. Produce a focused context note that preserves source references, conflicting evidence, assumptions, and remaining gaps.
中文简介正在准备中。当前显示英语简介。
Get reminders to compact conversation context, meaning summarize it for continued work, during long Claude Code sessions. A tool-call counter prompts consideration of manual compaction, with guidance on choosing useful breaks between task phases.
中文简介正在准备中。当前显示英语简介。
Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task. Use for "/wiki-context-pack", "use my vault as context", "context slice for X", "pack the wiki for my agent", or "bounded context for Y".
中文简介正在准备中。当前显示原文说明。
[omh] Context window or token budget at risk: plan compact context, token/cost budgets, summarization checkpoints, and overflow recovery before long agent work. Use when the user says: context-budget-review, context budget review, context budget, token budget review, token budget, prompt budget, prompt caching, prompt cache.
中文简介正在准备中。当前显示原文说明。
Builds resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critical replay model, step operations, wait/callback patterns, error handling with saga pattern, testing with LocalDurableTestRunner. Triggers on phrases like lambda durable functions, durable execution, workflow orchestration, state machines, retry/checkpoint patterns, long-running stateful Lambda functions, saga pattern, human-in-the-loop callbacks, reliable serverless applications, context.step, context.wait, context.invoke, context.runInChildContext, withDurableExecution, DurableContext, UnrecoverableInvocationError, durable-execution-sdk, qualified ARN invocation, and durable handler replay.
中文简介正在准备中。当前显示原文说明。
When the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' or wants to avoid repeating foundational information across marketing tasks. Creates `.agents/product-marketing-context.md` that other marketing skills reference.
中文简介正在准备中。当前显示原文说明。
Foundation skill that captures and stores core brand context — identity, audience, positioning, values, and voice. Use when the user says "set brand context", "save my brand info", "store brand details", "brand profile", "create brand context file", "update brand context", or when starting any brand project for the first time. Every other brand skill reads this file first. Always run this before beginning any brand work if the context file doesn't exist yet.
中文简介正在准备中。当前显示原文说明。
Dung khi bat dau lam viec voi mot san pham hoac khach hang moi — skill nay tao FILE CONTEXT ma hon 60 skill khac se doc, gom san pham, khach hang, dinh vi, proof, objection, brand voice va KPI. Chay mot lan, dung lai mai ve sau. Kich hoat khi user nhac 'tao context', 'setup product marketing context', 'bat dau du an moi', 'AI chua hieu san pham cua toi', 'khai bao thong tin san pham'. Khong dung cho — context cho thuong hieu CA NHAN thi dung skill 22-personal-brand-context; nghien cuu insight sau thi dung skill 09-insight-khach-hang.
中文简介正在准备中。当前显示原文说明。