Menü
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | context-engineering |
| description | Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts. |
Context is the complete state available to a language model at inference time. It includes everything the model can attend to when generating responses: system instructions, tool definitions, retrieved documents, message history, and tool outputs. Understanding context fundamentals is prerequisite to effective context engineering.
Context comprises several distinct components, each with different characteristics and constraints. The attention mechanism creates a finite budget that constrains effective context usage. Progressive disclosure manages this constraint by loading information only as needed. The engineering discipline is curating the smallest high-signal token set that achieves desired outcomes.
Context as Finite Resource Context must be treated as a finite resource with diminishing marginal returns. Like humans with limited working memory, language models have an attention budget drawn on when parsing large volumes of context. Every new token introduced depletes this budget by some amount.
Progressive Disclosure Progressive disclosure manages context efficiently by loading information only as needed. At startup, agents load only skill names and descriptions--sufficient to know when a skill might be relevant. Full content loads only when a skill is activated for specific tasks.
Quality Over Quantity The assumption that larger context windows solve memory problems has been empirically debunked. Context engineering means finding the smallest possible set of high-signal tokens that maximize the likelihood of desired outcomes.
Informativity Over Exhaustiveness Include what matters for the decision at hand, exclude what does not, and design systems that can access additional information on demand.
L2 Content (loaded when fundamentals or patterns needed):
See: references/fundamentals.md
See: references/degradation-patterns.md
L3 Content (loaded when workflows or optimization needed):
See: references/optimization.md
Use this skill whenever the user wants high-quality semantic retrieval, cross-textbook synthesis, reference verification, or authority-ranked question answering over the PageIndex corpus. Trigger on requests like "find which texts cover X", "compare sources", "retrieve semantically", "verify this claim from my textbooks", "build a reading list from the corpus", "cluster by topic", or any PageIndex question where naïve filename search would miss relevant material. This skill teaches a state-of-the-art hybrid retrieval workflow over the PageIndex catalog and live MCP extraction surface.
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming. Use when you need to build complex AI systems, program LMs declaratively, optimize prompts automatically, create modular AI pipelines, or build RAG systems and agents.
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows in real-time through a web dashboard. Track multiple agents running in parallel with swim lane visualization, event filtering, and live charts. **Key Features:** - 🔴 Real-time event streaming via WebSocket - 📊 Agent swim lanes showing parallel execution - 🔍 Event filtering by agent, session, event type - 📈 Live charts for tool usage patterns - 💾 Filesystem-based (no database required) **Inspired by [@indydevdan](https://github.com/indydevdan)**'s work on multi-agent observability. **Our approach:** Filesystem + in-memory streaming vs. indydevdan's SQLite database approach.
Track and optimize agent specialization during methodology development. Use when agent specialization emerges (generic agents show >5x performance gap), multi-experiment comparison needed, or methodology transferability analysis required. Captures agent set evolution (Aₙ tracking), meta-agent evolution (Mₙ tracking), specialization decisions (when/why to create specialized agents), and reusability assessment (universal vs domain-specific vs task-specific). Enables systematic cross-experiment learning and optimized M₀ evolution. 2-3 hours overhead per experiment.
Routes tasks to appropriate Task tool agents (subagents). Triggers on complex multi-step tasks, research, code review, exploration, or any task benefiting from specialized agent execution. Matches intent to agent types.
