Minimal-claude-code context-engineering

Guidance for designing, auditing, and improving context supplied to LLM agents, prompts, tools, RAG/MCP servers, and multi-agent systems. Use when the task involves context selection, prompt or agent architecture, tool descriptions, retrieval context, memory, compaction, autonomy, or evaluation of LLM behavior.

install

source · Clone the upstream repo

git clone https://github.com/Byunk/minimal-claude-code

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/Byunk/minimal-claude-code "$T" && mkdir -p ~/.claude/skills && cp -r "$T/context-engineering/skills/context-engineering" ~/.claude/skills/byunk-minimal-claude-code-context-engineering-533d99 && rm -rf "$T"

manifest: context-engineering/skills/context-engineering/SKILL.md

source content

Context Engineering

A practical guide for choosing, structuring, and evaluating the context supplied to LLM systems. It covers prompts, tool descriptions, retrieval, memory, compaction, autonomy, and agent architecture.

References


01-quality-over-quantity.md
02-start-minimal.md
03-hierarchical-organization.md
04-multi-dimensional-context.md
05-simple-composable-patterns.md
06-invest-in-tool-design.md
07-match-architecture-to-complexity.md
08-transparency-in-planning.md
09-contextualize-retrieved-chunks.md
10-dynamic-context-adaptation.md
11-meta-context.md
12-ground-in-environment.md
13-test-and-measure.md
14-retrieve-generously.md
15-anti-patterns.md
16-guide-model-thinking.md
17-multi-window-state.md
18-calibrate-autonomy.md

#	Principle	File	Summary
1	Quality Over Quantity	`01-quality-over-quantity.md`	Include only relevant context. Precision beats exhaustiveness.
2	Start Minimal, Layer Progressively	`02-start-minimal.md`	Begin with essentials, expand based on performance gaps.
3	Hierarchical Context Organization	`03-hierarchical-organization.md`	Structure context from general to specific. Use XML tags for disambiguation.
4	Multi-Dimensional Context	`04-multi-dimensional-context.md`	Effective context spans task, domain, history, constraints, motivation, and format.
5	Simple Composable Patterns	`05-simple-composable-patterns.md`	Prefer prompt chaining, routing, parallelization over complex frameworks.
6	Invest in Tool Design (ACI)	`06-invest-in-tool-design.md`	Tool descriptions deserve as much effort as UIs. Calibrate action language for Claude 4.6.
7	Match Architecture to Complexity	`07-match-architecture-to-complexity.md`	Choose the right pattern: chaining, routing, parallelization, orchestrator, or agent.
8	Transparency in Agent Planning	`08-transparency-in-planning.md`	Show planning steps. Use structured state tracking for long-horizon tasks.
9	Contextualize Retrieved Chunks	`09-contextualize-retrieved-chunks.md`	Prepend explanatory context before embedding. Reduces retrieval failures by 35-67%.
10	Dynamic Context Adaptation	`10-dynamic-context-adaptation.md`	Adjust context based on task complexity and model confidence.
11	Meta-Context	`11-meta-context.md`	Explain why information is provided. Use grounding directives to reduce hallucinations.
12	Ground Agents in Environment Feedback	`12-ground-in-environment.md`	Use tool results and human checkpoints, not just model reasoning.
13	Test and Measure Systematically	`13-test-and-measure.md`	A/B test context variations. Measure accuracy, latency, reasoning quality.
14	Retrieve Generously, Filter Late	`14-retrieve-generously.md`	Top-20 chunks outperform top-5. Don't over-filter prematurely.
15	Avoid Common Anti-Patterns	`15-anti-patterns.md`	Don't dump everything, over-abstract, overengineer, or inherit stale aggressive prompts.
16	Guide Model Thinking	`16-guide-model-thinking.md`	Control reasoning depth with adaptive thinking. Prevent overthinking on simple tasks.
17	Multi-Window State Management	`17-multi-window-state.md`	Externalize state for tasks spanning multiple context windows.
18	Calibrate Autonomy and Safety	`18-calibrate-autonomy.md`	Tune action thresholds. Claude 4.6 defaults to high autonomy; set guardrails.