Context Engineering
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.
Install
npx skills add claudekit/skillmark --skill context-engineeringgit clone --depth 1 https://github.com/claudekit/skillmark.git /tmp/skillmark
mkdir -p ~/.claude/skills
cp -r /tmp/skillmark/demo/.claude/skills/ck-context-engineering ~/.claude/skills/context-engineeringPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Context Engineering Context engineering curates the smallest high-signal token set for LLM tasks. The goal: maximize reasoning quality while minimizing token usage. ## When to Activate - Designing/debugging agent systems - Context limits constrain performance - Optimizing cost/latency - Building multi-agent coordination - Implementing memory systems - Evaluating agent performance - Developing LLM-powered pipelines ## Core Principles 1. **Context quality > quantity** - High-signal tokens beat exhaustive content 2. **Attention is finite** - U-shaped curve favors beginning/end positions 3. **Progressive disclosure** - Load information just-in-time 4. **Isolation prevents degradation** - Partition work across sub-agents 5. **Measure before optimizing** - Know your baseline **IMPORTANT:** - Sacrifice grammar for the sake of concision. - Ensure token efficiency while maintaining high quality. - Pass these rules to subagents. ## Quick Reference | Topic | Key Terms | Reference | |-------|-----------|-----------| | **Fundamentals** | context anatomy, attention mechanics, position encoding | [context-fundamentals.md](./references/context-fundamentals.md) | | **Degradation** | lost-in-middle, poisoning, attention decay | [context-degradation.md](./references/context-degradation.md) | | **Optimization** | compaction, **observation masking**, **KV-cache**, prefix caching | [context-optimization.md](./references/context-optimization.md) |
Details
- Skill name
context-engineering- Repository
- claudekit/skillmark
- Path
demo/.claude/skills/ck-context-engineering/SKILL.md- Repo updated
- 23 September 2026
FAQ
What does the Context Engineering skill do?
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.
How do I install the Context Engineering skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add claudekit/skillmark --skill context-engineering. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Context Engineering popular?
It lives in claudekit/skillmark, which has 9 GitHub stars and 4 forks.
Related skills
Benchmark Fileops
9claudekit/skillmark
Execute 21-step file operations workflow for benchmarking prompt adherence. Use for Skills vs Commands comparison testing.
Brainstorm
9claudekit/skillmark
Brainstorm solutions with trade-off analysis and brutal honesty. Use for ideation, architecture decisions, technical debates, feature exploration, feasibility assessment, design discussions.
Code Review
9claudekit/skillmark
Review code quality, receive feedback with technical rigor, verify completion claims. Use before PRs, after implementing features, when claiming task completion, for subagent reviews.
Coti Transaction Tools
9coti-io/coti-skills
Monitors transactions, decodes events, manages native COTI tokens, and signs messages. Use when user asks to 'check transaction', 'transaction status', 'decode event', 'native balance', 'transfer COTI', 'send COTI', 'sign message', 'verify signature', or 'transaction logs'. Utility toolkit for on-chain debugging and native token operations.
Computer Use CLI
9TwillAI/skills
Automate and test Linux desktop apps (Electron, Tauri, React Native Desktop) in an X11 session using CLI commands for screenshot + mouse + keyboard. Includes coordinate scaling so you can click/type based on a smaller “API-sized” screenshot.
Duvo CLI
9duvoai/skills
Drive the Duvo public API from the terminal via the `duvo` CLI (`@duvoai/cli`). Use when the user wants to script Duvo — managing automations, Policy, agents, runs, cases, queues, files, skills, connections, Clarity processes, Pulse dashboards, or hitting an arbitrary endpoint via `duvo api` — instead of clicking through the Duvo web UI or hand-crafting `curl` calls.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.