Context Engineering Skills: a Claude Code skill by Muratcan Koylan
For engineers building agent systems who want written guidance on context, memory and evaluation. Skip it if you want a tool that runs tasks rather than a set of explanations.
High-risk warning At least one scanner rated it high risk, so we keep it out of the top ten. Read its code before you install it.
- Score
- 58of 100
- Rank
- #228of 239
- Installs
- 9.5Kon skills.sh
- Stars
- 18.3Kon GitHub
- Security
- Warning 5 scanners
- Updated
- 2026
- Context
- ~79tokens always
Install
npx skills add https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering
Run it in your terminal. View the source
Most people install it straight from GitHub, where it has 18.3K stars, so its skills.sh count understates how widely it is used.
Using the Claude app rather than Claude Code? You can add a skill there too. How to add it in the app
What does Context Engineering Skills do?
Context Engineering Skills is a set of 24 skills that explain how to design agent systems around what reaches the model's context. The collection skill is a map pointing to members such as context-fundamentals, context-degradation, context-compression, memory-systems, tool-design, multi-agent-patterns, harness-engineering and evaluation. They cover the lost-in-the-middle effect, observation masking, sub-agents used to isolate context, the filesystem as memory, and harness rules like locked metrics and rollback. Niche members include BDI mental states, latent briefing through shared KV cache, and a book SFT pipeline. The collection file itself is guidance and runs no commands.
It comes as a set of skills that work together:
- Agent-Skills-for-Context-Engineering
- advanced-evaluation (185 installs)
- bdi-mental-states (160 installs)
- book-sft-pipeline (94 installs)
- comprehensive-research-agent (123 installs)
- context-compression (549 installs)
- context-degradation (279 installs)
- context-fundamentals (250 installs)
- context-optimization (432 installs)
- digital-brain-skill
- evaluation (259 installs)
- filesystem-context (376 installs)
When should you use Context Engineering Skills?
Use it when
- Your agent loses track as its context grows
- You are choosing between multi-agent layouts
- You need an evaluation rubric for agent runs
Skip it when
- You want a skill that does a task for you
- You are not building or tuning agents
Why it scores 58
Strongest on quality (85 of 100), weakest on adoption (37).
Is Context Engineering Skills safe to install?
At least one scanner rated it high risk, so we keep it out of the top ten. Read its code before you install it. Scanners often miss what other scanners catch, and a skill can change after a scan. Read its source before you install it.
| Scanner | Result | Date |
|---|---|---|
| Gen Agent Trust Hub | Medium risk | Oct 1, 2026 |
| Socket | Medium risk | Oct 1, 2026 |
| Snyk | Low risk | Oct 1, 2026 |
| Runlayer | High risk | Mar 12, 2026 |
| ZeroLeaks | Medium risk | Apr 16, 2026 |
Details
- Installs
- 9,472
- Repository stars
- 18,333
- Last repository change
- Tokens always loaded
- about 79
- Tokens when used
- about 2,714
- License
- MIT
- Data confidence
- High
Did it do the job for you?
Alternatives to Context Engineering Skills
All skills for this job-
Get mastramastra
For TypeScript developers building agents and workflows with Mastra who want Claude to check current APIs first.
-
Get Google Agents CLIGoogle Agents CLI
For developers building AI agents with Google's ADK who want guidance from scaffold to deploy.
-
Get developing-genkit-jsdeveloping-genkit-js
For TypeScript developers building AI flows or agents with Genkit who want Claude to use current APIs.
-
Get deep-agents-memorydeep-agents-memory
For developers building LangChain Deep Agents that need to remember things between threads.
Context Engineering Skills
Get Context Engineering Skills