Context Engineering teaches an agent and its user to curate the information in a session. It ranks context from rules files down to conversation history and says what to load at each level.
The skill covers restartable session boundaries, three packing strategies, context budget management, MCP integrations and patterns for surfacing conflicts and missing requirements.
What You Get
- A five-level context hierarchy
- A rules file template and the names of the equivalent files for other agents
- Packing strategies: brain dump, selective include and hierarchical summary
- Restartable session rules, anti-pattern table and a verification checklist
Common Use Cases
- Starting a coding session with the right context
- Recovering when output quality drops
- Writing a rules file for a project
- Handing work to a fresh session
What Makes It Unique
The skill adds session boundary rules that name what to persist before a restart, a recency rule that places the active task material last, and explicit trust levels for loaded files. It also gives a format for raising spec conflicts to the user in place of silently choosing.
Under The Hood
The skill is a single SKILL.md of instructions and templates. It runs no scripts. It points the agent to read rules files, specs, source files and git status, and it lists MCP servers such as Context7, Chrome DevTools, PostgreSQL, Filesystem and GitHub that supply extra context.