Master context engineering operations

context-engineeringskillsetup L22,280
rohitg00/pro-workflow
What it does

Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.

Best for

Optimizing large AI sessions by partitioning work across execution spaces and compacting without losing critical state.

Inputs
  • · 1. Start complex task → create NOTES.md with goals and constraints 2. After research → write findings to NOTES.md 3. After compaction → NOTES.md survives, context does not 4. Resume → read NOTES.md to
  • · 1. Start with file names (Glob) 2. Narrow to specific functions (Grep) 3. Read only the relevant lines (Read with offset+limit) 4. Never read entire large files when you need one function
  • · { "type": "PostCompact", "command": "cat .claude/critical-context.md" }
Outputs
  • · Reactive state store
  • · Type-safe store instance
Preconditions

Data model understood, valid input structure

Failure modes

Missed gotchas, misunderstood patterns, misconfiguration

Trust signals
  • · Documented examples
  • · Testing guidance included