iLearn-Lab

Long Context Retrieval — Development skill for Claude Code

Development community

Read large files and broad search results progressively instead of blowing up the live context window.

How to install Long Context Retrieval

Installs to ~/.claude/skills/ilearn-lab-evoharness-long-context-retrieval/SKILL.md

Terminal
mkdir -p ~/.claude/skills/ilearn-lab-evoharness-long-context-retrieval && curl -fsSL https://raw.githubusercontent.com/iLearn-Lab/EvoHarness/HEAD/.claude/skills/long-context-retrieval.md -o ~/.claude/skills/ilearn-lab-evoharness-long-context-retrieval/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Long Context Retrieval does


name: long-context-retrieval description: Read large files and broad search results progressively instead of blowing up the live context window.

Long Context Retrieval

Use this skill when the task needs large-file reading, deep codebase explanation, or long search sessions.

  • start with workspace_status or list_registry only once, then narrow down
  • prefer grep before read_file when you do not yet know the exact window
  • for large files, read the first segment, then request

Alternatives in Development

  • Obsidian Find — Smart vault search — returns results with context, not just filenames 277 ★
  • Ccr — CCR (Compressed Context with Retrieval) — recall the full original of context that great_cto compressed/filter 83 ★
  • Toonify MCP — Context compression plugin for Claude Code 65 ★

Full documentation available on GitHub

View Source Repository