recursive-decomposition

Recursive Decomposition Skill

Handle long-context tasks with Claude Code through recursive decomposition

What It Does • Installation • Usage • How It Works • Benchmarks • Acknowledgments

---

The Problem

When analyzing large codebases, processing many documents, or aggregating information across dozens of files, Claude's context window becomes a bottleneck. As context grows, "context rot" degrades performance:

• Missed details in long documents
• Decreased accuracy on information retrieval
• Hallucinated connections between distant content
• Degraded reasoning over large evidence sets

The Solution

This skill implements Recursive Language Model (RLM) strategies from Zhang, Kraska, and Khattab's 2025 research, enabling Claude Code to handle inputs up to 2 orders of magnitude beyond normal context limits.

Instead of cramming everything into context, Claude learns to:

1. Filter — Narrow search space before deep analysis
2. Chunk — Partition inputs strategically
3. Recurse — Spawn sub-agents for independent segments
4. Verify — Re-check answers on smaller, focused windows
5. Synthesize — Aggregate results programmatically

---

What It Does

Task Type	Without Skill	With Skill
Analyze 100+ files	Context overflow / degraded results	Systematic coverage via decomposition
Multi-document QA	Missed information	Comprehensive extraction
Codebase-wide search	Manual iteration	Parallel sub-agent analysis
Information aggregation	Incomplete synthesis	Map-reduce pattern

Real Test Results

We tested on the Anthropic Cookbook (196 files, 356MB):

Task: "Find all Anthropic API calling patterns across the codebase"

Results:
├── Files scanned: 142
├── Files with API calls: 18
├── Patterns identified: 8 distinct patterns
├── Anti-patterns detected: 4
└── Output: Comprehensive report with file:line references

---

Installation

Via Claude Code Marketplace

# Add the marketplace
claude plugin marketplace add massimodeluisa/recursive-decomposition-skill

# Install the plugin
claude plugin install recursive-decomposition@recursive-decomposition

From Local Clone

# Clone the repository
git clone https://github.com/massimodeluisa/recursive-decomposition-skill.git ~/recursive-decomposition-skill

# Add as local marketplace
claude plugin marketplace add ~/recursive-decomposition-skill

# Install the plugin
claude plugin install recursive-decomposition

Manual Installation (Skills Directory)

# Copy skill directly to Claude's skills directory
cp -r plugins/recursive-decomposition/skills/recursive-decomposition ~/.claude/skills/

After installation, restart Claude Code for the skill to take effect.

Updating

# Update marketplace index
claude plugin marketplace update

# Update the plugin
claude plugin update recursive-decomposition@recursive-decomposition

---

Usage

The skill activates automatically when you describe tasks involving:

• Large-scale file analysis ("analyze all files in...")
• Multi-document processing ("aggregate information from...")
• Codebase-wide searches ("find all occurrences across...")
• Long-context reasoning ("summarize these 50 documents...")

Example Prompts

"Analyze error handling patterns across this entire codebase"

"Find all TODO comments in the project and categorize by priority"

"What API endpoints are defined across all route files?"

"Summarize the key decisions from all meeting notes in /docs"

"Find security vulnerabilities across all Python files"

Trigger Phrases

The skill recognizes these patterns:

• "analyze all files"
• "process this large document"
• "aggregate information from"
• "search across the codebase"
• Tasks involving 10+ files or 50k+ tokens

---

When to Use