recursive-decomposition-skill
A Claude Code skill/plugin that applies recursive decomposition strategies (filtering, chunking, parallel sub-agenting, verification, and synthesis) to improve handling of long-context tasks such as multi-file codebase analysis and multi-document aggregation.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
No server/network interface, TLS, auth, or secret-handling details are provided in the supplied content. As an agent skill operating on code/documents, the main security considerations are ensuring sensitive data handling is appropriate within the Claude Code environment and being cautious about exposing proprietary code to any external services the skill/underlying platform might call (not described here). Dependency hygiene is unknown from the provided material; a neutral score is used.
⚡ Reliability
Best When
When Claude Code needs broader coverage than the context window can comfortably handle, especially for 10+ files / large token sets requiring synthesis and verification.
Avoid When
When tasks are small/specific (e.g., grep-like lookups) or latency/cost must be minimized over completeness.
Use Cases
- • Analyze large codebases across many files (e.g., find patterns, anti-patterns, or API usages)
- • Multi-document question answering and evidence aggregation
- • Long-context summarization and synthesis (e.g., across 50+ documents)
- • Codebase-wide feature extraction (e.g., endpoints, TODOs, vulnerability surface)
Not For
- • Single-file edits or narrow tasks where direct processing is faster
- • Time-critical operations where added decomposition latency/cost is undesirable
- • Tasks under ~30k tokens where overhead may not pay off
Interface
Authentication
No authentication scheme is described in the provided content; as a Claude Code skill, it likely runs within the Claude Code environment rather than exposing its own external API.
Pricing
No pricing information for the plugin is provided in the supplied README content.
Agent Metadata
Known Gotchas
- ⚠ This skill is triggered by intent/phrasing patterns (e.g., 'analyze all files', 'search across the codebase'); unexpected trigger wording may prevent it from activating.
- ⚠ The workflow adds decomposition/parallelization overhead; for small tasks it may reduce efficiency versus direct answers.
- ⚠ The provided README discusses strategies at a conceptual level but does not describe deterministic output schemas or tool-level contracts that an agent could rely on.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for recursive-decomposition-skill.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.